This directory contains a python3 example that shows how to classify images using deep neural networks on the Intel Neural Compute Stick 2 using a simple GUI. This sample can be used with GoogLeNet, SqueezeNet V1.0, and AlexNet. All models are sourced from the Open Model Zoo.
The provided Makefile does the following:
- Builds the IR files using the model files from Open Model Zoo.
- Copies the IR files from the model directory to the project base directory.
- Runs the sample.
To run the example code do the following :
- Open a terminal and change directory to the project base directory
- Type the following command in the terminal:
When the application runs normally and is able to connect to the NCS device, the output will be similar to this:
classifier_gui: Running the sample... python3 classifier_gui.py Starting application... - Plugin: Myriad - IR File: ../../caffe/GoogLeNet/googlenet-v1.xml - Input Shape: [1, 3, 224, 224] - Output Shape: [1, 1000] - Labels File: ../../data/ilsvrc12/synset_labels.txt - Mean File: None - Image File: ../../data/images/nps_mug.png ********** Results *********** Prediction is 91.0% coffee mug
You should also see the image on which inference was performed.
This program requires:
- 1 NCS device
- OpenVINO 2020.1 Toolkit
- PIL (Python Imaging library) with Image and Imagetk modules
Note: To install Scikit-image, use the following command:
sudo apt-get install -y python3-pil.imagetk
Note: To install PIL with ImageTk, use the following command:
pip3 install scikit-image --user
Note: To install scikit-image, you may need to upgrade your pip version to pip version => 9.0.1. You can try using the command
pip3 install --upgrade pip==9.0.1 to upgrade to pip version 9.0.1.
Note: All development and testing has been done on Ubuntu 16.04 on an x86-64 machine.
*It may run with older versions but you may see some glitches such as the GUI Window not closing when you click the X in the title bar, and other key binding issues.
Provided Makefile has various targets that help with the above mentioned tasks.
Runs the sample application.
Shows available targets.
Builds and/or gathers all the required files needed to run the application.
Gathers all of the required data need to run the sample.
Builds all of the dependencies needed to run the sample.
Compiles an IR file from a default model to be used when running the sample.
Checks required packages that aren’t installed as part of the OpenVINO installation. Note: python3-pil.imagetk and scikit-image will need to be installed to run this sample.
Uninstalls requirements that were installed by the sample program. This command will uninstall python3-pil.imagetk and scikit-image.
Removes all the temporary files that are created by the Makefile.