Legacy autograd function error

[etemtezcan]

to fix "Legacy autograd function with non-static forward method is deprecated. "
RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method
which appeared on when using pytorch1.8

[nuel77]

This pr gives the following error..

Learning rate: 0.01
Traceback (most recent call last):
  File "C:\Users\emman\OneDrive\Desktop\s8\S7\MainProject\main_repo\XNOR-Net-PyTorch\MNIST\main.py", line 189, in <module>
    train(epoch)
  File "C:\Users\emman\OneDrive\Desktop\s8\S7\MainProject\main_repo\XNOR-Net-PyTorch\MNIST\main.py", line 39, in train
    output = model(data)
  File "C:\Users\emman\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\emman\OneDrive\Desktop\s8\S7\MainProject\main_repo\XNOR-Net-PyTorch\MNIST\models\LeNet_5.py", line 95, in forward
    x = self.bin_conv2(x)
  File "C:\Users\emman\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\emman\OneDrive\Desktop\s8\S7\MainProject\main_repo\XNOR-Net-PyTorch\MNIST\models\LeNet_5.py", line 55, in forward
    x, mean = BinActive.apply(x)
ValueError: too many values to unpack (expected 2)