The Age/GenderNet network (on GitHub can be used for image classification. The provided Makefile does the following
- Downloads the Caffe prototxt file and makes few changes necessary to work with the Movidius Neural Compute SDK
- Downloads and generates the required age/gender mean data
- Downloads the .caffemodel file which was trained and provided by Gil Levi.
- Profiles, Compiles and Checks the network using the Neural Compute SDK.
- There is a run.py provided that does a single inference on a provided image as an example on how to use the network using the Neural Compute API
Provided Makefile describes various targets that help with the above mentioned tasks.
Runs ncprofile, nccompile and run.
Runs the provided network on the NCS and generates per layer statistics that are helpful for understanding the performance of the network on the Neural Compute Stick.
Uses the network description and the trained weights files to generate a Movidius internal 'graph' format file. This file is later used for loading the network on to the Neural Compute Stick and executing the network.
Runs the provided run.py file which sends a single image to the Neural Compute Stick and receives and displays the inference results.
Runs the network on Caffe on CPU and runs the network on the Neural Compute Stick. Check then compares the two results to make sure they are consistent with each other.
Removes all the temporary files that are created by the Makefile