Tiny-Imagenet-binarized-training

(Do not consider the accuracy)

Modified from brevitas CNV example.

https://github.com/Xilinx/brevitas/blob/master/src/brevitas_examples/bnn_pynq/models/CNV.py

Usage:

After download and unzip the Tiny imagenet dataset from http://cs231n.stanford.edu/tiny-imagenet-200.zip run

python trans.py

Which will rearrange the dict of the Tiny imagenet dataset and make it follow the reading requirement for the prtorch.

After that run

python traing_smaller.py

Which will finish the training process.