Open xiaosen-wang opened 5 years ago
_, loss = ########## TO DO ############ total_loss += loss Here the loss variable name will overwrite the loss function so that in next epoch there will be a error "Can not convert a float32 into a Tensor or Operation."
@jiangchengyike rename it to loss_
loss_
_, loss = ########## TO DO ############ total_loss += loss Here the loss variable name will overwrite the loss function so that in next epoch there will be a error "Can not convert a float32 into a Tensor or Operation."