Rename files for easier handling

-Removed whitespace from tutorial makrdown filenames
- Fixed relative reference to images

Author: aweinert-MIT

README.md

@@ -4,7 +4,6 @@ Tutorial for the Low Altitude Disaster Imagery (LADI) dataset. This tutorial was
 
 - [Tutorials Guide](#tutorials-guide)
   - [Getting Started](#getting-started)
-  - [Getting Dataset](#getting-dataset)
   - [Clean and Validate LADI Dataset](#clean-and-validate-ladi-dataset)
   - [PyTorch Data Loading](#pytorch-data-loading)
   - [Train and Test A Classifier](#train-and-test-a-classifier)
@@ -14,46 +13,40 @@ Tutorial for the Low Altitude Disaster Imagery (LADI) dataset. This tutorial was
 
 ## Getting Started
 
-[Getting Started](https://github.com/NaeRong/DS440_Capstone/blob/master/Tutorials/Getting%20Started.md)
+[Getting Started](./Tutorials/Get_Started.md)
 
 This documentation is about installing AWS tools and configuring AWS environment to download LADI dataset and load dataset in Python locally and remotely.
 
-## Getting Dataset
-
-[Getting Dataset](https://github.com/NaeRong/DS440_Capstone/blob/master/Data)
-
-This folder contains dataset with 2000 images and labels.
-
 ## Clean and Validate LADI Dataset
 
-[Clean and Validate LADI Dataset](https://github.com/NaeRong/DS440_Capstone/blob/master/Tutorials/Clean%20and%20Validate%20LADI%20Dataset.md)
+[Clean and Validate LADI Dataset](./Tutorials/Clean_Validate.md)
 
 This documentation is about clean the LADI dataset. For this project, we have only extracted 2000 images for training.
 
 ## PyTorch Data Loading
 
-[PyTorch Data Loading](https://github.com/NaeRong/DS440_Capstone/blob/master/Tutorials/Pytorch%20Data%20Load.md)
+[PyTorch Data Loading](./Tutorials/Pytorch_Data_Load.md)
 
 This documentation is about loading LADI dataset in PyTorch framework including examples of writing custom `Dataset`, `Transforms` and `Dataloader`.
 
 ## Train and Test A Classifier
 
-[Train and Test A Classifier](https://github.com/NaeRong/DS440_Capstone/blob/master/Tutorials/Train%20and%20Test%20A%20Classifier.md)
+[Train and Test A Classifier](./Tutorials/Train_Test_Classifier.md)
 
 This documentation is about training and testing a classifier model using Convolutional Neural Network (CNN) from scratch.
 
 ## Fine Tuning Torchvision Models
 
-[Fine Tuning Torchvision Models](Tutorials/Fine%20Tuning%20Torchvision%20Models.md)
+[Fine Tuning Torchvision Models](./Tutorials/Fine_Tune_Torchvision_Models.md)
 
 This documentation is about training and testing a classifier model using pre-trained ResNet and AlexNet.
 
 ## SageMaker Build Train and Deploy ML Models
 
-[SageMaker Build Train and Deploy ML Models](Tutorials/SageMaker%20-%20Build,%20Train,%20and%20Deploy%20ML%20Model.md)
+[SageMaker Build Train and Deploy ML Models](./Tutorials/SageMaker_Intro.md)
 
 This documentation is about migrating model scripts into the AWS SageMaker environment.
 
 ## Distribution Statement
 
-[BSD -Clause License](https://github.com/LADI-Dataset/ladi-tutorial/blob/master/LICENSE)
+[BSD -Clause License](https://github.com/LADI-Dataset/ladi-tutorial/blob/master/LICENSE)

…rials/Clean and Validate LADI Dataset.md Tutorials/Clean_Validate.mdTutorials/Clean and Validate LADI Dataset.md renamed to Tutorials/Clean_Validate.md Tutorials/Clean and Validate LADI Dataset.md renamed to Tutorials/Clean_Validate.md

@@ -22,7 +22,8 @@
 Pytorch provides `cnn_finetune`, which includes multiple deep learning models, pre-trained on the ImageNet dataset. The package automatically replaces classifier on top of the network, which allows the user to train a network with a dataset that has a different number of classes. 
 Also, `cnn_finetune` allows users to add a dropout layer or a custom pooling layer.
 
-In this project, we are focusing on ResNet and AlexNet
+In this project, we are focusing on ResNet and AlexNet:
+
 - ResNet (resnet18, resnet34, resnet50, resnet101, resnet152)
 - AlexNet (alexnet)
 - DenseNet (densenet161)
@@ -94,7 +95,9 @@ parser.add_argument('--no-cuda', action='store_true', default=False,
 parser.add_argument('--model-name', type=str, default='resnet34', metavar='M',
                     help='model name (default: resnet34)')
 ```
+
 Users can use "to.device" to switch the training from using cpu to gpu.
+
 ```python
 args = parser.parse_args()
 use_cuda = not args.no_cuda and torch.cuda.is_available()
@@ -170,6 +173,7 @@ def test(model, test_loader, criterion=nn.CrossEntropyLoss()):
 ```
 
 ## Run Training and Testing Step
+
 Finally, the last step is to setup the loss for the model, then run the training and testing function for the set number of epochs.
 In this step, we also create an optimizer that only updates the desired parameters. To construct an Optimizer you have to give it an iterable containing the parameters (all should be Variable s) to optimize. Then, you can specify optimizer-specific options such as the learning rate, weight decay, etc.
 The common optimizer includes:
@@ -207,9 +211,10 @@ In PyTorch, the user can save the trained model into a .pt or .pth file extensio
 In this step, we used the existing model to predict the new dataset.
 
 Parameter Tuning Example: (define new parameter using "parser.add_argument" function)
-* Change the number of epochs from 30 to 50 
-* Change the batch size from 4 to 16
-* Change the learing rate from 0.1 to 0.01
+
+- Change the number of epochs from 30 to 50
+- Change the batch size from 4 to 16
+- Change the learing rate from 0.1 to 0.01
 
 ### ResNet / DenseNet / MobileNet
 
@@ -305,7 +310,7 @@ print('Predicted: ', ' '.join('%5s' % predicted[j]
                               for j in range(8)))
 ```
 
-![pred.png](./Images/pred.png)
+![pred.png](../Images/pred.png)
 
 ## Model Accuracy
 
@@ -334,7 +339,7 @@ In terms of future improvement, we are looking into fine-tuning the MobilNetV2 a
 
 The true positives rate and true negatives rate are both about 80%, which indicates a good precision / recall of our model.
 
-![confusionmatrix](./Images/cm.png)
+![confusionmatrix](../Images/cm.png)
 
 ### Python Script for Confusion Matrix
 

…orials/Fine Tuning Torchvision Models.md Tutorials/Fine_Tune_Torchvision_Models.mdTutorials/Fine Tuning Torchvision Models.md renamed to Tutorials/Fine_Tune_Torchvision_Models.md Tutorials/Fine Tuning Torchvision Models.md renamed to Tutorials/Fine_Tune_Torchvision_Models.md

@@ -162,7 +162,7 @@ image_path = 'Images/FEMA_CAP/1012/20118/VIRB0002_fa5065eb-773a-4b41-8f2c-80a734
 im = Image.open(image_path)
 plt.imshow(im, cmap='Greys_r')
 ```
-![img](https://github.com/NaeRong/DS440_Capstone/blob/master/Images/010_0775_4365f589-de67-4561-8fdd-f1ac1ac1ae07.jpg)
+![img](../Images/010_0775_4365f589-de67-4561-8fdd-f1ac1ac1ae07.jpg)
 
 ## Distribution Statement
 

Tutorials/Getting Started.md Tutorials/Get_Started.mdTutorials/Getting Started.md renamed to Tutorials/Get_Started.md

@@ -221,7 +221,7 @@ for i in range(len(flood_tiny_dataset)):
 
 The first 4 samples will shown below.
 
-![img](./Images/custom_flood_tiny_dataset_output.png)
+![img](../Images/custom_flood_tiny_dataset_output.png)
 
 Output:
 
@@ -388,7 +388,7 @@ for i_batch, sample_batched in enumerate(dataloader):
 
 The transformed images in the 4th batch:
 
-![img](./Images/dataloader_batch_result.png)
+![img](../Images/dataloader_batch_result.png)
 
 The index and size of images in batch:
 

Tutorials/Pytorch Data Load.md Tutorials/Pytorch_Data_Load.mdTutorials/Pytorch Data Load.md renamed to Tutorials/Pytorch_Data_Load.md

@@ -4,4 +4,4 @@ Default directory for tutorials markdowns.
 
 ## Distribution Statement
 
-[BSD -Clause License](https://github.com/LADI-Dataset/ladi-tutorial/blob/master/LICENSE)
+[BSD -Clause License](https://github.com/LADI-Dataset/ladi-tutorial/blob/master/LICENSE)

Tutorials/README.md

@@ -10,28 +10,29 @@
 
 1. Enter Amazon SageMaker console
 
-![img](./Images/sagemaker1.png)
+![img](../Images/sagemaker1.png)
 
 2. Navigate to the Amazon SageMaker dashboard located in the left-hand panel and select **Notebook Instances**.
-![img](./Images/sagemaker2.png)
+![img](../Images/sagemaker2.png)
 
 3. Select **Create notebook instance** button to begin creating the notebook instance.
-![img](./Images/sagemaker3.png)
+![img](../Images/sagemaker3.png)
 
 4. Enter a name in the **Notebook instance name** field.  Keep ml.t2.medium as the **Notebook instance type**.
-![img](./Images/sagemaker4.png)
+![img](../Images/sagemaker4.png)
 
 5. An IAM role must be specified to enable the notebook instance to access and securely upload data to Amazon S3.  In the **IAM role** field, choose **Create a new role** to have Amazon SageMaker create a role with the required permissions and assign it to your instance.
-![img](./Images/sagemaker5.png)
+![img](../Images/sagemaker5.png)
 
 6. In the **Create an IAM role** box, select **Any S3 bucket**.  This allows your Amazon SageMaker instance to access all S3 buckets in your account.  For now, we will allow **Any S3 bucket** until we upload our our own bucket.
-![img](./Images/sagemaker6.png)
+![img](../Images/sagemaker6.png)
 
    1. If you would like to clone our Git respository for your notebook instance, go to the **Git repositories** box and select **Clone a public Git repository to this notebook instance only**.  Then insert "https://github.com/LADI-Dataset/ladi-tutorial.git" in the **Git repository URL** box.
+
 7. Choose **Create role**.
 
 8. On the **Notebook instances** page, your new instance with your specified name should be shown with a **Pending** status.  Your noteobok instance should transition from **Pending** to **InService** status in less than 2 minutes.
-![img](./Images/sagemaker7.png)
+![img](../Images/sagemaker7.png)
 
 ## Distribution Statement
 

…r - Build, Train, and Deploy ML Model.md Tutorials/SageMaker_Intro.mdTutorials/SageMaker - Build, Train, and Deploy ML Model.md renamed to Tutorials/SageMaker_Intro.md Tutorials/SageMaker - Build, Train, and Deploy ML Model.md renamed to Tutorials/SageMaker_Intro.md

@@ -255,7 +255,7 @@ imshow(torchvision.utils.make_grid(images))
 print('GroundTruth: ', ' '.join('%5s' % labels[j] for j in range(16)))
 ```
 
-![img](https://github.com/NaeRong/DS440_Capstone/blob/master/Images/testimages.png)
+![testimages.png](../Images/testimages.png)
 
 Out: