The result of my training is very poor，why？

Hello, I tried to train the binary network in the way of the paper XNOR-Net （https://github.com/allenai/XNOR-Net), however, the training result is very poor, the structure of my model is the same as the pretrained model you give ,and the training parameters are based on the parameters given in the paper. I used BCECriterion, the loss is always around 0.027 when i trained more then 47 epoch, it doesn't drop anymore, and the prediction is poor too. I‘m very confused why the result is so poor ,could you tell me some training details？ Thank you very much!

The issue references training a binary network using XNOR-Net methodology with poor results. Examine the training scripts and model definitions in the repository to understand the binary convolution implementation. Check loss computation with BCECriterion and compare hyperparameters against the paper. Running existing training tests or examples may help reproduce the issue.

Written by the indexing model from the issue text.