Loss function in main_mnist.py

itayhubara / BinaryNet.pytorch

Binarized Neural Network (BNN) for pytorch

505 stars 126 forks source link

Closed zhaohui-yang closed 5 years ago

zhaohui-yang commented 6 years ago

Line 86, log softmax Line 94, Cross Entropy Loss

In the mnist example, you combine Cross Entropy Loss with log softmax, why not using NLLLoss + logsoftmax?

alldbi commented 4 years ago

Yes, you are right. It should be either only corss_entropy or NLL+logsoftmax.