Shortcut quantization (+, *)

[Siamw]

I'm leaving an issue to see if there's something I haven't caught in the code.

Did you guys quantize the results of the shortcut??

because at QBasicBlock, it does not have a quantization part after addition (EWGS/CIFAR10/custom_models.py Line 83~85).

Thanks.

[junghyup-lee]

Both weights and activations are quantized inside a QConv module, right before applying a convolution operation. (see custom_modules.py#L134.)
The output of QBasicBlock in custom_models.py#85 is fed into the QConv module in the next block in which the quantization is performed.