/CNN_batchnorm_backpropagation_from_scratch

implement CNN and batchnorm layer's backpropagation from scratch

Primary LanguagePython

build convolution neural network and batch norm backprop from scratch

Common Deep Learning Framework hides the backpropagation part of the neural network
in the frontend, this is very convenient but sometimes makes it hard to understand,
this repo implements the Convolution Neural Network and BatchNorm layer's backpropagation from scratch, using pytorch just for gpu acceleration and didn't use the automatic backprop function of the library.

train the net

It's training on the CIFAR10 dataset after training 3 epochs(about 5 minutes on a RTX3060GPU),
you should get about 67 % test accuracy

python _1_train.py

draw plots

python _2_test.py

“”