Difference between revisions of "X-LINUX-AI - image classification using Coral Edge TPU TensorFlow Lite Python runtime"

[checked revision] [quality revision]
m
m
 

This article explains how to experiment with Coral Edge TPU[1] applications for image classification based on the MobileNet v1 model using TensorFlow Lite Python runtime.

Info.png Python applications are good for prototyping but are less efficient than C/C++ applications

1 Description[edit]

The image classification[2] neural network model allows identification of the subject represented by an image. It classifies an image into various classes.

Python Coral edge TPU image classification application

The application enables OpenCV camera streaming (or test data picture) and the Coral Edge TPU[1] TensorFlow Lite[3] interpreter runing the NN inference based on the camera (or test data pictures) inputs.
The user interface is implemented using Python GTK.

The model used with this application is the MobileNet v1 downloaded from the Coral GitHub testing models[4].

2 Installation[edit]

2.1 Install from the OpenSTLinux AI package repository[edit]

Warning.png The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA). The detailed content licenses can be found here.

After having configured the AI OpenSTLinux package you can install the X-LINUX-AI components for this application:

Board $> apt-get install tflite-cv-apps-edgetpu-image-classification-python

Then restart the demo launcher:

Board $> systemctl restart weston@root

2.2 Source code location[edit]

The label_tfl_edgetpu.py Python script is available:

  • in the Openembedded OpenSTLinux Distribution with X-LINUX-AI Expansion Packageexpansion package:
<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py
  • on the target:
/usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/label_tfl_edgetpu.py
  • on GitHub:
https://github.com/STMicroelectronics/meta-st-stm32mpu-ai/tree/dunfell/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py

3 How to use the application[edit]

3.1 Launching via the demo launcher[edit]

Launch python tfl edgetpu image classification.png

3.2 Executing with the command line[edit]

The Python script label_tfl_edgetpu.py application is located in the userfs partition:

/usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/label_tfl_edgetpu.py

It accepts the following input parameters:

usage: label_tfl_edgetpu.py [-h] [-i IMAGE] [-v VIDEO_DEVICE] [--frame_width FRAME_WIDTH] [--frame_height FRAME_HEIGHT]               
                            [--framerate FRAMERATE] [-m MODEL_FILE] [-l LABEL_FILE] [--lib_edgetpu {max,throttled}]                   
                            [--input_mean INPUT_MEAN] [--input_std INPUT_STD] [--top_k TOP_K]                                         
                                                                                                                                      
optional arguments:                                                                                                                   
  -h, --help            show this help message and exit                                                                               
  -i IMAGE, --image IMAGE                                                                                                             
                        image directory with image to be classified                                                                   
  -v VIDEO_DEVICE, --video_device VIDEO_DEVICE                                                                                        
                        video device (default /dev/video0)                                                                            
  --frame_width FRAME_WIDTH                                                                                                           
                        width of the camera frame (default is 320)                                                                    
  --frame_height FRAME_HEIGHT                                                                                                         
                        height of the camera frame (default is 240)                                                                   
  --framerate FRAMERATE                                                                                                               
                        framerate of the camera (default is 15fps)                                                                    
  -m MODEL_FILE, --model_file MODEL_FILE                                                                                              
                        .tflite model to be executed                                                                                  
  -l LABEL_FILE, --label_file LABEL_FILE                                                                                              
                        name of file containing labels                                                                                
  --lib_edgetpu {max,throttled}                                                                                                       
                        Choose the version of your EdgeTPU runtime                                                                    
  --input_mean INPUT_MEAN                                                                                                             
                        input mean                                                                                                    
  --input_std INPUT_STD                                                                                                               
                        input standard deviation                                                                                      
  --top_k TOP_K         The top_k classes to show 

3.3 Testing with MobileNet V1[edit]

The model used for test is the mobilenet_v1_1.0_224_quant_edgetpu.tflite downloaded from Coral GitHub testing models[4].

Info.png The different objects the neural network is able to classify are listed in the labels.txt file located in the target:

/usr/local/demo-ai/computer-vision/models/mobilenet/labels.txt


To ease launching of the Python script, two shell scripts are available:

  • launch image classification based on camera frame inputs
Board $> /usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/launch_python_label_tfl_edgetpu_mobilenet.sh
  • launch image classification based on the pictures located in /usr/local/demo-ai/computer-vision/models/mobilenet/testdata directory:
Board $> /usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/launch_python_label_tfl_edgetpu_mobilenet_testdata.sh
Info.png Note that you need to populate the testdata directory with your own data sets.

The pictures are then randomly read from the testdata directory

4 References[edit]


This article explains how to experiment with {{Highlight|'''Coral Edge TPU'''<ref name=edgetpu_url>[https://coral.ai/ Coral Edge TPU]</ref>}} applications for image classification based on the MobileNet v1 model using TensorFlow Lite Python runtime.

{{Info|Python applications are good for prototyping but are less efficient than C/C++ applications}}

==Description==
The '''image classification'''<ref name=tflite_image_class_url>[https://www.tensorflow.org/lite/models/image_classification/overview TFLite image classification overview]</ref> neural network model allows identification of the subject represented by an image. It classifies an image into various classes. <br>


[[File: python_tfl_edgetpu_image_classification_application_screenshot.png|thumb|upright=2|center|link=|Python Coral edge TPU image classification application]]

The application enables OpenCV camera streaming (or test data picture) and the {{Highlight|'''Coral Edge TPU'''<ref name=edgetpu_url></ref>}} {{Highlight|TensorFlow Lite<ref name=tensorflowlite_url>[https://www.tensorflow.org/lite TensorFlow Lite]</ref>}} interpreter runing the NN inference based on the camera (or test data pictures) inputs.<br>

The user interface is implemented using Python GTK.<br>


The model used with this application is the {{Highlight|MobileNet v1}} downloaded from the  '''Coral GitHub testing models'''<ref name=coral_testing_modelsl>[https://github.com/google-coral/edgetpu/blob/master/test_data/mobilenet_v1_1.0_224_quant_edgetpu.tflite Coral GitHub testing models]</ref>.

==Installation==
===Install from the OpenSTLinux AI package repository===
{{Warning|{{SoftwareLicenseAgreement | distribution=X-LINUX-AI}}}}
After having [[X-LINUX-AI_OpenSTLinux_Expansion_Package#Configure the AI OpenSTLinux package repository|configured the AI OpenSTLinux package]] you can install the X-LINUX-AI components for this application:
 {{Board$}} apt-get install tflite-cv-apps-edgetpu-image-classification-python
Then restart the demo launcher:
 {{Board$}} systemctl restart weston@root

===Source code location===
The '''label_tfl_edgetpu.py''' Python script is available:
* in the Openembedded OpenSTLinux Distribution with X-LINUX-AI Expansion Packageexpansion package:
:'''<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py'''
* on the target:
:'''/usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/label_tfl_edgetpu.py'''
* on GitHub: 
:https://github.com/STMicroelectronics/meta-st-stm32mpu-ai/tree/dunfell/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py

==How to use the application==
===Launching via the demo launcher===
[[File: launch_python_tfl_edgetpu_image_classification.png|thumb|upright=2|center|link=]]

===Executing with the command line===
The Python script '''label_tfl_edgetpu.py''' application is located in the userfs partition:
 /usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/label_tfl_edgetpu.py
It accepts the following input parameters:
<pre>

usage: label_tfl_edgetpu.py [-h] [-i IMAGE] [-v VIDEO_DEVICE] [--frame_width FRAME_WIDTH] [--frame_height FRAME_HEIGHT]               
                            [--framerate FRAMERATE] [-m MODEL_FILE] [-l LABEL_FILE] [--lib_edgetpu {max,throttled}]                   
                            [--input_mean INPUT_MEAN] [--input_std INPUT_STD] [--top_k TOP_K]                                         

optional arguments:                                                                                                                   
  -h, --help            show this help message and exit                                                                               
  -i IMAGE, --image IMAGE                                                                                                             
                        image directory with image to be classified                                                                   
  -v VIDEO_DEVICE, --video_device VIDEO_DEVICE                                                                                        
                        video device (default /dev/video0)                                                                            
  --frame_width FRAME_WIDTH                                                                                                           
                        width of the camera frame (default is 320)                                                                    
  --frame_height FRAME_HEIGHT                                                                                                         
                        height of the camera frame (default is 240)                                                                   
  --framerate FRAMERATE                                                                                                               
                        framerate of the camera (default is 15fps)                                                                    
  -m MODEL_FILE, --model_file MODEL_FILE                                                                                              
                        .tflite model to be executed                                                                                  
  -l LABEL_FILE, --label_file LABEL_FILE                                                                                              
                        name of file containing labels                                                                                
  --lib_edgetpu {max,throttled}                                                                                                       
                        Choose the version of your EdgeTPU runtime                                                                    
  --input_mean INPUT_MEAN                                                                                                             
                        input mean                                                                                                    
  --input_std INPUT_STD                                                                                                               
                        input standard deviation                                                                                      
  --top_k TOP_K         The top_k classes to show </pre>


===Testing with MobileNet V1===
The model used for test is the {{Highlight|mobilenet_v1_1.0_224_quant_edgetpu.tflite}} downloaded from '''Coral GitHub testing models'''<ref name=coral_testing_modelsl></ref>.

{{Info|The different objects the neural network is able to classify are listed in the labels.txt file located in the target:
/usr/local/demo-ai/computer-vision/models/mobilenet/labels.txt}}

To ease launching of the Python script, two shell scripts are available:
* launch image classification based on camera frame inputs
 {{Board$}} /usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/launch_python_label_tfl_edgetpu_mobilenet.sh

*launch image classification based on the pictures located in '''/usr/local/demo-ai/computer-vision/models/mobilenet/testdata''' directory:
 {{Board$}} /usr/local/demo-ai/computer-vision/tflite-image-classification-edgetpu/python/launch_python_label_tfl_edgetpu_mobilenet_testdata.sh

{{Info|Note that you need to populate the testdata directory with your own data sets.<br>

The pictures are then randomly read from the testdata directory}}

==References==<references />

<noinclude>

[[Category:Artificial intelligence sample apps|21]]
{{PublicationRequestId | 16539 | 24Jun'20}}</noinclude>
Line 23: Line 23:
 
===Source code location===
 
===Source code location===
 
The '''label_tfl_edgetpu.py''' Python script is available:
 
The '''label_tfl_edgetpu.py''' Python script is available:
* in the Openembedded OpenSTLinux Distribution with X-LINUX-AI expansion package:
+
* in the Openembedded OpenSTLinux Distribution with X-LINUX-AI Expansion Package:
 
:'''<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py'''
 
:'''<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/tflite-cv-apps-edgetpu/files/image-classification/python/label_tfl_edgetpu.py'''
 
* on the target:
 
* on the target: