diff --git a/ar-SA/images/12_or_330.gif b/ar-SA/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/ar-SA/images/12_or_330.gif differ diff --git a/ar-SA/images/banner.png b/ar-SA/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/ar-SA/images/banner.png differ diff --git a/ar-SA/images/bee_or_berry.gif b/ar-SA/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/ar-SA/images/bee_or_berry.gif differ diff --git a/ar-SA/images/cake_or_biscuit.gif b/ar-SA/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/ar-SA/images/cake_or_biscuit.gif differ diff --git a/ar-SA/images/five_or_three.gif b/ar-SA/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/ar-SA/images/five_or_three.gif differ diff --git a/ar-SA/images/train_model.png b/ar-SA/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/ar-SA/images/train_model.png differ diff --git a/ar-SA/images/wywm.png b/ar-SA/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/ar-SA/images/wywm.png differ diff --git a/ar-SA/meta.yml b/ar-SA/meta.yml new file mode 100644 index 0000000..abf9e1e --- /dev/null +++ b/ar-SA/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: What you will make + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Challenge + challenge: true + completion: + - external diff --git a/ar-SA/resources/Teach a machine 1.srt b/ar-SA/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/ar-SA/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/ar-SA/resources/readme.txt b/ar-SA/resources/readme.txt new file mode 100644 index 0000000..0e0956c --- /dev/null +++ b/ar-SA/resources/readme.txt @@ -0,0 +1 @@ +To watch a video with subtitles on VLC (videolan.org), ensure the video file and subtitle file are in the same folder and have the exact same name (e.g., video.mp4 and video.srt). Open the video in VLC, and it will automatically load the subtitles. If the subtitles don’t appear, right-click the video screen, go to **Subtitle**, then **Add Subtitle File**, and select the correct .srt file. Enjoy watching with subtitles! \ No newline at end of file diff --git a/ar-SA/resources/teach a machine 2.srt b/ar-SA/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/ar-SA/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/ar-SA/step_1.md b/ar-SA/step_1.md new file mode 100644 index 0000000..d2e1ce6 --- /dev/null +++ b/ar-SA/step_1.md @@ -0,0 +1,27 @@ +## What you will make + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## title: No YouTube? Download the videos! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/ar-SA/step_2.md b/ar-SA/step_2.md new file mode 100644 index 0000000..2fb7b0e --- /dev/null +++ b/ar-SA/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- /task --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- diff --git a/ar-SA/step_3.md b/ar-SA/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/ar-SA/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/ar-SA/step_4.md b/ar-SA/step_4.md new file mode 100644 index 0000000..adbc2be --- /dev/null +++ b/ar-SA/step_4.md @@ -0,0 +1,36 @@ +## Challenge + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/ar-SA/step_5.md b/ar-SA/step_5.md new file mode 100644 index 0000000..5fde839 --- /dev/null +++ b/ar-SA/step_5.md @@ -0,0 +1,3 @@ +## What can you do now? + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/cy-GB/images/12_or_330.gif b/cy-GB/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/cy-GB/images/12_or_330.gif differ diff --git a/cy-GB/images/banner.png b/cy-GB/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/cy-GB/images/banner.png differ diff --git a/cy-GB/images/bee_or_berry.gif b/cy-GB/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/cy-GB/images/bee_or_berry.gif differ diff --git a/cy-GB/images/cake_or_biscuit.gif b/cy-GB/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/cy-GB/images/cake_or_biscuit.gif differ diff --git a/cy-GB/images/five_or_three.gif b/cy-GB/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/cy-GB/images/five_or_three.gif differ diff --git a/cy-GB/images/train_model.png b/cy-GB/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/cy-GB/images/train_model.png differ diff --git a/cy-GB/images/wywm.png b/cy-GB/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/cy-GB/images/wywm.png differ diff --git a/cy-GB/meta.yml b/cy-GB/meta.yml new file mode 100644 index 0000000..abf9e1e --- /dev/null +++ b/cy-GB/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: What you will make + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Challenge + challenge: true + completion: + - external diff --git a/cy-GB/resources/Teach a machine 1.srt b/cy-GB/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/cy-GB/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/cy-GB/resources/readme.txt b/cy-GB/resources/readme.txt new file mode 100644 index 0000000..0e0956c --- /dev/null +++ b/cy-GB/resources/readme.txt @@ -0,0 +1 @@ +To watch a video with subtitles on VLC (videolan.org), ensure the video file and subtitle file are in the same folder and have the exact same name (e.g., video.mp4 and video.srt). Open the video in VLC, and it will automatically load the subtitles. If the subtitles don’t appear, right-click the video screen, go to **Subtitle**, then **Add Subtitle File**, and select the correct .srt file. Enjoy watching with subtitles! \ No newline at end of file diff --git a/cy-GB/resources/teach a machine 2.srt b/cy-GB/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/cy-GB/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/cy-GB/step_1.md b/cy-GB/step_1.md new file mode 100644 index 0000000..d2e1ce6 --- /dev/null +++ b/cy-GB/step_1.md @@ -0,0 +1,27 @@ +## What you will make + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## title: No YouTube? Download the videos! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/cy-GB/step_2.md b/cy-GB/step_2.md new file mode 100644 index 0000000..2fb7b0e --- /dev/null +++ b/cy-GB/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- /task --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- diff --git a/cy-GB/step_3.md b/cy-GB/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/cy-GB/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/cy-GB/step_4.md b/cy-GB/step_4.md new file mode 100644 index 0000000..adbc2be --- /dev/null +++ b/cy-GB/step_4.md @@ -0,0 +1,36 @@ +## Challenge + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/cy-GB/step_5.md b/cy-GB/step_5.md new file mode 100644 index 0000000..5fde839 --- /dev/null +++ b/cy-GB/step_5.md @@ -0,0 +1,3 @@ +## What can you do now? + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/de-DE/images/12_or_330.gif b/de-DE/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/de-DE/images/12_or_330.gif differ diff --git a/de-DE/images/banner.png b/de-DE/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/de-DE/images/banner.png differ diff --git a/de-DE/images/bee_or_berry.gif b/de-DE/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/de-DE/images/bee_or_berry.gif differ diff --git a/de-DE/images/cake_or_biscuit.gif b/de-DE/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/de-DE/images/cake_or_biscuit.gif differ diff --git a/de-DE/images/five_or_three.gif b/de-DE/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/de-DE/images/five_or_three.gif differ diff --git a/de-DE/images/train_model.png b/de-DE/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/de-DE/images/train_model.png differ diff --git a/de-DE/images/wywm.png b/de-DE/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/de-DE/images/wywm.png differ diff --git a/de-DE/meta.yml b/de-DE/meta.yml new file mode 100644 index 0000000..24faf1f --- /dev/null +++ b/de-DE/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-06" +steps: + - + title: Das wirst du machen + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Herausforderung + challenge: true + completion: + - external diff --git a/de-DE/resources/Teach a machine 1.srt b/de-DE/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/de-DE/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/de-DE/resources/readme.txt b/de-DE/resources/readme.txt new file mode 100644 index 0000000..11e75ad --- /dev/null +++ b/de-DE/resources/readme.txt @@ -0,0 +1 @@ +Um ein Video mit Untertiteln auf VLC (videolan. rg), stelle sicher, dass sich die Videodatei und die Untertiteldatei im selben Ordner befinden, und genau den gleichen Namen haben (z.B. video.mp4 und video.srt). Öffne das Video in VLC, und es wird automatisch die Untertitel laden. Wenn die Untertitel nicht erscheinen, klicke mit der rechten Maustaste auf den Videobildschirm, klicke auf **Untertitel**, dann **Untertiteldatei hinzufügen** und wähle die korrekte .srt-Datei aus. Viel Spaß beim Anschauen mit Untertiteln! \ No newline at end of file diff --git a/de-DE/resources/teach a machine 2.srt b/de-DE/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/de-DE/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/de-DE/step_1.md b/de-DE/step_1.md new file mode 100644 index 0000000..e1af016 --- /dev/null +++ b/de-DE/step_1.md @@ -0,0 +1,27 @@ +## Das wirst du machen + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## Titel: Kein YouTube? Video downloaden! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/de-DE/step_2.md b/de-DE/step_2.md new file mode 100644 index 0000000..d9eb4f2 --- /dev/null +++ b/de-DE/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- / aufgabe --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- / aufgabe --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- / aufgabe --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- / aufgabe --- diff --git a/de-DE/step_3.md b/de-DE/step_3.md new file mode 100644 index 0000000..327500b --- /dev/null +++ b/de-DE/step_3.md @@ -0,0 +1,37 @@ +## Trainieren des Modells + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- / aufgabe --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- / aufgabe --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- / aufgabe --- diff --git a/de-DE/step_4.md b/de-DE/step_4.md new file mode 100644 index 0000000..ee8ec27 --- /dev/null +++ b/de-DE/step_4.md @@ -0,0 +1,36 @@ +## Herausforderung + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- / aufgabe --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- / aufgabe --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/de-DE/step_5.md b/de-DE/step_5.md new file mode 100644 index 0000000..526a4e2 --- /dev/null +++ b/de-DE/step_5.md @@ -0,0 +1,3 @@ +## Was kannst du jetzt tun? + +Es gibt viele weitere Projekte zum maschinellen Lernen und zur KI im Toolkit für [künstliche Intelligenz](https://projects.raspberrypi.org/en/pathways/ai-toolkit). \ No newline at end of file diff --git a/el-GR/images/12_or_330.gif b/el-GR/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/el-GR/images/12_or_330.gif differ diff --git a/el-GR/images/banner.png b/el-GR/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/el-GR/images/banner.png differ diff --git a/el-GR/images/bee_or_berry.gif b/el-GR/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/el-GR/images/bee_or_berry.gif differ diff --git a/el-GR/images/cake_or_biscuit.gif b/el-GR/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/el-GR/images/cake_or_biscuit.gif differ diff --git a/el-GR/images/five_or_three.gif b/el-GR/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/el-GR/images/five_or_three.gif differ diff --git a/el-GR/images/train_model.png b/el-GR/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/el-GR/images/train_model.png differ diff --git a/el-GR/images/wywm.png b/el-GR/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/el-GR/images/wywm.png differ diff --git a/el-GR/meta.yml b/el-GR/meta.yml new file mode 100644 index 0000000..b0de4bb --- /dev/null +++ b/el-GR/meta.yml @@ -0,0 +1,23 @@ +title: Δίδαξε μια μηχανή +hero_image: images/banner.png +description: Δίδαξε έναν υπολογιστή να σου λέει πόσα δάχτυλα δείχνεις! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: Τι θα φτιάξεις + - + title: Προσθήκη εικόνων + completion: + - engaged + - + title: Εκπαίδευση και δοκιμή + completion: + - internal + - + title: Πρόκληση + challenge: true + completion: + - external diff --git a/el-GR/resources/Teach a machine 1.srt b/el-GR/resources/Teach a machine 1.srt new file mode 100644 index 0000000..73e1e2c --- /dev/null +++ b/el-GR/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Πήγαινε στο rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +και μετονόμασε τις 'Class 1' και +'Class 2' σε 'Five' και 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Κάνε κλικ στο 'Webcam' στην κλάση Five + +4 +00:00:13,040 --> 00:00:14,760 +και κράτησε ψηλά πέντε δάχτυλα + +5 +00:00:14,760 --> 00:00:19,240 +Με το άλλο σου χέρι, πάτα παρατεταμένα +το κουμπί 'Hold to record' + +6 +00:00:19,240 --> 00:00:21,680 +για να συγκεντρώσεις πολλές εικόνες + +7 +00:00:21,680 --> 00:00:24,360 +Πήγαινε στην κλάση 'Three' +και συγκέντρωσε πολλές εικόνες + +8 +00:00:24,360 --> 00:00:29,200 +κρατώντας μποστά στην κάμερα τα 3 δάχτυλα του χεριού σου + diff --git a/el-GR/resources/readme.txt b/el-GR/resources/readme.txt new file mode 100644 index 0000000..3289b81 --- /dev/null +++ b/el-GR/resources/readme.txt @@ -0,0 +1 @@ +Για να παρακολουθήσεις ένα βίντεο με υπότιτλους στο VLC (videolan.org), βεβαιώσου ότι το αρχείο βίντεο και το αρχείο υποτίτλων βρίσκονται στον ίδιο φάκελο και έχουν το ίδιο ακριβώς όνομα (π.χ. video.mp4 και video.srt). Άνοιξε το βίντεο σε VLC και θα φορτώσει αυτόματα τους υπότιτλους. Εάν οι υπότιτλοι δεν εμφανίζονται, κάνε δεξί κλικ στην οθόνη του βίντεο, πήγαινε στο **Υπότιτλοι**, μετά στο **Προσθήκη αρχείου υποτίτλων** και επίλεξε το σωστό αρχείο .srt. Απόλαυσε την παρακολούθηση με υπότιτλους! \ No newline at end of file diff --git a/el-GR/resources/teach a machine 2.srt b/el-GR/resources/teach a machine 2.srt new file mode 100644 index 0000000..c46c7bd --- /dev/null +++ b/el-GR/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Κάνε κλικ στο 'Train model' και περίμενε... + +2 +00:00:05,320 --> 00:00:08,920 +γιατί μπορεί να χρειαστούν δέκα έως +είκοσι δευτερόλεπτα για να ολοκληρωθεί + +3 +00:00:08,920 --> 00:00:12,800 +Όταν το μοντέλο σου εκπαιδευτεί, +θα ανοίξει ο πίνακας προεπισκόπησης + +4 +00:00:12,800 --> 00:00:18,200 +Κράτα ψηλά πέντε και τρία δάχτυλα και παρακολούθησε +τις βαθμολογίες εμπιστοσύνης στην παρακάτω έξοδο (output). + +5 +00:00:18,200 --> 00:00:21,440 +Γιατί να μην δούμε αν μπορεί να αναγνωρίσει κέικ ή μπισκότα; + +6 +00:00:21,440 --> 00:00:27,200 +Ή μέλισσες και μούρα; + diff --git a/el-GR/step_1.md b/el-GR/step_1.md new file mode 100644 index 0000000..ce04d07 --- /dev/null +++ b/el-GR/step_1.md @@ -0,0 +1,27 @@ +## Τι θα φτιάξεις + +![Η εικόνα δείχνει μια διεπαφή μηχανικής εκμάθησης από το "Teachable Machine" όπου ένα μοντέλο εκπαιδεύεται να αναγνωρίζει χειρονομίες για τους αριθμούς 5 και 3 ("Five" και "Three"). Στα δεξιά, στην ενότητα "Preview", η εικόνα της κάμερας εμφανίζει ένα χέρι που δείχνει τρία δάχτυλα. Κάτω από αυτό, η ενότητα "Output" εμφανίζει τα αποτελέσματα ταξινόμησης, με το μοντέλο να προβλέπει με πιθανότητα 94% ότι είναι "Three" και μια μικρή πιθανότητα 6% ότι είναι "Five". Το μοντέλο αναγνώρισε με επιτυχία τη χειρονομία ως "Three."](images/wywm.png) + +Θα διδάξεις έναν υπολογιστή να σου λέει πόσα δάχτυλα δείχνεις! + +\--- collapse --- + +--- + +## title: Πού αποθηκεύονται οι εικόνες μου; + +- Αυτό το έργο χρησιμοποιεί μια τεχνολογία που ονομάζεται «μηχανική μάθηση». Τα συστήματα μηχανικής μάθησης εκπαιδεύονται χρησιμοποιώντας μεγάλο όγκο δεδομένων. +- Αυτό το έργο δεν απαιτεί να δημιουργήσεις λογαριασμό ή να συνδεθείς. Γι' αυτό το έργο, τα παραδείγματα εικόνων που χρησιμοποιείς για να δημιουργήσεις το μοντέλο αποθηκεύονται μόνο προσωρινά στο πρόγραμμα περιήγησής σου (μόνο στον υπολογιστή σου). +- Δεν αποστέλλονται εικόνες από την κάμερα web σε αυτόν τον ιστότοπο ή σε οποιονδήποτε άλλο ιστότοπο. + +\--- /collapse --- + +Θα χρειαστείς μια **κάμερα web**. + +## --- collapse --- + +## title: Δεν υπάρχει πρόβαση στο YouTube; Κάνε λήψη των βίντεο! + +Μπορείς να [κατεβάσεις όλα τα βίντεο γι' αυτό το έργο](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/el-GR/step_2.md b/el-GR/step_2.md new file mode 100644 index 0000000..e85b011 --- /dev/null +++ b/el-GR/step_2.md @@ -0,0 +1,54 @@ +## Προσθήκη εικόνων + + +
+

+
+ + +\--- task --- + +Άνοιξε το [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Κάθε κλάση είναι μια κατηγορία που θέλεις να αναγνωρίσει ο υπολογιστής. + +\--- task --- + +- Μετονόμασε το `Class 1` σε `Five` +- Μετονόμασε το `Class 2` σε `Three` + +\--- /task --- + +Συγκέντρωσε εικόνες από τα «πέντε» δάχτυλα. + +\--- task --- + +- Κάνε κλικ στο **Webcam** στην κλάση `Five` +- Κράτα ψηλά πέντε δάχτυλα μπροστά από την κάμερα web (βεβαιώσου ότι φαίνεται ολόκληρο το χέρι σου) +- Με το άλλο σου χέρι, πάτα παρατεταμένα το κουμπί **Hold to Record** για να συγκεντρώσεις πολλές εικόνες + +\--- /task --- + +\--- collapse --- + +--- + +## title: Πού αποθηκεύονται οι εικόνες μου; + +- Κανένα από τα δεδομένα σου δεν αποθηκεύεται ούτε αποστέλλεται σε αυτόν ή σε οποιονδήποτε άλλο ιστότοπο. +- Η τεχνολογία ονομάζεται «μηχανική μάθηση», αλλά δεν μαθαίνει όσο τη χρησιμοποιείς. +- Έχει ήδη εκπαιδευτεί χρησιμοποιώντας μεγάλο αριθμό φωτογραφιών. + +\--- /collapse --- + +Συγκέντρωσε εικόνες από τα «τρία» δάχτυλα. + +\--- task --- + +- Κάνε κλικ στο **Webcam** στην κλάση `Three` +- Κράτα ψηλά τρία δάχτυλα μπροστά από την κάμερα web (βεβαιώσου ότι φαίνεται ολόκληρο το χέρι σου) +- Με το άλλο σου χέρι, πάτα παρατεταμένα το κουμπί **Hold to Record** για να συγκεντρώσεις πολλές εικόνες + +\--- /task --- diff --git a/el-GR/step_3.md b/el-GR/step_3.md new file mode 100644 index 0000000..c70cde0 --- /dev/null +++ b/el-GR/step_3.md @@ -0,0 +1,37 @@ +## Εκπαίδευση του μοντέλου + + +
+

+
+ + +\--- task --- + +Κάνε κλικ στο **Train Model**. + +![Το κουμπί 'Train Model'.](images/train_model.png) + +\--- /task --- + +**Σημείωση**: Κάνε υπομονή! Μπορεί να χρειαστούν 10 έως 20 δευτερόλεπτα για να ολοκληρωθεί. + +### Προεπισκόπηση και δοκιμή + +Όταν το μοντέλο σου εκπαιδευτεί, θα ανοίξει ο πίνακας προεπισκόπησης. + +\--- task --- + +- Κράτα ψηλά **πέντε** δάχτυλα και παρακολούθησε την ενότητα 'Output' κάτω από την προεπισκόπηση. + +Θα δείτε βαθμολογίες εμπιστοσύνης για `Five` και `Three`. + +\--- /task --- + +\--- task --- + +- Κράτα ψηλά **τρία** δάχτυλα +- Ποια είναι η υψηλότερη βαθμολογία εμπιστοσύνης που μπορείς να πάρεις για το `Five`; +- Ποια είναι η υψηλότερη βαθμολογία εμπιστοσύνης που μπορείς να πάρεις για το `Three`; + +\--- /task --- diff --git a/el-GR/step_4.md b/el-GR/step_4.md new file mode 100644 index 0000000..cdf5f5d --- /dev/null +++ b/el-GR/step_4.md @@ -0,0 +1,36 @@ +## Πρόκληση + +\--- challenge --- + +Δημιούργησε τον δικό σου ταξινομητή! + +### Μέλισσα ή μούρο; + +\--- task --- + +Μια φορά κατά λάθος έφαγα μια μέλισσα. Δίδαξε μια μηχανή για να σε προστατεύει! + +![Η εικόνα μιας μέλισσας μπροστά σε μια κάμερα web. Στη συνέχεια, μια εικόνα ενός μούρου. Στον πίνακα εξόδου κάτω από το βίντεο, εμφανίζεται η βαθμολογία εμπιστοσύνης ως προς το εάν εμφανίζεται μια μέλισσα ή ένα μούρο.](images/bee_or_berry.gif) + +\--- /task --- + +### Κέικ ή μπισκότο; + +\--- task --- + +Θέσε το ερώτημα. + +![Ένα κομμάτι κέικ μπροστά από μια web κάμερα. Μετά, ένα μπισκότο. Στον πίνακα εξόδου κάτω από το βίντεο, εμφανίζεται η βαθμολογία εμπιστοσύνης ως προς το εάν εμφανίζεται κέικ ή ένα μπισκότο.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Αναγνώριση αντίστασης + +\--- task --- + +Λύσε ένα πρόβλημα για τους ψηφιακούς κατασκευαστές σε όλον τον κόσμο! + +![Μια αντίσταση 12 ohm μπροστά από μια web κάμερα. Στη συνέχεια, μια αντίσταση 330 ohm. Στον πίνακα εξόδου κάτω από το βίντεο, εμφανίζεται η βαθμολογία εμπιστοσύνης ως προς το εάν εμφανίζεται μια αντίσταση 12 ohm ή 330 ohm.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/el-GR/step_5.md b/el-GR/step_5.md new file mode 100644 index 0000000..674383a --- /dev/null +++ b/el-GR/step_5.md @@ -0,0 +1,3 @@ +## Τι μπορείς να κάνεις τώρα; + +Υπάρχουν πολλά άλλα έργα μηχανικής μάθησης και τεχνητής νοημοσύνης στην εργαλειοθήκη [τεχνητή νοημοσύνη](https://projects.raspberrypi.org/en/pathways/ai-toolkit). \ No newline at end of file diff --git a/es-419/images/12_or_330.gif b/es-419/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/es-419/images/12_or_330.gif differ diff --git a/es-419/images/banner.png b/es-419/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/es-419/images/banner.png differ diff --git a/es-419/images/bee_or_berry.gif b/es-419/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/es-419/images/bee_or_berry.gif differ diff --git a/es-419/images/cake_or_biscuit.gif b/es-419/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/es-419/images/cake_or_biscuit.gif differ diff --git a/es-419/images/five_or_three.gif b/es-419/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/es-419/images/five_or_three.gif differ diff --git a/es-419/images/train_model.png b/es-419/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/es-419/images/train_model.png differ diff --git a/es-419/images/wywm.png b/es-419/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/es-419/images/wywm.png differ diff --git a/es-419/meta.yml b/es-419/meta.yml new file mode 100644 index 0000000..b8803b7 --- /dev/null +++ b/es-419/meta.yml @@ -0,0 +1,23 @@ +title: Enseñar a una máquina +hero_image: images/banner.png +description: '¡Enséñele a una computadora a decirle cuántos dedos tiene levantados!' +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: Lo que harás + - + title: Añadir imágenes + completion: + - comprometido + - + title: Entrenar y probar + completion: + - interno + - + title: Desafío + challenge: true + completion: + - external diff --git a/es-419/resources/Teach a machine 1.srt b/es-419/resources/Teach a machine 1.srt new file mode 100644 index 0000000..5ee5450 --- /dev/null +++ b/es-419/resources/Teach a machine 1.srt @@ -0,0 +1,33 @@ +1 +00:00:02,840 --> 00:00:03,960 +Vaya a rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +y renombre la 'Clase 1' y 'Clase 2' a 'Cinco' y 'Tres' + +3 +00:00:10,880 --> 00:00:13,040 +Haga clic en 'Webcam' en la clase Cinco + +4 +00:00:13,040 --> 00:00:14,760 +y levanta cinco dedos + +5 +00:00:14,760 --> 00:00:19,240 +Con tu otra mano, presiona y +mantén presionado el botón 'Mantén pulsado para grabar' + +6 +00:00:19,240 --> 00:00:21,680 +para reunir un montón de imágenes + +7 +00:00:21,680 --> 00:00:24,360 +Cambia a la clase 'Tres'  y recolecta un montón de imágenes + +8 +00:00:24,360 --> 00:00:29,200 +de ti levantando tres dedos + diff --git a/es-419/resources/readme.txt b/es-419/resources/readme.txt new file mode 100644 index 0000000..9f1f981 --- /dev/null +++ b/es-419/resources/readme.txt @@ -0,0 +1 @@ +Para ver un video con subtítulos en VLC (videolan.org), asegúrese de que el archivo de video y el archivo de subtítulos estén en la misma carpeta y tengan exactamente el mismo nombre (por ejemplo, video.mp4 y video.srt). Abra el video en VLC y cargará automáticamente los subtítulos. Si no aparecen los subtítulos, haga clic derecho en la pantalla de video, vaya a **Subtítulo**, luego a **Agregar archivo de subtítulos** y seleccione el archivo .srt correcto. ¡Disfruta viéndolo con subtítulos! \ No newline at end of file diff --git a/es-419/resources/teach a machine 2.srt b/es-419/resources/teach a machine 2.srt new file mode 100644 index 0000000..69d7de9 --- /dev/null +++ b/es-419/resources/teach a machine 2.srt @@ -0,0 +1,24 @@ +1 +00:00:03,040 --> 00:00:05,320 +Haz clic en "Entrenar modelo" y espera... + +2 +00:00:05,320 --> 00:00:08,920 +porque podría tardar diez a veinte segundos en completarse + +3 +00:00:08,920 --> 00:00:12,800 +Cuando su modelo esté entrenado, se abrirá el panel de vista previa + +4 +00:00:12,800 --> 00:00:18,200 +Levante cinco y tres dedos para observar los puntajes de confianza en el resultado a continuación. + +5 +00:00:18,200 --> 00:00:21,440 +¿Por qué no comprobar si reconoce un pastel o unas galletas? + +6 +00:00:21,440 --> 00:00:27,200 +¿O abejas y bayas? + diff --git a/es-419/step_1.md b/es-419/step_1.md new file mode 100644 index 0000000..8608d1d --- /dev/null +++ b/es-419/step_1.md @@ -0,0 +1,27 @@ +## Lo que harás + +![La imagen muestra una interfaz de aprendizaje automático de "Teachable Machine" donde se está entrenando un modelo para reconocer gestos de las manos para los números "Cinco" y "Tres". A la derecha, en la sección "Vista previa", la transmisión de la cámara web muestra una mano con tres dedos. Debajo de esto, la sección "Salida" muestra los resultados de la clasificación, con el modelo prediciendo una probabilidad del 94% para "Tres" y una pequeña probabilidad del 6% para "Cinco". El modelo ha identificado con éxito el gesto de la mano como "Tres".](images/wywm.png) + +¡Enseñarás a una computadora a decirte cuántos dedos tienes levantados! + +\--- collapse --- + +--- + +## título: ¿Dónde se almacenan mis imágenes? + +- Este proyecto utiliza una tecnología llamada “Machine Learning”. Los sistemas de Machine Learning son entrenados usando una gran cantidad de datos. +- Este proyecto no requiere que usted cree una cuenta o inicie sesión. Para este proyecto, los ejemplos de imágenes que utiliza para crear el modelo solo se almacenan temporalmente en su navegador (solo en su computadora). +- No se envían imágenes de su cámara web a este sitio web ni a ningún otro sitio web. + +\--- /collapse --- + +Necesitarás una **webcam**. + +## --- collapse --- + +## título: ¿No tienes YouTube? ¡Descarga los videos! + +Puedes [descargar todos los vídeos de este proyecto](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/es-419/step_2.md b/es-419/step_2.md new file mode 100644 index 0000000..16875d4 --- /dev/null +++ b/es-419/step_2.md @@ -0,0 +1,54 @@ +## Añadir imágenes + + +
+

+
+ + +\--- task --- + +Abra [Máquina de enseñanza](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Cada clase es una categoría que desea que la computadora reconozca. + +\--- task --- + +- Cambiar el nombre de `Clase 1` a `Cinco` +- Cambiar el nombre de `Clase 2` a `Tres` + +\--- /task --- + +Reúne imágenes de `cinco` dedos. + +\--- task --- + +- Haga clic en **Webcam** en la clase `Cinco` +- Levanta cinco dedos hacia tu cámara web (asegúrate de que toda tu mano esté a la vista) +- Con la otra mano, mantenga presionado el botón **Mantener pulsado para grabar** para recopilar muchas imágenes. + +\--- /task --- + +\--- collapse --- + +--- + +## título: ¿Dónde se almacenan mis imágenes? + +- Ninguno de sus datos se almacena ni se envía a este ni a ningún otro sitio. +- La tecnología se llama 'machine learning', pero no aprende mientras la usas. +- Ya ha sido entrenado usando una gran cantidad de fotografías. + +\--- /collapse --- + +Reúne imágenes de `tres` dedos. + +\--- task --- + +- Haga clic en **'Webcam'** en la clase `Tres` +- Levanta tres dedos hacia tu cámara web (asegúrate de que toda tu mano esté a la vista) +- Con la otra mano, mantenga presionado el botón **Mantener pulsado para grabar** para recopilar muchas imágenes. + +\--- /task --- diff --git a/es-419/step_3.md b/es-419/step_3.md new file mode 100644 index 0000000..2154bc9 --- /dev/null +++ b/es-419/step_3.md @@ -0,0 +1,37 @@ +## Entrena el modelo + + +
+

+
+ + +\--- task --- + +Haga clic en **Entrenar el Modelo**. + +![El botón 'Entrenar el Modelo'.](images/train_model.png) + +\--- /task --- + +**Nota**: ¡Ten paciencia! Puede tardar de 10 a 20 segundos en completarse. + +### Vista previa y prueba + +Cuando su modelo esté entrenado, se abrirá el panel de vista previa. + +\--- task --- + +- Levante **cinco** dedos y mire la sección 'Salida' debajo de la vista previa. + +Verá el indice de confianza para `Cinco` y `Tres`. + +\--- /task --- + +\--- task --- + +- Levanta **tres** dedos +- ¿Cuál es el indice de confianza más alto que puedes obtener para `Cinco`? +- ¿Cuál es el indice de confianza más alto que puedes obtener para `Tres`? + +\--- /task --- diff --git a/es-419/step_4.md b/es-419/step_4.md new file mode 100644 index 0000000..585c385 --- /dev/null +++ b/es-419/step_4.md @@ -0,0 +1,36 @@ +## Desafío + +\--- challenge --- + +¡Crea tu propio clasificador! + +### ¿Abeja o baya? + +\--- task --- + +Una vez me comí una abeja por error. ¡Enséñale a una máquina a mantenerte seguro! + +![Se muestra la imagen de una abeja frente a una cámara web. Luego, una imagen de una baya. En el panel de salida debajo del video, se muestra el indice de confianza que indica si se muestra una abeja o una baya.](images/bee_or_berry.gif) + +\--- /task --- + +### ¿Pastel o galleta? + +\--- task --- + +Resolver la discusión. + +![Se sostiene un trozo de pastel frente a una cámara web. Luego, una galleta. En el panel de salida debajo del video, se muestra el indice de confianza que indica si se muestra un pastel o una galleta.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Reconocimiento de resistencias + +\--- task --- + +¡Resuelve un problema para los creadores digitales de todo el mundo! + +![Se coloca una resistencia de 12 ohmios frente a una cámara web. Luego, una resistencia de 330 ohmios. En el panel de salida debajo del video, se muestra el indice de confianza según se esté mostrando una resistencia de 12 ohmios o de 330 ohmios.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/es-419/step_5.md b/es-419/step_5.md new file mode 100644 index 0000000..86740d8 --- /dev/null +++ b/es-419/step_5.md @@ -0,0 +1,3 @@ +## ¿Qué puedes hacer ahora? + +Hay muchos otros proyectos de aprendizaje automático e IA en el kit de herramientas de [inteligencia artificial](https://projects.raspberrypi.org/en/pathways/ai-toolkit). \ No newline at end of file diff --git a/fr-FR/images/12_or_330.gif b/fr-FR/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/fr-FR/images/12_or_330.gif differ diff --git a/fr-FR/images/banner.png b/fr-FR/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/fr-FR/images/banner.png differ diff --git a/fr-FR/images/bee_or_berry.gif b/fr-FR/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/fr-FR/images/bee_or_berry.gif differ diff --git a/fr-FR/images/cake_or_biscuit.gif b/fr-FR/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/fr-FR/images/cake_or_biscuit.gif differ diff --git a/fr-FR/images/five_or_three.gif b/fr-FR/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/fr-FR/images/five_or_three.gif differ diff --git a/fr-FR/images/train_model.png b/fr-FR/images/train_model.png new file mode 100644 index 0000000..62daa15 Binary files /dev/null and b/fr-FR/images/train_model.png differ diff --git a/fr-FR/images/wywm.png b/fr-FR/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/fr-FR/images/wywm.png differ diff --git a/fr-FR/meta.yml b/fr-FR/meta.yml new file mode 100644 index 0000000..eac980c --- /dev/null +++ b/fr-FR/meta.yml @@ -0,0 +1,23 @@ +title: Apprendre à une machine +hero_image: images/banner.png +description: Apprends à un ordinateur à te dire combien de doigts tu tiens en l'air ! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: Ce que tu vas faire + - + title: Ajouter des images + completion: + - engagé + - + title: Entraîner et tester + completion: + - interne + - + title: Défi + challenge: true + completion: + - external diff --git a/fr-FR/resources/Teach a machine 1.srt b/fr-FR/resources/Teach a machine 1.srt new file mode 100644 index 0000000..4aaefa7 --- /dev/null +++ b/fr-FR/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Va sur rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +et renomme « Classe 1 » et +« Classe 2 » en « Cinq » et « Trois » + +3 +00:00:10,880 --> 00:00:13,040 +Clique sur « Webcam » dans la classe Cinq + +4 +00:00:13,040 --> 00:00:14,760 +et lève cinq doigts + +5 +00:00:14,760 --> 00:00:19,240 +Avec l'autre main, appuie et  +maintien enfoncé le bouton « Maintenir pour enregistrer » + +6 +00:00:19,240 --> 00:00:21,680 +pour récupérer plein d'images + +7 +00:00:21,680 --> 00:00:24,360 +Passe à la classe « Trois »  +et récupère de nombreuses images + +8 +00:00:24,360 --> 00:00:29,200 +de toi levant trois doigts + diff --git a/fr-FR/resources/readme.txt b/fr-FR/resources/readme.txt new file mode 100644 index 0000000..39ad83b --- /dev/null +++ b/fr-FR/resources/readme.txt @@ -0,0 +1 @@ +Pour regarder une vidéo avec des sous-titres sur VLC (videolan.org), assure-toi que le fichier vidéo et le fichier de sous-titres sont dans le même dossier et ont exactement le même nom (par exemple, video.mp4 et video.srt). Ouvre la vidéo dans VLC, les sous-titres seront chargés automatiquement. Si les sous-titres n'apparaissent pas, fais un clic droit sur l'écran vidéo, va dans **Sous-titres**, puis **Ajouter un fichier de sous-titres**, et sélectionne le bon fichier .srt. Profite du visionnage avec les sous-titres ! \ No newline at end of file diff --git a/fr-FR/resources/teach a machine 2.srt b/fr-FR/resources/teach a machine 2.srt new file mode 100644 index 0000000..f2d488d --- /dev/null +++ b/fr-FR/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Clique sur « Entraîner le modèle » et attends... + +2 +00:00:05,320 --> 00:00:08,920 +car cela peut prendre de dix à  +vingt secondes + +3 +00:00:08,920 --> 00:00:12,800 +Lorsque ton modèle est entraîné,  +le panneau de prévisualisation s'ouvrira + +4 +00:00:12,800 --> 00:00:18,200 +Leve cinq et trois doigts et regarde  +les scores de confiance dans le résultat ci-dessous. + +5 +00:00:18,200 --> 00:00:21,440 +Pourquoi ne pas voir s'il peut reconnaître des gâteaux ou des biscuits ? + +6 +00:00:21,440 --> 00:00:27,200 +Ou des abeilles et des baies ? + diff --git a/fr-FR/step_1.md b/fr-FR/step_1.md new file mode 100644 index 0000000..69f5c98 --- /dev/null +++ b/fr-FR/step_1.md @@ -0,0 +1,27 @@ +## Ce que tu vas faire + +![L'image montre une interface d'apprentissage automatique de "Teachable Machine" où un modèle est entraîné à reconnaître les gestes de la main pour les nombres "Cinq" et "Trois". Sur la droite, dans la section "Preview", le flux de webcam affiche une main montrant trois doigts. En dessous, la section "Output" montre les résultats de la classification, le modèle prédisant une probabilité de 94 % pour "Trois" et une faible probabilité de 6 % pour "Cinq". Le modèle a identifié avec succès le geste de la main comme "trois".](images/wywm.png) + +Tu apprendras à un ordinateur à te dire combien de doigts tu tiens en l'air ! + +\--- collapse --- + +--- + +## title: Où sont stockées mes images ? + +- Ce projet utilise une technologie appelée « apprentissage automatique ». Les systèmes d'apprentissage automatique sont entraînés à l'aide d'une grande quantité de données. +- Ce projet ne nécessite pas la création d'un compte ou d'une connexion. Pour ce projet, les exemples d'images que tu utilises pour réaliser le modèle ne sont stockés que temporairement dans ton navigateur (uniquement sur ta machine). +- Aucune image de ta webcam n'est envoyée à ce site ou à aucun autre site web. + +\--- /collapse --- + +Tu auras besoin d'une **webcam**. + +## --- collapse --- + +## title: Pas de YouTube ? Télécharge les vidéos ! + +Tu peux [télécharger l'ensemble des vidéos de ce projet](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/fr-FR/step_2.md b/fr-FR/step_2.md new file mode 100644 index 0000000..474131f --- /dev/null +++ b/fr-FR/step_2.md @@ -0,0 +1,54 @@ +## Ajouter des images + + +
+

+
+ + +\--- task --- + +Ouvre [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Chaque classe est une catégorie que l'ordinateur doit reconnaître. + +\--- task --- + +- Renomme « Class 1 » en « Cinq » +- Renomme « Class 2 » en « Trois » + +\--- /task --- + +Obtiens une image des cinq doigts. + +\--- task --- + +- Clique sur **Webcam** dans la classe « Cinq » +- Lève cinq doigts devant ta webcam (assure-toi que toute ta main est visible) +- De l'autre main, appuie sur le bouton **Hold to Record** et maintiens-le enfoncé pour obtenir de nombreuses images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Où sont stockées mes images ? + +- Aucune de tes données n'est stockée ou envoyée à ce site ou à tout autre site. +- Cette technologie est appelée « apprentissage automatique », mais elle n’apprend pas pendant que tu l’utilises. +- Elle a déjà été entraînée en utilisant un grand nombre de photos. + +\--- /collapse --- + +Obtiens les images de « trois » doigts. + +\--- task --- + +- Clique sur **Webcam** dans la classe « Trois » +- Lève trois doigts devant ta webcam (assure-toi que toute ta main est visible) +- De l'autre main, appuie sur le bouton **Hold to Record** et maintiens-le enfoncé pour obtenir de nombreuses images + +\--- /task --- diff --git a/fr-FR/step_3.md b/fr-FR/step_3.md new file mode 100644 index 0000000..def1019 --- /dev/null +++ b/fr-FR/step_3.md @@ -0,0 +1,37 @@ +## Entraîner le modèle + + +
+

+
+ + +\--- task --- + +Clique sur **Train Model**. + +![Le bouton "Train Model".](images/train_model.png) + +\--- /task --- + +**Remarque** : Patience ! Cela peut prendre entre 10 et 20 secondes. + +### Prévisualiser et tester + +Lorsque ton modèle est entraîné, le panneau d'aperçu s'ouvre. + +\--- task --- + +- Lève **cinq** doigts et regarde la section « Output » sous l'aperçu. + +Tu verras des scores de confiance pour « Cinq » et « Trois ». + +\--- /task --- + +\--- task --- + +- Lève **trois** doigts +- Quel est le score de confiance le plus élevé que tu puisses obtenir pour « Cinq » ? +- Quel est le score de confiance le plus élevé que tu puisses obtenir pour « Trois » ? + +\--- /task --- diff --git a/fr-FR/step_4.md b/fr-FR/step_4.md new file mode 100644 index 0000000..4fe503a --- /dev/null +++ b/fr-FR/step_4.md @@ -0,0 +1,36 @@ +## Défi + +\--- challenge --- + +Crée ton propre classificateur ! + +### Abeille ou baie ? + +\--- task --- + +J'ai mangé une abeille par erreur. Apprends à une machine à assurer ta sécurité ! + +![Une image d’une abeille est placée devant une webcam. Puis, une image d'une baie. Dans le panneau de résultat situé sous la vidéo, le score de confiance s'affiche pour indiquer s'il s'agit d'une abeille ou d'une baie.](images/bee_or_berry.gif) + +\--- /task --- + +### Gâteau ou biscuit ? + +\--- task --- + +Règle l'argument. + +![Une part de gâteau est placée devant une webcam. Puis, un biscuit. Dans le panneau de résultat situé sous la vidéo, le score de confiance est affiché pour indiquer s'il s'agit d'un gâteau ou d'un biscuit.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Reconnaissance de résistance + +\--- task --- + +Résous un problème pour les créateurs numériques du monde entier ! + +![Une résistance de 12 ohms est placée devant une webcam. Ensuite, une résistance de 330 ohm. Dans le panneau de résultat situé sous la vidéo, le score de confiance est affiché pour indiquer s'il s'agit d'une résistance de 12 ohms ou de 330 ohms.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/fr-FR/step_5.md b/fr-FR/step_5.md new file mode 100644 index 0000000..c410bae --- /dev/null +++ b/fr-FR/step_5.md @@ -0,0 +1,3 @@ +## Que peux-tu faire maintenant ? + +Il existe de nombreux autres projets d'apprentissage automatique et d'IA dans le toolkit [intelligence artificielle] (https://projects.raspberrypi.org/fr-FR/pathways/ai-toolkit). \ No newline at end of file diff --git a/hi-IN/images/12_or_330.gif b/hi-IN/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/hi-IN/images/12_or_330.gif differ diff --git a/hi-IN/images/banner.png b/hi-IN/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/hi-IN/images/banner.png differ diff --git a/hi-IN/images/bee_or_berry.gif b/hi-IN/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/hi-IN/images/bee_or_berry.gif differ diff --git a/hi-IN/images/cake_or_biscuit.gif b/hi-IN/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/hi-IN/images/cake_or_biscuit.gif differ diff --git a/hi-IN/images/five_or_three.gif b/hi-IN/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/hi-IN/images/five_or_three.gif differ diff --git a/hi-IN/images/train_model.png b/hi-IN/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/hi-IN/images/train_model.png differ diff --git a/hi-IN/images/wywm.png b/hi-IN/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/hi-IN/images/wywm.png differ diff --git a/hi-IN/meta.yml b/hi-IN/meta.yml new file mode 100644 index 0000000..14db994 --- /dev/null +++ b/hi-IN/meta.yml @@ -0,0 +1,23 @@ +title: मशीन को सिखाएं +hero_image: images/banner.png +description: कंप्यूटर को सिखाएं कि वह आपको बताए कि आपने कितनी उंगलियां पकड़ रखी हैं! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: आप क्या बनाएँगे + - + title: छवि जोड़ें + completion: + - engaged + - + title: प्रशिक्षण और परीक्षण + completion: + - internal + - + title: चुनौती + challenge: true + completion: + - external diff --git a/hi-IN/resources/Teach a machine 1.srt b/hi-IN/resources/Teach a machine 1.srt new file mode 100644 index 0000000..3f9aac3 --- /dev/null +++ b/hi-IN/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +rpf.io/tm पर जाएं + +2 +00:00:05,920 --> 00:00:10,880 +और 'क्लास 1' और +'क्लास 2' का नाम बदलकर 'पांच' और 'तीन' कर दें + +3 +00:00:10,880 --> 00:00:13,040 +पांच वर्ग में 'वेबकैम' पर क्लिक करें + +4 +00:00:13,040 --> 00:00:14,760 +और पाँच उंगलियाँ ऊपर उठाएँ + +5 +00:00:14,760 --> 00:00:19,240 +अपने दूसरे हाथ से, 'रिकॉर्ड करने के लिए होल्ड करें' बटन को +दबाकर रखें + +6 +00:00:19,240 --> 00:00:21,680 +ढेर सारी छवियाँ इकट्ठा करना + +7 +00:00:21,680 --> 00:00:24,360 +'Three' वर्ग +पर जाएँ और ढेर सारी छवियां इकट्ठा करें + +8 +00:00:24,360 --> 00:00:29,200 +आप तीन उंगलियाँ ऊपर उठाए हुए हैं + diff --git a/hi-IN/resources/readme.txt b/hi-IN/resources/readme.txt new file mode 100644 index 0000000..60574cf --- /dev/null +++ b/hi-IN/resources/readme.txt @@ -0,0 +1 @@ +वीएलसी (videolan.org) पर उपशीर्षक के साथ वीडियो देखने के लिए, सुनिश्चित करें कि वीडियो फ़ाइल और उपशीर्षक फ़ाइल एक ही फ़ोल्डर में हों और उनका नाम भी बिल्कुल समान हो (उदाहरण के लिए, video.mp4 और video.srt)। वीडियो को VLC में खोलें, और यह स्वचालित रूप से उपशीर्षक लोड कर देगा। यदि उपशीर्षक दिखाई नहीं देते हैं, तो वीडियो स्क्रीन पर राइट-क्लिक करें, **उपशीर्षक** पर जाएं, फिर **उपशीर्षक फ़ाइल जोड़ें**, और सही .srt फ़ाइल का चयन करें। उपशीर्षक के साथ देखने का आनंद लें! \ No newline at end of file diff --git a/hi-IN/resources/teach a machine 2.srt b/hi-IN/resources/teach a machine 2.srt new file mode 100644 index 0000000..6560983 --- /dev/null +++ b/hi-IN/resources/teach a machine 2.srt @@ -0,0 +1,26 @@ +1 +00:00:03,040 --> 00:00:05,320 +'ट्रेन मॉडल' पर क्लिक करें और रुकें... + +2 +00:00:05,320 --> 00:00:08,920 +क्योंकि इसे पूरा होने में दस से +बीस सेकंड का समय लग सकता है + +3 +00:00:08,920 --> 00:00:12,800 +जब मॉडल प्रशिक्षित हो जाएगा, तो पूर्वावलोकन पैनल खुल जाएगा + +4 +00:00:12,800 --> 00:00:18,200 +पांच और तीन उंगलियां ऊपर उठाएं और नीचे दिए गए आउटपुट में +विश्वास स्कोर देखें। + +5 +00:00:18,200 --> 00:00:21,440 +क्यों न देखा जाए कि क्या यह केक या बिस्कुट को पहचान सकता है? + +6 +00:00:21,440 --> 00:00:27,200 +या मधुमक्खियां और जामुन? + diff --git a/hi-IN/step_1.md b/hi-IN/step_1.md new file mode 100644 index 0000000..bd784b5 --- /dev/null +++ b/hi-IN/step_1.md @@ -0,0 +1,27 @@ +## आप क्या बनाएँगे + +![चित्र "टीचएबल मशीन" से एक मशीन लर्निंग इंटरफ़ेस दिखाता है जहां एक मॉडल को "पांच" और "तीन" संख्याओं के लिए हाथ के इशारों को पहचानने के लिए प्रशिक्षित किया जा रहा है। दाईं ओर, "पूर्वावलोकन" अनुभाग में, वेबकैम फ़ीड में तीन उंगलियां दिखाते हुए एक हाथ प्रदर्शित होता है। इसके नीचे, "आउटपुट" अनुभाग वर्गीकरण परिणाम दिखाता है, जिसमें मॉडल "तीन" के लिए 94% संभावना और "पांच" के लिए 6% की छोटी संभावना की भविष्यवाणी करता है। मॉडल ने हाथ के इशारे को "तीन" के रूप में सफलतापूर्वक पहचान लिया है।](images/wywm.png) + +कंप्यूटर को सिखाएं कि वह आपको बताए कि आपने कितनी उंगलियां पकड़ रखी हैं! + +\--- collapse --- + +--- + +## title: मेरी छवियाँ कहाँ संग्रहीत हैं? + +- इस परियोजना में 'मशीन लर्निंग' नामक तकनीक का उपयोग किया गया है। मशीन लर्निंग सिस्टम को बड़ी मात्रा में डेटा का उपयोग करके प्रशिक्षित किया जाता है। +- इस परियोजना के लिए आपको खाता बनाने या लॉग इन करने की आवश्यकता नहीं है। इस परियोजना के लिए, मॉडल बनाने के लिए आपके द्वारा उपयोग किए जाने वाले छवि उदाहरण केवल आपके ब्राउज़र में अस्थायी रूप से संग्रहीत किए जाते हैं (केवल आपकी मशीन पर)। +- आपके वेबकैम से कोई भी छवि इस वेबसाइट या किसी अन्य वेबसाइट पर नहीं भेजी जाती है। + +\--- /collapse --- + +आपको एक वेबकैम की आवश्यकता होगी। + +## --- collapse --- + +## शीर्षक: यूट्यूब नहीं? वीडियो डाउनलोड करें! + +आप [इस परियोजना के लिए सभी वीडियो डाउनलोड कर सकते हैं](https://rpf.io/p/hi-IN/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/hi-IN/step_2.md b/hi-IN/step_2.md new file mode 100644 index 0000000..7beb8fe --- /dev/null +++ b/hi-IN/step_2.md @@ -0,0 +1,54 @@ +## छवि जोड़ें + + +
+

+
+ + +\--- task --- + +[टीचएबल मशीन](https://rpf.io/tm){:target="_blank"} खोलें. + +\--- /task --- + +प्रत्येक क्लास एक श्रेणी है जिसे आप चाहते हैं कि कंप्यूटर पहचाने। + +\--- task --- + +- `क्लास 1` का नाम बदलकर `पांच` करें +- `क्लास 2` का नाम बदलकर `तीन` करें + +\--- /task --- + +`पांच` उंगलियों की छवियां इकट्ठा करें। + +\--- task --- + +- पांच वर्ग में `वेबकैम` पर क्लिक करें +- अपने वेबकैम के सामने पांच उंगलियां दिखाएँ (सुनिश्चित करें कि आपका पूरा हाथ दिखाई दे रहा है) +- अपने दूसरे हाथ से, बहुत सारी छवियाँ एकत्र करने के लिए **रिकॉर्ड करने के लिए दबाए रखें** बटन को दबाकर रखें + +\--- /task --- + +\--- collapse --- + +--- + +## title: मेरी छवियाँ कहाँ संग्रहीत हैं? + +- आपका कोई भी डेटा इस या किसी अन्य साइट पर संग्रहीत या भेजा नहीं जाता है। +- इस तकनीक को 'मशीन लर्निंग' कहा जाता है, लेकिन इसका उपयोग करते समय आप कुछ नहीं सीखते। +- इसे पहले ही बड़ी संख्या में तस्वीरों का उपयोग करके प्रशिक्षित किया जा चुका है। + +\--- /collapse --- + +`तीन` उंगलियों की छवियां इकट्ठा करें। + +\--- task --- + +- `तीन` वर्ग में **वेबकैम** पर क्लिक करें +- अपने वेबकैम के सामने तीन उंगलियां दिखाएँ (सुनिश्चित करें कि आपका पूरा हाथ दिखाई दे रहा है) +- अपने दूसरे हाथ से, बहुत सारी छवियाँ एकत्र करने के लिए **रिकॉर्ड करने के लिए दबाए रखें** बटन को दबाकर रखें + +\--- /task --- diff --git a/hi-IN/step_3.md b/hi-IN/step_3.md new file mode 100644 index 0000000..8e56b39 --- /dev/null +++ b/hi-IN/step_3.md @@ -0,0 +1,37 @@ +## मॉडल का परीक्षण करें + + +
+

+
+ + +\--- task --- + +**ट्रेन मॉडल** पर क्लिक करें। + +!['ट्रेन मॉडल' बटन.](images/train_model.png) + +\--- /task --- + +**नोट:** धैर्य रखें! इसे पूरा होने में 10 से 20 सेकंड का समय लग सकता है। + +### पूर्वावलोकन और परीक्षण + +जब मॉडल प्रशिक्षित हो जाएगा, तो पूर्वावलोकन पैनल खुल जाएगा + +\--- task --- + +- पांच उंगलियां ऊपर उठाएं और पूर्वावलोकन के नीचे 'आउटपुट' अनुभाग देखें। + +आप `पांच` और `तीन` के लिए विश्वास स्कोर देखेंगे। + +\--- /task --- + +\--- task --- + +- **तीन** उंगलियाँ ऊपर उठाएँ +- `पांच` के लिए आप कितना उच्चतम विश्वास स्कोर प्राप्त कर सकते हैं? +- `तीन` के लिए आप कितना उच्चतम विश्वास स्कोर प्राप्त कर सकते हैं? + +\--- /task --- diff --git a/hi-IN/step_4.md b/hi-IN/step_4.md new file mode 100644 index 0000000..79dc2df --- /dev/null +++ b/hi-IN/step_4.md @@ -0,0 +1,36 @@ +## चुनौती + +\--- challenge --- + +अपना स्वयं का वर्गीकरणकर्ता बनाएं! + +### मधुमक्खी या बेरी? + +\--- task --- + +एक बार मैंने गलती से एक मधुमक्खी खा लिया। मशीन को सिखाएं कि वह आपको सुरक्षित रखे! + +![एक मधुमक्खी की छवि को वेब कैमरे के सामने रखा गया है। फिर, एक बेरी की छवि। वीडियो के नीचे आउटपुट पैनल में, विश्वास स्कोर प्रदर्शित किया जाता है कि क्या मधुमक्खी या बेरी दिखाई जा रही है।](images/bee_or_berry.gif) + +\--- /task --- + +### केक या बिस्किट? + +\--- task --- + +बहस को सुलझाओ. + +![केक का एक टुकड़ा वेब कैमरे के सामने रखा गया है। फिर, एक बिस्किट. वीडियो के नीचे आउटपुट पैनल में, यह विश्वास स्कोर प्रदर्शित किया जाता है कि केक दिखाया जा रहा है या बिस्किट।](images/cake_or_biscuit.gif) + +\--- /task --- + +### प्रतिरोधक पहचानकर्ता + +\--- task --- + +दुनिया भर के डिजिटल निर्माताओं की समस्या का समाधान! + +एक 12 ओम अवरोधक को एक वेब कैमरा के सामने रखा गया है। फिर, एक 330 ओम प्रतिरोधक. वीडियो के नीचे आउटपुट पैनल में, विश्वास स्कोर प्रदर्शित किया जाता है कि 12 ओम या 330 ओम प्रतिरोधक दिखाया जा रहा है।](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/hi-IN/step_5.md b/hi-IN/step_5.md new file mode 100644 index 0000000..41e297a --- /dev/null +++ b/hi-IN/step_5.md @@ -0,0 +1,3 @@ +## अब आप क्या कर सकते हैं? + +टूलकिट में कई अन्य मशीन लर्निंग और एआई परियोजनाएं हैं [कृत्रिम बुद्धिमत्ता](https://projects.raspberrypi.org/hi-IN/pathways/ai-toolkit) \ No newline at end of file diff --git a/hu-HU/images/12_or_330.gif b/hu-HU/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/hu-HU/images/12_or_330.gif differ diff --git a/hu-HU/images/banner.png b/hu-HU/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/hu-HU/images/banner.png differ diff --git a/hu-HU/images/bee_or_berry.gif b/hu-HU/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/hu-HU/images/bee_or_berry.gif differ diff --git a/hu-HU/images/cake_or_biscuit.gif b/hu-HU/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/hu-HU/images/cake_or_biscuit.gif differ diff --git a/hu-HU/images/five_or_three.gif b/hu-HU/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/hu-HU/images/five_or_three.gif differ diff --git a/hu-HU/images/train_model.png b/hu-HU/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/hu-HU/images/train_model.png differ diff --git a/hu-HU/images/wywm.png b/hu-HU/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/hu-HU/images/wywm.png differ diff --git a/hu-HU/meta.yml b/hu-HU/meta.yml new file mode 100644 index 0000000..abf9e1e --- /dev/null +++ b/hu-HU/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: What you will make + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Challenge + challenge: true + completion: + - external diff --git a/hu-HU/resources/Teach a machine 1.srt b/hu-HU/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/hu-HU/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/hu-HU/resources/readme.txt b/hu-HU/resources/readme.txt new file mode 100644 index 0000000..0e0956c --- /dev/null +++ b/hu-HU/resources/readme.txt @@ -0,0 +1 @@ +To watch a video with subtitles on VLC (videolan.org), ensure the video file and subtitle file are in the same folder and have the exact same name (e.g., video.mp4 and video.srt). Open the video in VLC, and it will automatically load the subtitles. If the subtitles don’t appear, right-click the video screen, go to **Subtitle**, then **Add Subtitle File**, and select the correct .srt file. Enjoy watching with subtitles! \ No newline at end of file diff --git a/hu-HU/resources/teach a machine 2.srt b/hu-HU/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/hu-HU/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/hu-HU/step_1.md b/hu-HU/step_1.md new file mode 100644 index 0000000..d2e1ce6 --- /dev/null +++ b/hu-HU/step_1.md @@ -0,0 +1,27 @@ +## What you will make + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## title: No YouTube? Download the videos! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/hu-HU/step_2.md b/hu-HU/step_2.md new file mode 100644 index 0000000..2fb7b0e --- /dev/null +++ b/hu-HU/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- /task --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- diff --git a/hu-HU/step_3.md b/hu-HU/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/hu-HU/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/hu-HU/step_4.md b/hu-HU/step_4.md new file mode 100644 index 0000000..adbc2be --- /dev/null +++ b/hu-HU/step_4.md @@ -0,0 +1,36 @@ +## Challenge + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/hu-HU/step_5.md b/hu-HU/step_5.md new file mode 100644 index 0000000..5fde839 --- /dev/null +++ b/hu-HU/step_5.md @@ -0,0 +1,3 @@ +## What can you do now? + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/it-IT/images/12_or_330.gif b/it-IT/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/it-IT/images/12_or_330.gif differ diff --git a/it-IT/images/banner.png b/it-IT/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/it-IT/images/banner.png differ diff --git a/it-IT/images/bee_or_berry.gif b/it-IT/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/it-IT/images/bee_or_berry.gif differ diff --git a/it-IT/images/cake_or_biscuit.gif b/it-IT/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/it-IT/images/cake_or_biscuit.gif differ diff --git a/it-IT/images/five_or_three.gif b/it-IT/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/it-IT/images/five_or_three.gif differ diff --git a/it-IT/images/train_model.png b/it-IT/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/it-IT/images/train_model.png differ diff --git a/it-IT/images/wywm.png b/it-IT/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/it-IT/images/wywm.png differ diff --git a/it-IT/meta.yml b/it-IT/meta.yml new file mode 100644 index 0000000..e51151e --- /dev/null +++ b/it-IT/meta.yml @@ -0,0 +1,23 @@ +title: Insegna a una macchina +hero_image: images/banner.png +description: Insegna a un computer a dirti quante dita stai alzando! +version: 1 +listed: true +copyedit: true +last_tested: "2024/05/24" +steps: + - + title: Cosa creerai + - + title: Aggiungi immagini + completion: + - fatto + - + title: Addestra e testa + completion: + - interno + - + title: Sfida + challenge: true + completion: + - external diff --git a/it-IT/resources/Teach a machine 1.srt b/it-IT/resources/Teach a machine 1.srt new file mode 100644 index 0000000..3672fb4 --- /dev/null +++ b/it-IT/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Vai su rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +e rinomina "Classe 1" e +"Classe 2" in "Cinque" e "Tre" + +3 +00:00:10,880 --> 00:00:13,040 +Fare clic su "Webcam" nella classe Cinque + +4 +00:00:13,040 --> 00:00:14,760 +e alza cinque dita + +5 +00:00:14,760 --> 00:00:19,240 +Con l'altra mano, tieni +premuto il pulsante "'Hold to record" + +6 +00:00:19,240 --> 00:00:21,680 +per raccogliere molte immagini + +7 +00:00:21,680 --> 00:00:24,360 +Passa alla classe "Tre" +e raccogli molte immagini + +8 +00:00:24,360 --> 00:00:29,200 +di te che alzi tre dita + diff --git a/it-IT/resources/readme.txt b/it-IT/resources/readme.txt new file mode 100644 index 0000000..277722d --- /dev/null +++ b/it-IT/resources/readme.txt @@ -0,0 +1 @@ +Per guardare un video con i sottotitoli su VLC (videolan.org), assicurati che il file video e il file dei sottotitoli siano nella stessa cartella e abbiano esattamente lo stesso nome (ad esempio, video.mp4 e video.srt). Apri il video in VLC: i sottotitoli verranno caricati automaticamente. Se i sottotitoli non vengono visualizzati, fai clic con il pulsante destro del mouse sulla schermata del video, vai su **Sottotitoli**, quindi su **Aggiungi file sottotitoli** e seleziona il file .srt corretto. Buona visione con i sottotitoli! \ No newline at end of file diff --git a/it-IT/resources/teach a machine 2.srt b/it-IT/resources/teach a machine 2.srt new file mode 100644 index 0000000..a46c658 --- /dev/null +++ b/it-IT/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Fai clic su "Train model" e aspetta... + +2 +00:00:05,320 --> 00:00:08,920 +poiché l'operazione potrebbe richiedere +dai dieci ai venti secondi + +3 +00:00:08,920 --> 00:00:12,800 +Una volta completato l'addestramento del modello, +si aprirà il pannello di anteprima + +4 +00:00:12,800 --> 00:00:18,200 +Alza cinque e tre dita e osserva +i punteggi di confidenza nell'output sottostante. + +5 +00:00:18,200 --> 00:00:21,440 +Perché non provi a vedere se riesce a riconoscere torte o biscotti? + +6 +00:00:21,440 --> 00:00:27,200 +Oppure api e bacche? + diff --git a/it-IT/step_1.md b/it-IT/step_1.md new file mode 100644 index 0000000..e0fdb78 --- /dev/null +++ b/it-IT/step_1.md @@ -0,0 +1,27 @@ +## Cosa creerai + +![L'immagine mostra un'interfaccia di apprendimento automatico di "Teachable Machine" in cui un modello viene addestrato a riconoscere i gesti delle mani che rappresentano i numeri "cinque" e "tre". Sulla destra, nella sezione "Anteprima", il feed della webcam mostra una mano con tre dita. Sotto, nella sezione "Output", vengono mostrati i risultati della classificazione: il modello prevede una probabilità del 94% per "tre" e una probabilità del 6% per "cinque". Il modello ha identificato correttamente il gesto della mano come "tre."](images/wywm.png) + +Insegnerai a un computer a riconoscere quante dita stai alzando! + +\--- collapse --- + +--- + +## title: Dove sono archiviate le mie immagini? + +- Questo progetto utilizza una tecnologia chiamata "apprendimento automatico". I sistemi di apprendimento automatico vengono addestrati utilizzando una grande quantità di dati. +- Questo progetto non richiede la creazione di un account né l’accesso. Per questo progetto, gli esempi di immagini utilizzati per creare il modello vengono memorizzati solo temporaneamente nel browser (solo sul computer). +- Le immagini della webcam non verranno inviate a questo o ad altri siti web. + +\--- /collapse --- + +Avrai bisogno di una **webcam**. + +## --- collapse --- + +## title: Non riesci ad accedere a YouTube? Scarica i video! + +Puoi [scaricare tutti i video per questo progetto](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/it-IT/step_2.md b/it-IT/step_2.md new file mode 100644 index 0000000..d81f3ff --- /dev/null +++ b/it-IT/step_2.md @@ -0,0 +1,54 @@ +## Aggiungi immagini + + +
+

+
+ + +\--- task --- + +Apri [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Ogni classe rappresenta una categoria che il computer deve riconoscere. + +\--- task --- + +- Rinomina `Classe 1` in `Cinque` +- Rinomina `Classe 2` in `Tre` + +\--- /task --- + +Raccogli immagini di `cinque` dita. + +\--- task --- + +- Fai clic su **Webcam** nella classe `Cinque` +- Alza cinque dita davanti alla webcam, assicurandoti che l'intera mano sia ben visibile. +- Con l'altra mano, tieni premuto il pulsante **Hold to Record** per raccogliere molte immagini. + +\--- /task --- + +\--- collapse --- + +--- + +## title: Dove sono archiviate le mie immagini? + +- I tuoi dati non verranno né archiviati né inviati a questo o ad altri siti. +- Questa tecnologia si chiama "apprendimento automatico", ma non sta imparando mentre la utilizzi. +- È stata già addestrata utilizzando un gran numero di foto. + +\--- /collapse --- + +Raccogli immagini di `tre` dita. + +\--- task --- + +- Fai clic su **Webcam** nella classe `Tre` +- Alza tre dita davanti alla webcam, assicurandoti che l'intera mano sia ben visibile. +- Con l'altra mano, tieni premuto il pulsante **Hold to Record** per raccogliere molte immagini. + +\--- /task --- diff --git a/it-IT/step_3.md b/it-IT/step_3.md new file mode 100644 index 0000000..446c86c --- /dev/null +++ b/it-IT/step_3.md @@ -0,0 +1,37 @@ +## Addestra il modello + + +
+

+
+ + +\--- task --- + +Fai clic su **Train Model**. + +![Il pulsante "Train Model".](images/train_model.png) + +\--- /task --- + +**Nota**: Abbi pazienza! Il processo può richiedere dai 10 ai 20 secondi. + +### Anteprima e test + +Una volta addestrato il modello, si aprirà il pannello di anteprima. + +\--- task --- + +- Alza **cinque** dita e osserva la sezione 'Output' sotto l'anteprima. + +Vedrai i punteggi di confidenza per `Cinque` e `Tre`. + +\--- /task --- + +\--- task --- + +- Alza **tre** dita +- Qual è il punteggio di confidenza più alto che puoi ottenere per `Cinque`? +- Qual è il punteggio di confidenza più alto che puoi ottenere per `Tre`? + +\--- /task --- diff --git a/it-IT/step_4.md b/it-IT/step_4.md new file mode 100644 index 0000000..d0635cf --- /dev/null +++ b/it-IT/step_4.md @@ -0,0 +1,36 @@ +## Sfida + +\--- challenge --- + +Crea il tuo classificatore! + +### Ape o bacca? + +\--- task --- + +Una volta ho mangiato un'ape per sbaglio. Insegna a una macchina a proteggerti! + +![L'immagine di un'ape viene tenuta davanti a una webcam. Poi, l'immagine di una bacca. Nel pannello di output, sotto il video, viene visualizzato il punteggio di confidenza che indica se si tratta di un'ape o di una bacca.](images/bee_or_berry.gif) + +\--- /task --- + +### Torta o biscotto? + +\--- task --- + +Sciogliamo ogni dubbio! + +![Un pezzo di torta viene tenuto in mano davanti a una webcam. Poi, un biscotto. Nel pannello di output, sotto il video, viene visualizzato il punteggio di confidenza che indica se si tratta di una torta o di un biscotto.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Riconoscitore di resistenze + +\--- task --- + +Risolvi un problema per i maker digitali di tutto il mondo! + +![Una resistenza da 12 ohm viene tenuta in mano davanti a una webcam. Poi, una resistenza da 330 ohm. Nel pannello di output, sotto il video, viene visualizzato il punteggio di confidenza che indica se si tratta di una risistenza da 12 ohm o una da 330 ohm.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/it-IT/step_5.md b/it-IT/step_5.md new file mode 100644 index 0000000..aae6009 --- /dev/null +++ b/it-IT/step_5.md @@ -0,0 +1,3 @@ +## Cosa puoi fare adesso? + +Ci sono molti altri progetti di apprendimento automatico e intelligenza artificiale nel toolkit di [intelligenza artificiale](https://projects.raspberrypi.org/en/pathways/ai-toolkit). \ No newline at end of file diff --git a/ja-JP/images/12_or_330.gif b/ja-JP/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/ja-JP/images/12_or_330.gif differ diff --git a/ja-JP/images/banner.png b/ja-JP/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/ja-JP/images/banner.png differ diff --git a/ja-JP/images/bee_or_berry.gif b/ja-JP/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/ja-JP/images/bee_or_berry.gif differ diff --git a/ja-JP/images/cake_or_biscuit.gif b/ja-JP/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/ja-JP/images/cake_or_biscuit.gif differ diff --git a/ja-JP/images/five_or_three.gif b/ja-JP/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/ja-JP/images/five_or_three.gif differ diff --git a/ja-JP/images/train_model.png b/ja-JP/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/ja-JP/images/train_model.png differ diff --git a/ja-JP/images/wywm.png b/ja-JP/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/ja-JP/images/wywm.png differ diff --git a/ja-JP/meta.yml b/ja-JP/meta.yml new file mode 100644 index 0000000..1205f49 --- /dev/null +++ b/ja-JP/meta.yml @@ -0,0 +1,23 @@ +title: 機械に教える +hero_image: images/banner.png +description: 何本の指を上げているかをコンピューターに教えましょう！ +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: はじめに + - + title: 画像を追加する + completion: + - engaged + - + title: トレーニングとテスト + completion: + - internal + - + title: チャレンジ + challenge: true + completion: + - external diff --git a/ja-JP/resources/Teach a machine 1.srt b/ja-JP/resources/Teach a machine 1.srt new file mode 100644 index 0000000..6bf8497 --- /dev/null +++ b/ja-JP/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +rpf.io/tm へアクセス + +2 +00:00:05,920 --> 00:00:10,880 +"Class 1"と +の"Class 2"の名前を`Five` と 'Three'に変更します + +3 +00:00:10,880 --> 00:00:13,040 +`Five`クラスの**Webcam**をクリックします + +4 +00:00:13,040 --> 00:00:14,760 +5本の指を立てて + +5 +00:00:14,760 --> 00:00:19,240 +もう一方の手で「Hold to record」ボタンを +押し続けてください + +6 +00:00:19,240 --> 00:00:21,680 +たくさんの画像を集めるために + +7 +00:00:21,680 --> 00:00:24,360 +'Three'クラス +に切り替えて大量の画像を収集します + +8 +00:00:24,360 --> 00:00:29,200 +3本の指を立てて + diff --git a/ja-JP/resources/readme.txt b/ja-JP/resources/readme.txt new file mode 100644 index 0000000..5138a84 --- /dev/null +++ b/ja-JP/resources/readme.txt @@ -0,0 +1 @@ +VLC (videolan.org) で字幕付きのビデオを観るには、ビデオ ファイルと字幕ファイルが同じフォルダーにあり、名前が完全に同じであることを確認します (例: video.mp4 と video.srt)。 VLC でビデオを開くと、字幕が自動的に読み込まれます。 字幕が表示されない場合は、ビデオ画面を右クリックし、**字幕** > **字幕ファイルの追加** の順に移動して、正しい .srt ファイルを選択します。 字幕付きでお楽しみください！ \ No newline at end of file diff --git a/ja-JP/resources/teach a machine 2.srt b/ja-JP/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/ja-JP/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/ja-JP/step_1.md b/ja-JP/step_1.md new file mode 100644 index 0000000..78f4d90 --- /dev/null +++ b/ja-JP/step_1.md @@ -0,0 +1,27 @@ +## はじめに + +![この画像は「Teachable Machine」の機械学習インターフェースを示しており、モデルが数字の「5」と「3」の手のジェスチャーを認識するようにトレーニングされています。 右側の「プレビュー」セクションでは、ウェブカメラのフィードに 3 本の指を示す手が表示されます。 その下の「出力」セクションには分類結果が表示され、モデルは「3」の確率を 94%、「5」の確率をわずか 6% と予測しています。 モデルは手のジェスチャーを「3」として正常に識別しました。](images/wywm.png) + +何本の指を上げているかをコンピューターに教えましょう！ + +\--- collapse --- + +--- + +## title:: 画像はどこに保存されますか？ + +- このプロジェクトでは「機械学習」と呼ばれる技術が使用されています。 機械学習システムは、大量のデータを使用してトレーニングされます。 +- このプロジェクトでは、アカウントの作成やログインは必要ありません。 このプロジェクトでは、モデルの作成に使用する画像サンプルは、ブラウザ（ご使用のマシン上）にのみ一時的に保存されます。 +- ウェブカメラからの画像は、このウェブサイトまたは他のウェブサイトに送信されることはありません。 + +\--- /collapse --- + +**ウェブカメラ**が必要になります。 + +## --- collapse --- + +## title:: YouTube はありませんか？ 動画をダウンロードしましょう！ + +[このプロジェクトのすべてのビデオをダウンロード] (https://rpf.io/p/en/teach-a-machine-go){:target="_blank"} できます。 + +\--- /collapse --- \ No newline at end of file diff --git a/ja-JP/step_2.md b/ja-JP/step_2.md new file mode 100644 index 0000000..0227332 --- /dev/null +++ b/ja-JP/step_2.md @@ -0,0 +1,54 @@ +## 画像を追加する + + +
+

+
+ + +\--- task --- + +[Teachable Machine](https://rpf.io/tm){:target="_blank"}を開きます。 + +\--- /task --- + +各クラスは、コンピューターに認識させたいカテゴリです。 + +\--- task --- + +- `Class 1` の名前を `Five` に変更します +- `Class 2` の名前を `Three` に変更します + +\--- /task --- + +「5本」の指の画像を集めます。 + +\--- task --- + +- `Five`クラスの**Webcam**をクリックします +- ウェブカメラに5本の指をかざします（手のひら全体が映っていることを確認してください） +- もう一方の手で**長押し録画**ボタンを押し、たくさんの画像を収集してください + +\--- /task --- + +\--- collapse --- + +--- + +## title:: 画像はどこに保存されますか？ + +- あなたのデータはこのサイトや他のサイトに保存されたり、送信されたりすることはありません。 +- 技術は「機械学習」と呼ばれていますが、それを使用している間は学習ではありません。 +- それはすでに多数の写真を使用して訓練されています。 + +\--- /collapse --- + +「3本」の指の画像を集めます。 + +\--- task --- + +- `Three`クラスの**Webcam**をクリックします +- ウェブカメラに3本の指をかざします（手のひら全体が映っていることを確認してください） +- もう一方の手で**長押し録画**ボタンを押し、たくさんの画像を収集してください + +\--- /task --- diff --git a/ja-JP/step_3.md b/ja-JP/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/ja-JP/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/ja-JP/step_4.md b/ja-JP/step_4.md new file mode 100644 index 0000000..d1421b6 --- /dev/null +++ b/ja-JP/step_4.md @@ -0,0 +1,36 @@ +## チャレンジ + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/ja-JP/step_5.md b/ja-JP/step_5.md new file mode 100644 index 0000000..5b4a686 --- /dev/null +++ b/ja-JP/step_5.md @@ -0,0 +1,3 @@ +## 次は何をしましょうか？ + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/nl-NL/images/12_or_330.gif b/nl-NL/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/nl-NL/images/12_or_330.gif differ diff --git a/nl-NL/images/banner.png b/nl-NL/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/nl-NL/images/banner.png differ diff --git a/nl-NL/images/bee_or_berry.gif b/nl-NL/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/nl-NL/images/bee_or_berry.gif differ diff --git a/nl-NL/images/cake_or_biscuit.gif b/nl-NL/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/nl-NL/images/cake_or_biscuit.gif differ diff --git a/nl-NL/images/five_or_three.gif b/nl-NL/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/nl-NL/images/five_or_three.gif differ diff --git a/nl-NL/images/train_model.png b/nl-NL/images/train_model.png new file mode 100644 index 0000000..f4543f3 Binary files /dev/null and b/nl-NL/images/train_model.png differ diff --git a/nl-NL/images/wywm.png b/nl-NL/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/nl-NL/images/wywm.png differ diff --git a/nl-NL/meta.yml b/nl-NL/meta.yml new file mode 100644 index 0000000..01f7052 --- /dev/null +++ b/nl-NL/meta.yml @@ -0,0 +1,23 @@ +title: Leer een machine +hero_image: images/banner.png +description: Leer een computer om te vertellen hoeveel vingers je omhoog houdt! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: Wat ga je maken + - + title: Afbeeldingen toevoegen + completion: + - engaged + - + title: Trainen en testen + completion: + - internal + - + title: Uitdaging + challenge: true + completion: + - external diff --git a/nl-NL/resources/Teach a machine 1.srt b/nl-NL/resources/Teach a machine 1.srt new file mode 100644 index 0000000..f00144a --- /dev/null +++ b/nl-NL/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Ga naar rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +en hernoem 'Klasse 1' en +'Klasse 2' naar 'Vijf' en 'Drie' + +3 +00:00:10,880 --> 00:00:13,040 +Klik op 'Webcam' in de klasse `Vijf` + +4 +00:00:13,040 --> 00:00:14,760 +en houd vijf vingers omhoog + +5 +00:00:14,760 --> 00:00:19,240 +Houd met je andere hand de knop +'Ingedrukt houden om op te nemen' ingedrukt + +6 +00:00:19,240 --> 00:00:21,680 +om veel afbeeldingen te verzamelen + +7 +00:00:21,680 --> 00:00:24,360 +Schakel over naar de klasse 'Drie' +en verzamel heel veel afbeeldingen + +8 +00:00:24,360 --> 00:00:29,200 +van jezelf terwijl je drie vingers omhoog houdt + diff --git a/nl-NL/resources/readme.txt b/nl-NL/resources/readme.txt new file mode 100644 index 0000000..f5f90aa --- /dev/null +++ b/nl-NL/resources/readme.txt @@ -0,0 +1 @@ +Om een video met ondertiteling te bekijken op VLC (videolan.org), zorg ervoor dat het videobestand en het ondertitelingsbestand in dezelfde map zitten en exact dezelfde naam hebben (bijv. video.mp4 en video.srt). Open de video in VLC, dan wordt de ondertiteling automatisch geladen. Als de ondertiteling niet verschijnt, klik dan met de rechtermuisknop op het videoscherm, ga naar **Subtitle**, dan **Add Subtitle File**, en selecteer het juiste .srt-bestand. Veel kijkplezier met de ondertiteling! \ No newline at end of file diff --git a/nl-NL/resources/teach a machine 2.srt b/nl-NL/resources/teach a machine 2.srt new file mode 100644 index 0000000..736dffd --- /dev/null +++ b/nl-NL/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Klik op 'Model trainen' en wacht even... + +2 +00:00:05,320 --> 00:00:08,920 +omdat het tien tot +twintig seconden kan duren om te voltooien + +3 +00:00:08,920 --> 00:00:12,800 +Zodra je model is getraind, +wordt het voorbeeldvenster geopend + +4 +00:00:12,800 --> 00:00:18,200 +Houd vijf en drie vingers omhoog en bekijk +de betrouwbaarheidsscores in de uitvoer hieronder. + +5 +00:00:18,200 --> 00:00:21,440 +Waarom probeer je niet eens of het taart of koekjes herkent? + +6 +00:00:21,440 --> 00:00:27,200 +Of bijen en bessen? + diff --git a/nl-NL/step_1.md b/nl-NL/step_1.md new file mode 100644 index 0000000..95c7907 --- /dev/null +++ b/nl-NL/step_1.md @@ -0,0 +1,27 @@ +## Wat ga je maken + +![De afbeelding toont een machine learning interface van "Teachable Machine" waarbij een model wordt getraind om handgebaren te herkennen voor de getallen "Vijf" en "Drie." Aan de rechterkant, in het "Voorbeeld bekijken"-gedeelte, toont de webcamfeed een hand met drie vingers. Daaronder worden in het gedeelte 'Uitvoer' de classificatieresultaten weergegeven, waarbij het model een waarschijnlijkheid van 94% voor 'Drie' en een kleine waarschijnlijkheid van 6% voor 'Vijf' voorspelt Het model heeft het handgebaar succesvol geïdentificeerd als "Drie."](images/wywm.png) + +Je gaat een computer leren om je te vertellen hoeveel vingers je omhoog houdt! + +\--- collapse --- + +--- + +## title: Waar worden mijn afbeeldingen opgeslagen? + +- Dit project maakt gebruik van een technologie genaamd 'machine learning'. Machine learning-systemen worden getraind met behulp van een grote hoeveelheid data. +- Voor dit project hoef je geen account aan te maken of in te loggen. Voor dit project worden de afbeeldingsvoorbeelden die je gebruikt om het model te maken tijdelijk opgeslagen in je browser (alleen op je machine). +- Er worden geen afbeeldingen van je webcam verzonden naar deze website of naar een andere website. + +\--- /collapse --- + +Je hebt een **webcam** nodig. + +## --- collapse --- + +## title: Geen YouTube? Download de video's! + +Je kunt [alle video's voor dit project downloaden](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/nl-NL/step_2.md b/nl-NL/step_2.md new file mode 100644 index 0000000..7c07e23 --- /dev/null +++ b/nl-NL/step_2.md @@ -0,0 +1,54 @@ +## Afbeeldingen toevoegen + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Elke klasse is een categorie die je wil dat de computer herkent. + +\--- task --- + +- Hernoem `Klasse 1` naar `Vijf` +- Hernoem `Klasse 2` naar `Drie` + +\--- /task --- + +Verzamel afbeeldingen van `vijf` vingers. + +\--- task --- + +- Klik op **Webcam** in de klasse `Vijf` +- Houd vijf vingers omhoog voor je webcam (zorg ervoor dat je hele hand in beeld is) +- Houd met je andere hand de knop **Ingedrukt houden om op te nemen** ingedrukt om veel afbeeldingen te verzamelen + +\--- /task --- + +\--- collapse --- + +--- + +## title: Waar worden mijn afbeeldingen opgeslagen? + +- Er worden geen gegevens van jou opgeslagen of naar deze of een andere site verzonden. +- De technologie heet 'machine learning', maar ze leert niet terwijl je er gebruik van maakt. +- Er is al getraind met behulp van een groot aantal foto's. + +\--- /collapse --- + +Verzamel afbeeldingen van `drie` vingers. + +\--- task --- + +- Klik op **Webcam** in de klasse `Drie` +- Houd drie vingers omhoog voor je webcam (zorg ervoor dat je hele hand in beeld is) +- Houd met je andere hand de knop **Ingedrukt houden om op te nemen** ingedrukt om veel afbeeldingen te verzamelen + +\--- /task --- diff --git a/nl-NL/step_3.md b/nl-NL/step_3.md new file mode 100644 index 0000000..953e7bd --- /dev/null +++ b/nl-NL/step_3.md @@ -0,0 +1,37 @@ +## Train het model + + +
+

+
+ + +\--- task --- + +Klik op **Model trainen**. + +![De 'Model trainen' knop.](images/train_model.png) + +\--- /task --- + +**Let op:** Heb geduld! Het kan 10 tot 20 seconden duren om te voltooien. + +### Preview en test + +Zodra je model is getraind, wordt het voorbeeldvenster geopend. + +\--- task --- + +- Steek **vijf** vingers omhoog en kijk naar het gedeelte 'Uitvoer' onder het voorbeeld. + +Je ziet betrouwbaarheidscores voor `Vijf` en `Drie`. + +\--- /task --- + +\--- task --- + +- Houd **drie** vingers omhoog +- Wat is de hoogste betrouwbaarheidsscore die je kunt halen voor `Vijf`? +- Wat is de hoogste betrouwbaarheidsscore die je kunt halen voor `Drie`? + +\--- /task --- diff --git a/nl-NL/step_4.md b/nl-NL/step_4.md new file mode 100644 index 0000000..cac6587 --- /dev/null +++ b/nl-NL/step_4.md @@ -0,0 +1,36 @@ +## Uitdaging + +\--- challenge --- + +Maak je eigen classificator! + +### Bij of bes? + +\--- task --- + +Ik heb ooit per ongeluk een bij opgegeten. Leer een machine om je veilig te houden! + +![Een afbeelding van een bij wordt voor een webcam gehouden. Dan een afbeelding van een bes. In het uitvoerpaneel onder de video wordt de betrouwbaarheidsscore weergegeven voor de weergave van een bij of een bes.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake of koekje? + +\--- task --- + +Beslecht het geschil. + +![Een stuk taart wordt voor een webcam gehouden. En dan een koekje. In het uitvoerpaneel onder de video wordt de betrouwbaarheidsscore weergegeven voor de vraag of er een taart of een koekje wordt getoond.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Weerstandsherkenner + +\--- task --- + +Los een probleem op voor digitale makers overal ter wereld! + +![Een weerstand van 12 ohm wordt voor een webcam gehouden. Dan een weerstand van 330 ohm. In het uitvoerpaneel onder de video wordt de betrouwbaarheidsscore weergegeven voor de weergave van een weerstand van 12 ohm of 330 ohm.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/nl-NL/step_5.md b/nl-NL/step_5.md new file mode 100644 index 0000000..6ea7910 --- /dev/null +++ b/nl-NL/step_5.md @@ -0,0 +1,3 @@ +## Wat kun je nu doen? + +Er zijn nog veel meer machine learning- en AI-projecten in de [kunstmatige intelligentie](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/pl-PL/images/12_or_330.gif b/pl-PL/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/pl-PL/images/12_or_330.gif differ diff --git a/pl-PL/images/banner.png b/pl-PL/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/pl-PL/images/banner.png differ diff --git a/pl-PL/images/bee_or_berry.gif b/pl-PL/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/pl-PL/images/bee_or_berry.gif differ diff --git a/pl-PL/images/cake_or_biscuit.gif b/pl-PL/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/pl-PL/images/cake_or_biscuit.gif differ diff --git a/pl-PL/images/five_or_three.gif b/pl-PL/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/pl-PL/images/five_or_three.gif differ diff --git a/pl-PL/images/train_model.png b/pl-PL/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/pl-PL/images/train_model.png differ diff --git a/pl-PL/images/wywm.png b/pl-PL/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/pl-PL/images/wywm.png differ diff --git a/pl-PL/meta.yml b/pl-PL/meta.yml new file mode 100644 index 0000000..abf9e1e --- /dev/null +++ b/pl-PL/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: What you will make + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Challenge + challenge: true + completion: + - external diff --git a/pl-PL/resources/Teach a machine 1.srt b/pl-PL/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/pl-PL/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/pl-PL/resources/readme.txt b/pl-PL/resources/readme.txt new file mode 100644 index 0000000..0e0956c --- /dev/null +++ b/pl-PL/resources/readme.txt @@ -0,0 +1 @@ +To watch a video with subtitles on VLC (videolan.org), ensure the video file and subtitle file are in the same folder and have the exact same name (e.g., video.mp4 and video.srt). Open the video in VLC, and it will automatically load the subtitles. If the subtitles don’t appear, right-click the video screen, go to **Subtitle**, then **Add Subtitle File**, and select the correct .srt file. Enjoy watching with subtitles! \ No newline at end of file diff --git a/pl-PL/resources/teach a machine 2.srt b/pl-PL/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/pl-PL/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/pl-PL/step_1.md b/pl-PL/step_1.md new file mode 100644 index 0000000..d2e1ce6 --- /dev/null +++ b/pl-PL/step_1.md @@ -0,0 +1,27 @@ +## What you will make + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## title: No YouTube? Download the videos! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/pl-PL/step_2.md b/pl-PL/step_2.md new file mode 100644 index 0000000..2fb7b0e --- /dev/null +++ b/pl-PL/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- /task --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- diff --git a/pl-PL/step_3.md b/pl-PL/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/pl-PL/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/pl-PL/step_4.md b/pl-PL/step_4.md new file mode 100644 index 0000000..adbc2be --- /dev/null +++ b/pl-PL/step_4.md @@ -0,0 +1,36 @@ +## Challenge + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/pl-PL/step_5.md b/pl-PL/step_5.md new file mode 100644 index 0000000..5fde839 --- /dev/null +++ b/pl-PL/step_5.md @@ -0,0 +1,3 @@ +## What can you do now? + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/pt-BR/images/12_or_330.gif b/pt-BR/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/pt-BR/images/12_or_330.gif differ diff --git a/pt-BR/images/banner.png b/pt-BR/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/pt-BR/images/banner.png differ diff --git a/pt-BR/images/bee_or_berry.gif b/pt-BR/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/pt-BR/images/bee_or_berry.gif differ diff --git a/pt-BR/images/cake_or_biscuit.gif b/pt-BR/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/pt-BR/images/cake_or_biscuit.gif differ diff --git a/pt-BR/images/five_or_three.gif b/pt-BR/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/pt-BR/images/five_or_three.gif differ diff --git a/pt-BR/images/train_model.png b/pt-BR/images/train_model.png new file mode 100644 index 0000000..415062a Binary files /dev/null and b/pt-BR/images/train_model.png differ diff --git a/pt-BR/images/wywm.png b/pt-BR/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/pt-BR/images/wywm.png differ diff --git a/pt-BR/meta.yml b/pt-BR/meta.yml new file mode 100644 index 0000000..1a3b59d --- /dev/null +++ b/pt-BR/meta.yml @@ -0,0 +1,23 @@ +title: Ensine uma máquina +hero_image: images/banner.png +description: Ensine um computador a dizer quantos dedos você está levantando! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: Você vai fazer + - + title: Adicionar imagens + completion: + - engaged + - + title: Treinar e testar + completion: + - internal + - + title: Desafio + challenge: true + completion: + - external diff --git a/pt-BR/resources/Teach a machine 1.srt b/pt-BR/resources/Teach a machine 1.srt new file mode 100644 index 0000000..e4b908e --- /dev/null +++ b/pt-BR/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Acesse o link rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +E renomeie 'Class 1' e +'Class 2' para 'Cinco' e 'Três' + +3 +00:00:10,880 --> 00:00:13,040 +Clique em 'Câmera' na classe 'Cinco' + +4 +00:00:13,040 --> 00:00:14,760 +mostre os cinco dedos + +5 +00:00:14,760 --> 00:00:19,240 +Com a outra mão, pressione e segure +o botão 'Segure para gravar' + +6 +00:00:19,240 --> 00:00:21,680 +para coletar cargas de imagens + +7 +00:00:21,680 --> 00:00:24,360 +Mude para a classe 'Três' +e colete varias imagens + +8 +00:00:24,360 --> 00:00:29,200 +de você mostrando três dedos + diff --git a/pt-BR/resources/readme.txt b/pt-BR/resources/readme.txt new file mode 100644 index 0000000..1dccbd1 --- /dev/null +++ b/pt-BR/resources/readme.txt @@ -0,0 +1 @@ +Para assistir a um vídeo com legendas no VLC (videolan.org), certifique-se de que o arquivo de vídeo e o arquivo de legenda estejam na mesma pasta e tenham o mesmo nome (por exemplo, video.mp4 e video.srt). Abra o vídeo no VLC, e ele carregará automaticamente as legendas. Se as legendas não aparecerem, clique com o botão direito do mouse na tela do vídeo, vá em **Legenda**, depois em **Adicionar arquivo de legenda** e selecione o arquivo .srt correto. Divirta-se assistindo com legendas! \ No newline at end of file diff --git a/pt-BR/resources/teach a machine 2.srt b/pt-BR/resources/teach a machine 2.srt new file mode 100644 index 0000000..afc83da --- /dev/null +++ b/pt-BR/resources/teach a machine 2.srt @@ -0,0 +1,25 @@ +1 +00:00:03,040 --> 00:00:05,320 +Clique em "Treinar modelo" e aguarde... + +2 +00:00:05,320 --> 00:00:08,920 +isso porque pode levar de dez a vinte segundos para ser concluído + +3 +00:00:08,920 --> 00:00:12,800 +Quando seu modelo é treinado, +o painel de pré-visualização será aberto + +4 +00:00:12,800 --> 00:00:18,200 +Levante cinco e três dedos e observe os índices de confiança na saída abaixo. + +5 +00:00:18,200 --> 00:00:21,440 +Por que não tentar ver se o modelo consegue reconhecer bolos ou biscoitos? + +6 +00:00:21,440 --> 00:00:27,200 +Ou abelhas e frutas vermelhas? + diff --git a/pt-BR/step_1.md b/pt-BR/step_1.md new file mode 100644 index 0000000..ad15053 --- /dev/null +++ b/pt-BR/step_1.md @@ -0,0 +1,27 @@ +## O que você vai fazer + +![A imagem mostra uma interface de aprendizado de máquina a partir da "Máquina Ensinável", onde um modelo está sendo treinado para reconhecer gestos de mão para os números "Cinco" e "Três." À direita, na seção "Visualizar", o feed da webcam exibe uma mão mostrando três dedos. Abaixo disso, a seção "Saída" mostra os resultados da classificação, com o modelo prevendo uma probabilidade de 94% para "Três" e uma pequena probabilidade de 6% para "Cinco". O modelo identificou com sucesso o gesto da mão como "Três"](images/wywm.png) + +Você vai ensinar um computador a te dizer quantos dedos você está mostrando! + +\--- collapse --- + +--- + +## title: Onde minhas imagens são armazenadas? + +- Este projeto usa uma tecnologia chamada "aprendizado de máquina". Os sistemas de aprendizado de máquina são treinados usando uma grande quantidade de dados. +- Este projeto não requer que você crie uma conta ou faça login. Para este projeto, os exemplos de imagem que você usa para criar o modelo são armazenados apenas temporariamente no seu navegador (somente na sua máquina). +- Nenhuma imagem da sua câmera é enviada para este site ou qualquer outro site. + +\--- /collapse --- + +Você precisará de uma **webcam**. + +## --- collapse --- + +## title: Sem YouTube? Baixe os vídeos! + +Você pode [baixar todos os vídeos deste projeto](https://rpf.io/p/pt-BR/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/pt-BR/step_2.md b/pt-BR/step_2.md new file mode 100644 index 0000000..f81d637 --- /dev/null +++ b/pt-BR/step_2.md @@ -0,0 +1,54 @@ +## Adicionar imagens + + +
+

+
+ + +\--- task --- + +Abra [Máquina Ensinável](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Cada classe é uma categoria que você quer que o computador reconheça. + +\--- task --- + +- Renomeie `Classe 1` para `Cinco` +- Renomeie `Classe 2` para `Três` + +\--- /task --- + +Colete imagens de `cinco` dedos. + +\--- task --- + +- Clique em **Webcam** na classe `Cinco` +- Mostre cinco dedos em direção à sua webcam (certifique-se de que toda a sua mão esteja visível) +- Com seu outro lado, pressione e segure o botão **Segure para gravar** para coletar muitas imagens + +\--- /task --- + +\--- collapse --- + +--- + +## title: Onde minhas imagens são armazenadas? + +- Nenhum dos seus dados é armazenado ou enviado para este ou qualquer outro site. +- A tecnologia é chamada de "aprendizado de máquina", mas a máquina não está aprendendo enquanto você a usa. +- Ela já foi treinada usando um grande número de fotos. + +\--- /collapse --- + +Colete imagens de `três` dedos. + +\--- task --- + +- Clique em **Webcam** na classe `Três` +- Mostre três dedos em direção à sua webcam (certifique-se de que toda a sua mão esteja visível) +- Com seu outro lado, pressione e segure o botão **Segure para gravar** para coletar muitas imagens + +\--- /task --- diff --git a/pt-BR/step_3.md b/pt-BR/step_3.md new file mode 100644 index 0000000..7216d1e --- /dev/null +++ b/pt-BR/step_3.md @@ -0,0 +1,37 @@ +## Treine o modelo + + +
+

+
+ + +\--- task --- + +Clique em **Treinar Modelo**. + +![Botão 'Treinar Modelo'.](images/train_model.png) + +\--- /task --- + +**Observação**: Seja paciente! Pode levar de 10 a 20 segundos para ser concluído. + +### Pré-visualizar e testar + +Quando seu modelo é treinado, o painel de pré-visualização será aberto. + +\--- task --- + +- Mostre **cinco** dedos e veja a seção 'Saída' embaixo da pretela. + +Você verá índices de confiança para `Cinco` e `Três`. + +\--- /task --- + +\--- task --- + +- Mostre **três** dedos +- Qual é a maior índice de confiança que você pode obter para `Cinco`? +- Qual é a maior índice de confiança que você pode obter para `Três`? + +\--- /task --- diff --git a/pt-BR/step_4.md b/pt-BR/step_4.md new file mode 100644 index 0000000..5aa1cf0 --- /dev/null +++ b/pt-BR/step_4.md @@ -0,0 +1,36 @@ +## Desafio + +\--- challenge --- + +Crie o seu próprio classificador! + +### Abelha ou framboesa? + +\--- task --- + +Uma vez comi uma abelha por engano. Ensine uma máquina a mantê-lo seguro! + +![Uma imagem de uma abelha é mostrada para uma webcam. Depois, a imagem de uma framboesa. No painel de saída abaixo do vídeo, o índice de confiança é exibido sobre se uma abelha ou uma framboesa está sendo mostrada.](images/bee_or_berry.gif) + +\--- /task --- + +### Bolo ou biscoito? + +\--- task --- + +Resolva a discussão. + +![Um pedaço de bolo é segurado em frente a uma webcam. Depois, um biscoito. No painel de saída abaixo do vídeo, o índice de confiança é exibido sobre se um bolo ou um biscoito está sendo mostrado.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Reconhecedor de resistores + +\--- task --- + +Resolva um problema para os fabricantes digitais em toda a parte! + +![Um resistor de 12 ohms é exibido para uma webcam. Em seguida, resistir a 330 ohms. No painel de saída abaixo do vídeo, o índice de confiança é exibido para saber se um resistor de 12 ohms ou 330 ohms está sendo mostrado.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/pt-BR/step_5.md b/pt-BR/step_5.md new file mode 100644 index 0000000..3455e56 --- /dev/null +++ b/pt-BR/step_5.md @@ -0,0 +1,3 @@ +## O que você pode fazer agora? + +Há muitos outros aprendizados de máquina e IA no conjunto de ferramentas [inteligência artificial](https://projects.raspberrypi.org/pt-BR/pathways/ai-toolkit). \ No newline at end of file diff --git a/pt-PT/images/12_or_330.gif b/pt-PT/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/pt-PT/images/12_or_330.gif differ diff --git a/pt-PT/images/banner.png b/pt-PT/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/pt-PT/images/banner.png differ diff --git a/pt-PT/images/bee_or_berry.gif b/pt-PT/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/pt-PT/images/bee_or_berry.gif differ diff --git a/pt-PT/images/cake_or_biscuit.gif b/pt-PT/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/pt-PT/images/cake_or_biscuit.gif differ diff --git a/pt-PT/images/five_or_three.gif b/pt-PT/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/pt-PT/images/five_or_three.gif differ diff --git a/pt-PT/images/train_model.png b/pt-PT/images/train_model.png new file mode 100644 index 0000000..e2905d1 Binary files /dev/null and b/pt-PT/images/train_model.png differ diff --git a/pt-PT/images/wywm.png b/pt-PT/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/pt-PT/images/wywm.png differ diff --git a/pt-PT/meta.yml b/pt-PT/meta.yml new file mode 100644 index 0000000..d447175 --- /dev/null +++ b/pt-PT/meta.yml @@ -0,0 +1,23 @@ +title: Ensina uma máquina +hero_image: images/banner.png +description: Ensina um computador a dizer-te quantos dedos tens levantados! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: O que vais fazer + - + title: Adiciona imagens + completion: + - engaged + - + title: Treina e testa + completion: + - internal + - + title: Desafio + challenge: true + completion: + - external diff --git a/pt-PT/resources/Teach a machine 1.srt b/pt-PT/resources/Teach a machine 1.srt new file mode 100644 index 0000000..58ea903 --- /dev/null +++ b/pt-PT/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Acede a rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +e renomea a 'Classe 1' e +a 'Classe 2' para 'Cinco' e 'Três' + +3 +00:00:10,880 --> 00:00:13,040 +Clica em **Webcam** na classe `Cinco` + +4 +00:00:13,040 --> 00:00:14,760 +e levanta cinco dedos + +5 +00:00:14,760 --> 00:00:19,240 +Com a tua outra mão, pressiona e segura +o botão 'Tocar sem soltar para gravar' + +6 +00:00:19,240 --> 00:00:21,680 +para recolher imensas imagens + +7 +00:00:21,680 --> 00:00:24,360 +Muda para a classe 'Três' +e recolhe imensas imagens + +8 +00:00:24,360 --> 00:00:29,200 +de ti a levantar três dedos + diff --git a/pt-PT/resources/readme.txt b/pt-PT/resources/readme.txt new file mode 100644 index 0000000..6da75e7 --- /dev/null +++ b/pt-PT/resources/readme.txt @@ -0,0 +1 @@ +Para assistir a um vídeo com legendas no VLC (videolan.org), certifica-te de que o arquivo do vídeo e o ficheiro das legendas está na mesma pasta e que tenham o mesmo nome (por ex.: video.mp4 e video.srt). Abre o vídeo no VLC, que ele vai carregar automaticamente as legendas. Se as legendas não aparecerem, clica com o lado direito do rato na tela do vídeo, vai a **Legendas**, depois **Adicionar Ficheiro de Legenda**, e seleciona o ficheiro .srt correto. Diverte-te a assistir com legendas! \ No newline at end of file diff --git a/pt-PT/resources/teach a machine 2.srt b/pt-PT/resources/teach a machine 2.srt new file mode 100644 index 0000000..9f7e13a --- /dev/null +++ b/pt-PT/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Clica em 'Preparar modelo' e aguarda... + +2 +00:00:05,320 --> 00:00:08,920 +porque pode levar dez a +vinte segundos para concluir + +3 +00:00:08,920 --> 00:00:12,800 +Quando o modelo estiver treinado, +o painel de pré-visualização vai abrir + +4 +00:00:12,800 --> 00:00:18,200 +Levanta cinco e três dedos e observa +a pontuação de confiança abaixo na saída. + +5 +00:00:18,200 --> 00:00:21,440 +Porque não experimentar se reconhece um bolo ou uma bolacha? + +6 +00:00:21,440 --> 00:00:27,200 +Ou abelhas e framboesas? + diff --git a/pt-PT/step_1.md b/pt-PT/step_1.md new file mode 100644 index 0000000..76bc4fd --- /dev/null +++ b/pt-PT/step_1.md @@ -0,0 +1,27 @@ +## O que vais fazer + +![A imagem mostra uma interface de uma machine learning do "Teachable Machine", onde um modelo é treinado para reconhecer gestos com a mão para os números "Cinco" e "Três". À direita, na secção "Pré-visualização", o feed da webcam exibe uma mão a mostrar três dedos. Abaixo, a secção "Saída" mostra os resultados da classificação, onde o modelo prevê 94% de probabilidade para "Três" e uma pequena probabilidade de 6% para "Cinco". O modelo identificou com sucesso o gesto da mão como "Três".](images/wywm.png) + +Vais ensinar um computador a dizer-te quantos dedos tens levantados! + +\--- collapse --- + +--- + +## title: Onde estão guardadas as minhas imagens? + +- Este projeto usa uma tecnologia chamada 'machine learning'. Os sistemas de machine learning são treinados com uma grande quantidade de dados. +- Este projeto não exige que cries uma conta ou faças login. Para este projeto, as imagens de exemplo que usas para fazer o modelo são armazenados temporariamente no teu navegador (apenas na tua máquina). +- Nenhuma imagem da tua webcam é enviada para este site ou qualquer outro. + +\--- /collapse --- + +Vais precisar de uma **webcam**. + +## --- collapse --- + +## title: Não tens Youtube? Descarrega estes vídeos! + +Podes [descarregar todos os vídeos para este projeto](https://rpf.io/p/pt-PT/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/pt-PT/step_2.md b/pt-PT/step_2.md new file mode 100644 index 0000000..b68f4dc --- /dev/null +++ b/pt-PT/step_2.md @@ -0,0 +1,54 @@ +## Adiciona imagens + + +
+

+
+ + +\--- task --- + +Abre [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Cada classe é uma categoria que tu queres que o computador reconheça. + +\--- task --- + +- Muda o nome `Classe 1` para `Cinco` +- Muda o nome `Classe 2` para `Três` + +\--- /task --- + +Reúne imagens de `cinco` dedos. + +\--- task --- + +- Clica em **Webcam** na classe `Cinco` +- Levanta cinco dedos em frente à tua webcam (certifica-te que a tua mão toda esteja visível) +- Com a tua outra mão, pressiona e segura o botão **Tocar sem soltar para gravar** para recolher muitas imagens + +\--- /task --- + +\--- collapse --- + +--- + +## title: Onde estão guardadas as minhas imagens? + +- Nenhum dos teus dados é armazenado ou enviado para este ou qualquer outro site. +- A tecnologia é chamada 'machine learning', mas não aprende enquanto estás a usá-la. +- Já foi treinada usando um grande número de fotos. + +\--- /collapse --- + +Recolhe imagens de `três` dedos. + +\--- task --- + +- Clica em **Webcam** na classe `Três` +- Levanta três dedos em frente à tua webcam (certifica-te que a tua mão toda esteja visível) +- Com a tua outra mão, pressiona e segura o botão **Tocar sem soltar para gravar** para recolher muitas imagens + +\--- /task --- diff --git a/pt-PT/step_3.md b/pt-PT/step_3.md new file mode 100644 index 0000000..2570bbd --- /dev/null +++ b/pt-PT/step_3.md @@ -0,0 +1,37 @@ +## Treina o modelo + + +
+

+
+ + +\--- task --- + +Clica em **Modelo preparado**. + +![O botão 'Modelo preparado'.](images/train_model.png) + +\--- /task --- + +**Nota:** Sê paciente! Pode levar 10 a 20 segundos para completar. + +### Pré-visualizar e testar + +Quando o modelo estiver treinado, o painel de pré-visualização vai abrir. + +\--- task --- + +- Levanta **cinco** dedos e observa a secção 'Saída' abaixo da pré-visualização. + +Vais ver pontuações de confiança para `Cinco` e `Três`. + +\--- /task --- + +\--- task --- + +- Levanta **três** dedos +- Qual é a maior pontuação de confiança que podes obter para `Cinco`? +- Qual é a maior pontuação de confiança que podes obter para `Três`? + +\--- /task --- diff --git a/pt-PT/step_4.md b/pt-PT/step_4.md new file mode 100644 index 0000000..3a7a7d0 --- /dev/null +++ b/pt-PT/step_4.md @@ -0,0 +1,36 @@ +## Desafio + +\--- challenge --- + +Cria o teu próprio classificador! + +### Abelha ou framboesa? + +\--- task --- + +Uma vez comi uma abelha por engano. Ensina a máquina a manter-te seguro! + +![Uma imagem de uma abelha é exibida para uma webcam. Depois, uma imagem de uma framboesa. No painel de saída abaixo do vídeo, a pontuação de confiança é exibida sobre se uma abelha ou uma fruta está a ser exibida.](images/bee_or_berry.gif) + +\--- /task --- + +### Bolo ou bolacha? + +\--- task --- + +Resolve a questão. + +![Um pedaço de bolo é exibido para uma webcam. Depois, uma bolacha. No painel de saída abaixo do vídeo, a pontuação de confiança é exibida sobre se um bolo ou uma bolacha está a ser exibida.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Reconhecedor de resistências + +\--- task --- + +Resolve um problema para os fabricantes do digital em toda a parte! + +![Uma resistência de 12 ohm é exibida para uma webcam. Depois, uma resistência de 330 ohm. No painel de saída abaixo do vídeo, a pontuação de confiança aparece sobre se uma resistência de 12 ohm ou uma de 330 ohm é exibida.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/pt-PT/step_5.md b/pt-PT/step_5.md new file mode 100644 index 0000000..456264b --- /dev/null +++ b/pt-PT/step_5.md @@ -0,0 +1,3 @@ +## O que se segue? + +Existem muitos outros projetos de machine learning e IA no kit de ferramentas de [inteligência artificial](https://projects.raspberrypi.org/pt-PT/pathways/ai-toolkit). \ No newline at end of file diff --git a/sk-SK/images/12_or_330.gif b/sk-SK/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/sk-SK/images/12_or_330.gif differ diff --git a/sk-SK/images/banner.png b/sk-SK/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/sk-SK/images/banner.png differ diff --git a/sk-SK/images/bee_or_berry.gif b/sk-SK/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/sk-SK/images/bee_or_berry.gif differ diff --git a/sk-SK/images/cake_or_biscuit.gif b/sk-SK/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/sk-SK/images/cake_or_biscuit.gif differ diff --git a/sk-SK/images/five_or_three.gif b/sk-SK/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/sk-SK/images/five_or_three.gif differ diff --git a/sk-SK/images/train_model.png b/sk-SK/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/sk-SK/images/train_model.png differ diff --git a/sk-SK/images/wywm.png b/sk-SK/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/sk-SK/images/wywm.png differ diff --git a/sk-SK/meta.yml b/sk-SK/meta.yml new file mode 100644 index 0000000..abf9e1e --- /dev/null +++ b/sk-SK/meta.yml @@ -0,0 +1,23 @@ +title: Teach a machine +hero_image: images/banner.png +description: Teach a computer to tell you how many fingers you are holding up! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-24" +steps: + - + title: What you will make + - + title: Add images + completion: + - engaged + - + title: Train and test + completion: + - internal + - + title: Challenge + challenge: true + completion: + - external diff --git a/sk-SK/resources/Teach a machine 1.srt b/sk-SK/resources/Teach a machine 1.srt new file mode 100644 index 0000000..555d9e7 --- /dev/null +++ b/sk-SK/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Go to rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +and rename 'Class 1' and  +'Class 2' to 'Five' and 'Three' + +3 +00:00:10,880 --> 00:00:13,040 +Click 'Webcam' in the Five class + +4 +00:00:13,040 --> 00:00:14,760 +and hold up five fingers + +5 +00:00:14,760 --> 00:00:19,240 +With your other hand, press and  +hold the 'Hold to record' button + +6 +00:00:19,240 --> 00:00:21,680 +to gather loads of images + +7 +00:00:21,680 --> 00:00:24,360 +Switch to the 'Three' class  +and gather loads of images + +8 +00:00:24,360 --> 00:00:29,200 +of you holding up three fingers + diff --git a/sk-SK/resources/readme.txt b/sk-SK/resources/readme.txt new file mode 100644 index 0000000..0e0956c --- /dev/null +++ b/sk-SK/resources/readme.txt @@ -0,0 +1 @@ +To watch a video with subtitles on VLC (videolan.org), ensure the video file and subtitle file are in the same folder and have the exact same name (e.g., video.mp4 and video.srt). Open the video in VLC, and it will automatically load the subtitles. If the subtitles don’t appear, right-click the video screen, go to **Subtitle**, then **Add Subtitle File**, and select the correct .srt file. Enjoy watching with subtitles! \ No newline at end of file diff --git a/sk-SK/resources/teach a machine 2.srt b/sk-SK/resources/teach a machine 2.srt new file mode 100644 index 0000000..92c64a4 --- /dev/null +++ b/sk-SK/resources/teach a machine 2.srt @@ -0,0 +1,27 @@ +1 +00:00:03,040 --> 00:00:05,320 +Click 'Train model' and hang on... + +2 +00:00:05,320 --> 00:00:08,920 +because it could take ten to  +twenty seconds to complete + +3 +00:00:08,920 --> 00:00:12,800 +When your model is trained,  +the preview panel will open + +4 +00:00:12,800 --> 00:00:18,200 +Hold up five and three fingers and watch  +the confidence scores in the output below. + +5 +00:00:18,200 --> 00:00:21,440 +Why not see if it can recognise cake or biscuits? + +6 +00:00:21,440 --> 00:00:27,200 +Or bees and berries? + diff --git a/sk-SK/step_1.md b/sk-SK/step_1.md new file mode 100644 index 0000000..d2e1ce6 --- /dev/null +++ b/sk-SK/step_1.md @@ -0,0 +1,27 @@ +## What you will make + +![The image shows a machine learning interface from "Teachable Machine" where a model is being trained to recognize hand gestures for the numbers "Five" and "Three." On the right, in the "Preview" section, the webcam feed displays a hand showing three fingers. Below this, the "Output" section shows the classification results, with the model predicting a 94% probability for "Three" and a small 6% probability for "Five." The model has successfully identified the hand gesture as "Three."](images/wywm.png) + +You will teach a computer to tell you how many fingers you are holding up! + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- This project uses a technology called 'machine learning'. Machine learning systems are trained using a large amount of data. +- This project does not require you to create an account or log in. For this project, the image examples you use to make the model are only stored temporarily in your browser (only on your machine). +- No images from your webcam are sent to this website or any other website. + +\--- /collapse --- + +You will need a **webcam**. + +## --- collapse --- + +## title: No YouTube? Download the videos! + +You can [download all the videos for this project](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/sk-SK/step_2.md b/sk-SK/step_2.md new file mode 100644 index 0000000..2fb7b0e --- /dev/null +++ b/sk-SK/step_2.md @@ -0,0 +1,54 @@ +## Add images + + +
+

+
+ + +\--- task --- + +Open [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Each class is a category that you want the computer to recognise. + +\--- task --- + +- Rename `Class 1` to `Five` +- Rename `Class 2` to `Three` + +\--- /task --- + +Gather images of `five` fingers. + +\--- task --- + +- Click **Webcam** in the `Five` class +- Hold up five fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- + +\--- collapse --- + +--- + +## title: Where are my images stored? + +- None of your data is stored or sent to this or any other site. +- The technology is called 'machine learning', but it is not learning while you use it. +- It has already been trained using a large number of photos. + +\--- /collapse --- + +Gather images of `three` fingers. + +\--- task --- + +- Click **Webcam** in the `Three` class +- Hold up three fingers to your webcam (make sure your whole hand is in view) +- With your other hand, press and hold the **Hold to Record** button to gather lots of images + +\--- /task --- diff --git a/sk-SK/step_3.md b/sk-SK/step_3.md new file mode 100644 index 0000000..7e13577 --- /dev/null +++ b/sk-SK/step_3.md @@ -0,0 +1,37 @@ +## Train the model + + +
+

+
+ + +\--- task --- + +Click **Train Model**. + +![The 'Train Model' button.](images/train_model.png) + +\--- /task --- + +**Note**: Be patient! It can take 10 to 20 seconds to complete. + +### Preview and test + +When your model is trained, the preview panel will open. + +\--- task --- + +- Hold up **five** fingers and watch the 'Output' section underneath the preview. + +You will see confidence scores for `Five` and `Three`. + +\--- /task --- + +\--- task --- + +- Hold up **three** fingers +- What is the highest confidence score you can get for `Five`? +- What is the highest confidence score you can get for `Three`? + +\--- /task --- diff --git a/sk-SK/step_4.md b/sk-SK/step_4.md new file mode 100644 index 0000000..adbc2be --- /dev/null +++ b/sk-SK/step_4.md @@ -0,0 +1,36 @@ +## Challenge + +\--- challenge --- + +Create your own classifier! + +### Bee or berry? + +\--- task --- + +I once ate a bee by mistake. Teach a machine to keep you safe! + +![An image of a bee is held up to a web camera. Then, an image of a berry. In the output panel underneath the video, the confidence score is displayed as to whether a bee or a berry is being shown.](images/bee_or_berry.gif) + +\--- /task --- + +### Cake or biscuit? + +\--- task --- + +Settle the argument. + +![A piece of cake is held up to a web camera. Then, a biscuit. In the output panel underneath the video, the confidence score is displayed as to whether a cake or a biscuit is being shown.](images/cake_or_biscuit.gif) + +\--- /task --- + +### Resistor recogniser + +\--- task --- + +Solve a problem for digital makers everywhere! + +![A 12 ohm resistor is held up to a web camera. Then, a 330 ohm resistor. In the output panel underneath the video, the confidence score is displayed as to whether a 12 ohm or a 330 ohm resistor is being shown.](images/12_or_330.gif) + +\--- /task --- +\--- /challenge --- diff --git a/sk-SK/step_5.md b/sk-SK/step_5.md new file mode 100644 index 0000000..5fde839 --- /dev/null +++ b/sk-SK/step_5.md @@ -0,0 +1,3 @@ +## What can you do now? + +There are lots of other machine learning and AI projects in the [artificial intelligence](https://projects.raspberrypi.org/en/pathways/ai-toolkit) toolkit. \ No newline at end of file diff --git a/uk-UA/images/12_or_330.gif b/uk-UA/images/12_or_330.gif new file mode 100644 index 0000000..2e8fa66 Binary files /dev/null and b/uk-UA/images/12_or_330.gif differ diff --git a/uk-UA/images/banner.png b/uk-UA/images/banner.png new file mode 100644 index 0000000..d730039 Binary files /dev/null and b/uk-UA/images/banner.png differ diff --git a/uk-UA/images/bee_or_berry.gif b/uk-UA/images/bee_or_berry.gif new file mode 100644 index 0000000..b3c3498 Binary files /dev/null and b/uk-UA/images/bee_or_berry.gif differ diff --git a/uk-UA/images/cake_or_biscuit.gif b/uk-UA/images/cake_or_biscuit.gif new file mode 100644 index 0000000..2355b18 Binary files /dev/null and b/uk-UA/images/cake_or_biscuit.gif differ diff --git a/uk-UA/images/five_or_three.gif b/uk-UA/images/five_or_three.gif new file mode 100644 index 0000000..cf492d8 Binary files /dev/null and b/uk-UA/images/five_or_three.gif differ diff --git a/uk-UA/images/train_model.png b/uk-UA/images/train_model.png new file mode 100644 index 0000000..87add9d Binary files /dev/null and b/uk-UA/images/train_model.png differ diff --git a/uk-UA/images/wywm.png b/uk-UA/images/wywm.png new file mode 100644 index 0000000..c15860c Binary files /dev/null and b/uk-UA/images/wywm.png differ diff --git a/uk-UA/meta.yml b/uk-UA/meta.yml new file mode 100644 index 0000000..f62e74c --- /dev/null +++ b/uk-UA/meta.yml @@ -0,0 +1,23 @@ +title: Навчи машину +hero_image: images/banner.png +description: Навчи компʼютер розрізняти, скільки пальців ти показуєш! +version: 1 +listed: true +copyedit: true +last_tested: "2024-05-06" +steps: + - + title: Що ти зробиш + - + title: Додай зображення + completion: + - engaged + - + title: Навчи і протестуй + completion: + - internal + - + title: Додаткове завдання + challenge: true + completion: + - external diff --git a/uk-UA/resources/Teach a machine 1.srt b/uk-UA/resources/Teach a machine 1.srt new file mode 100644 index 0000000..7b4670a --- /dev/null +++ b/uk-UA/resources/Teach a machine 1.srt @@ -0,0 +1,35 @@ +1 +00:00:02,840 --> 00:00:03,960 +Перейди на rpf.io/tm + +2 +00:00:05,920 --> 00:00:10,880 +і перейменуй «Class 1» і +«Class 2» на «П’ять» і «Три». + +3 +00:00:10,880 --> 00:00:13,040 +Натисни **Webcam** («вебкамера») у класі «П'ять» + +4 +00:00:13,040 --> 00:00:14,760 +і покажи пʼять пальців. + +5 +00:00:14,760 --> 00:00:19,240 +Іншою рукою натисни й +утримуй кнопку Hold to record («Утримувати для запису»), + +6 +00:00:19,240 --> 00:00:21,680 +щоб зібрати багато зображень. + +7 +00:00:21,680 --> 00:00:24,360 +Перейди до класу «Три» +і отримай багато зображень, + +8 +00:00:24,360 --> 00:00:29,200 +де ти тримаєш три пальці. + diff --git a/uk-UA/resources/readme.txt b/uk-UA/resources/readme.txt new file mode 100644 index 0000000..663519d --- /dev/null +++ b/uk-UA/resources/readme.txt @@ -0,0 +1 @@ +Щоб переглянути відео із субтитрами у програмі VLC (videolan.org), переконайся, що файл відео і файл субтитрів знаходяться в одній папці та мають однакові назви (наприклад, video.mp4 і video.srt). Відкрий відео у VLC, і програма автоматично завантажить субтитри. Якщо субтитри не з’являються, клацни правою кнопкою миші по відео, вибери **Субтитри**, потім **Додати файл субтитрів** і вибери відповідний файл .srt. Приємного перегляду з субтитрами! \ No newline at end of file diff --git a/uk-UA/resources/teach a machine 2.srt b/uk-UA/resources/teach a machine 2.srt new file mode 100644 index 0000000..0a507ef --- /dev/null +++ b/uk-UA/resources/teach a machine 2.srt @@ -0,0 +1,28 @@ +1 +00:00:03,040 --> 00:00:05,320 +Натисни Train model («Тренувати модель») і зачекай... + +2 +00:00:05,320 --> 00:00:08,920 +оскільки тренування може зайняти +від десяти до двадцяти секунд. + +3 +00:00:08,920 --> 00:00:12,800 +Коли модель закінчить навчання, +відкриється панель попереднього перегляду + +4 +00:00:12,800 --> 00:00:18,200 +Покажи п’ять, а потім три пальці та подивись, + як змінюються показники впевненості. + +5 +00:00:18,200 --> 00:00:21,440 +Чому б не перевірити, чи може модель +відрізнити тістечко від печива? + +6 +00:00:21,440 --> 00:00:27,200 +Чи бджолу від ягоди? + diff --git a/uk-UA/step_1.md b/uk-UA/step_1.md new file mode 100644 index 0000000..f10c699 --- /dev/null +++ b/uk-UA/step_1.md @@ -0,0 +1,27 @@ +## Що ти зробиш + +![На зображенні показано інтерфейс машинного навчання Teachable Machine, де модель навчається розпізнавати жести на позначення чисел «пʼять» і «три». Праворуч у розділі Preview («Попередній перегляд») панель вебкамери показує руку з трьома пальцями. Нижче розділ Output («Результат») показує результати класифікації: модель передбачає «три» з імовірністю в 94 % та «п’ять» із невеликою ймовірністю в 6 %. Модель успішно розпізнала жест як «три».](images/wywm.png) + +Ти навчиш компʼютер розрізняти, скільки пальців ти показуєш! + +\--- collapse --- + +--- + +## title: Де зберігаються мої зображення? + +- Цей проєкт використовує технологію під назвою «машинне навчання». Системи машинного навчання навчаються з використанням великої кількості даних. +- Для цього проєкту тобі не потрібно створювати обліковий запис або входити в систему. У цьому проєкті приклади зображень, які ти використовуєш для створення моделі, лише тимчасово зберігаються у твоєму браузері (лише на твоєму компʼютері). +- Зображення з твоєї вебкамери не надсилаються на цей вебсайт або будь-який інший. + +\--- /collapse --- + +Тобі знадобиться **вебкамера**. + +## --- collapse --- + +## title: Немає доступу до YouTube? Завантаж відео! + +Ти можеш [завантажити всі відео для цього проєкту](https://rpf.io/p/en/teach-a-machine-go){:target="_blank"}. + +\--- /collapse --- \ No newline at end of file diff --git a/uk-UA/step_2.md b/uk-UA/step_2.md new file mode 100644 index 0000000..1653fb7 --- /dev/null +++ b/uk-UA/step_2.md @@ -0,0 +1,54 @@ +## Додай зображення + + +
+

+
+ + +\--- task --- + +Відкрий вебсайт [Teachable Machine](https://rpf.io/tm){:target="_blank"}. + +\--- /task --- + +Кожен клас — це категорія, яку комп’ютер має розпізнавати. + +\--- task --- + +- Зміни назву `Class 1` на `Пʼять` +- Зміни назву `Class 2` на `Три` + +\--- /task --- + +Отримай зображення `п'яти` пальців. + +\--- task --- + +- Натисни **Webcam** («вебкамера») у класі `П'ять` +- Піднеси п’ять пальців до вебкамери (переконайся, що камера бачить всю твою долоню) +- Іншою рукою натисни й утримуй кнопку **Hold to Record** («Утримуйте для запису»), щоб зібрати багато зображень + +\--- /task --- + +\--- collapse --- + +--- + +## title: Де зберігаються мої зображення? + +- Твої дані не зберігаються та не надсилаються на цей або будь-який інший сайт. +- Ця технологія називається «машинне навчання», але вона навчається не під час того, як ти її використовуєш. +- Її вже навчили з використанням великої кількості фотографій. + +\--- /collapse --- + +Отримай зображення `трьох` пальців. + +\--- task --- + +- Натисни **Webcam** («вебкамера») у класі `Три` +- Піднеси три пальці до вебкамери (переконайся, що камера бачить всю твою долоню) +- Іншою рукою натисни й утримуй кнопку **Hold to Record** («Утримуйте для запису»), щоб зібрати багато зображень + +\--- /task --- diff --git a/uk-UA/step_3.md b/uk-UA/step_3.md new file mode 100644 index 0000000..7f3997c --- /dev/null +++ b/uk-UA/step_3.md @@ -0,0 +1,37 @@ +## Навчи модель + + +
+

+
+ + +\--- task --- + +Натисни **Train Model** («Навчити модель»). + +![Кнопка «Навчити модель».](images/train_model.png) + +\--- /task --- + +**Примітка**: не поспішай! Навчання може тривати від 10 до 20 секунд. + +### Попередній перегляд і тестування + +Коли модель закінчить навчання, відкриється панель попереднього перегляду. + +\--- task --- + +- Піднеси **п’ять** пальців і подивись на панель результатів (Output) під попереднім переглядом. + +Ти побачиш, наскільки модель упевнена у своєму передбаченні щодо «п’яти» та «трьох» пальців. + +\--- /task --- + +\--- task --- + +- Піднеси **три** пальці +- Який найвищий відсоток упевненості ти можеш отримати для «П’яти»? +- Який найвищий відсоток упевненості ти можеш отримати для «Трьох»? + +\--- /task --- diff --git a/uk-UA/step_4.md b/uk-UA/step_4.md new file mode 100644 index 0000000..45f7aa1 --- /dev/null +++ b/uk-UA/step_4.md @@ -0,0 +1,36 @@ +## Додаткове завдання + +\--- challenge --- + +Створи власний класифікатор! + +### Бджола чи ягода? + +\--- task --- + +Одного разу я випадково з'їв бджолу. Навчи машину оберігати тебе! + +![До вебкамери підноситься зображення бджоли. Потім зображення ягоди. На панелі результатів під відео показано рівень упевненості щодо того, чи це бджола чи ягода.](images/bee_or_berry.gif) + +\--- /task --- + +### Пиріг чи печиво? + +\--- task --- + +Створи класифікатор смаколиків. + +![До вебкамери підноситься шматок пирога. Потім печиво. На панелі результатів під відео показано рівень упевненості щодо того, чи це пиріг чи печиво.](images/bee_or_berry.gif) + +\--- /task --- + +### Розпізнавач резисторів + +\--- task --- + +Допоможи любителям електроніки у всьому світі! + +![До вебкамери підноситься резистор на 12 Ом. Потім резистор на 330 Ом. На панелі результатів під відео показано рівень упевненості щодо того, чи це резистор на 12 чи 330 Ом.](images/bee_or_berry.gif) + +\--- /task --- +\--- /challenge --- diff --git a/uk-UA/step_5.md b/uk-UA/step_5.md new file mode 100644 index 0000000..0d217bf --- /dev/null +++ b/uk-UA/step_5.md @@ -0,0 +1,3 @@ +## Що ти тепер вмієш? + +У напрямі [«Інструменти штучного інтелекту»](https://projects.raspberrypi.org/en/pathways/ai-toolkit) є багато інших проєктів про машинне навчання та ШІ. \ No newline at end of file