Skip to content

Commit 94fce17

Browse files
cshilwantcshilwant
committed
feat(configs): Enable Machine learning guide for Sitara
* Enable Foundational_Components_Machine_Learning & all the sub-pages in linux toc tree for SITARA platforms. Signed-off-by: Chirag Shilwant <c-shilwant@ti.com>
1 parent edf4a33 commit 94fce17

5 files changed

Lines changed: 22 additions & 6 deletions

File tree

‎configs/AM62LX/AM62LX_linux_toc.txt‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -85,6 +85,12 @@ linux/Foundational_Components/Tools/Development_Tools
8585
linux/Foundational_Components/Tools/Pin_Mux_Tools
8686
#linux/Foundational_Components/Tools/GPIO_Tools
8787
linux/Foundational_Components_IPC62l
88+
linux/Foundational_Components_Machine_Learning
89+
linux/Foundational_Components/Machine_Learning/arm_compute_library
90+
linux/Foundational_Components/Machine_Learning/armnn
91+
linux/Foundational_Components/Machine_Learning/nnstreamer
92+
linux/Foundational_Components/Machine_Learning/onnxrt
93+
linux/Foundational_Components/Machine_Learning/tflite
8894
#linux/Foundational_Components_OPTEE
8995
linux/Foundational_Components_ATF
9096
linux/Foundational_Components_Virtualization

‎configs/AM62PX/AM62PX_linux_toc.txt‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -108,6 +108,11 @@ linux/Foundational_Components/Tools/Flash_via_UART
108108
linux/Foundational_Components/Tools/GPIO_Tools
109109
linux/Foundational_Components_IPC62px
110110
linux/Foundational_Components_Machine_Learning
111+
linux/Foundational_Components/Machine_Learning/arm_compute_library
112+
linux/Foundational_Components/Machine_Learning/armnn
113+
linux/Foundational_Components/Machine_Learning/nnstreamer
114+
linux/Foundational_Components/Machine_Learning/onnxrt
115+
linux/Foundational_Components/Machine_Learning/tflite
111116
linux/Foundational_Components_OPTEE
112117
linux/Foundational_Components_ATF
113118
linux/Foundational_Components_Multimedia_wave5

‎configs/AM62X/AM62X_linux_toc.txt‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -122,7 +122,6 @@ linux/Foundational_Components/Machine_Learning/armnn
122122
linux/Foundational_Components/Machine_Learning/nnstreamer
123123
linux/Foundational_Components/Machine_Learning/onnxrt
124124
linux/Foundational_Components/Machine_Learning/tflite
125-
linux/Foundational_Components/Machine_Learning/tflite_j7
126125

127126
linux/Foundational_Components_OPTEE
128127
linux/Foundational_Components_ATF

‎configs/AM64X/AM64X_linux_toc.txt‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -74,6 +74,12 @@ linux/Foundational_Components_Kernel_Users_Guide
7474
linux/Foundational_Components_Kernel_LTP-DDT_Validation
7575
linux/Foundational_Components_Kernel_FAQs
7676
linux/Foundational_Components_Security
77+
linux/Foundational_Components_Machine_Learning
78+
linux/Foundational_Components/Machine_Learning/arm_compute_library
79+
linux/Foundational_Components/Machine_Learning/armnn
80+
linux/Foundational_Components/Machine_Learning/nnstreamer
81+
linux/Foundational_Components/Machine_Learning/onnxrt
82+
linux/Foundational_Components/Machine_Learning/tflite
7783
linux/Foundational_Components_Migration_Guide
7884
linux/Foundational_Components_Secure_Boot
7985
linux/Foundational_Components_Filesystem

‎source/linux/Foundational_Components/Machine_Learning/tflite.rst‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -7,10 +7,10 @@ Introduction
77
************
88

99
LiteRT, formerly known as TensorFlow Lite, is an open-source library designed for running machine learning models on mobile and embedded devices.
10-
|__SDK_FULL_NAME__| has integrated open source `TensorFlow Lite <https://www.tensorflow.org/lite>`__ for deep learning inference at the edge.
10+
|__SDK_FULL_NAME__| has integrated open-source `TensorFlow Lite <https://www.tensorflow.org/lite>`__ for deep learning inference at the edge.
1111
TensorFlow Lite runs on Arm for Sitara devices (AM3/AM4/AM5/AM6).
1212

13-
It supports on-device inference with low latency and a compact binary size. You can find more information at https://www.tensorflow.org/lite
13+
It supports on-device inference with low latency and a compact binary size. You can find more information at `TensorFlow Lite <https://www.tensorflow.org/lite>`__
1414

1515
********
1616
Features
@@ -56,14 +56,14 @@ This library offers optimized implementations for a subset of TensorFlow Lite op
5656

5757
.. note::
5858

59-
XNNPACK delegate is not supported for ARMv7 based platforms like AM335x & AM437x.
59+
The XNNPACK delegate is not supported for ARMv7-based platforms like AM335x and AM437x.
6060
Refer `XNNPACK supported architectures <https://github.com/google/XNNPACK?tab=readme-ov-file#supported-architectures>`__ for more details.
6161

6262
*******************************
6363
Benchmark Tool for TFLite Model
6464
*******************************
6565

66-
The :file:`tisdk-default-image` wic image from |__SDK_DOWNLOAD_URL__| by default contains a pre-installed benchmarking application named as :command:`benchmark_model`.
66+
The :file:`tisdk-default-image` wic image from |__SDK_DOWNLOAD_URL__| by default contains a pre-installed benchmarking application named :command:`benchmark_model`.
6767
It's a C++ binary designed to benchmark a TFLite model and its individual operators. It takes a TFLite model, generates random inputs, and repeatedly runs the model
6868
for a specified number of runs. After running the benchmark, it reports aggregate latency statistics.
6969

@@ -80,7 +80,7 @@ To execute the benchmark using CPU for computation, use the following command:
8080
8181
root@<machine>:~# /opt/tensorflow-lite/tools/benchmark_model --graph=/usr/share/oob-demo-assets/models/ssd_mobilenet_v2_coco.tflite --use_xnnpack=false
8282
83-
The output of the benchmarking application should be similar to,
83+
The output of the benchmarking application should be similar to:
8484

8585
.. code-block:: console
8686

0 commit comments

Comments
 (0)