Speed profiling improvements (#2648)

* Speed profiling improvements

* Update torch_utils.py

deepcopy() required to avoid adding elements to model.

* Update torch_utils.py

utils/torch_utils.py

@@ -191,7 +191,7 @@ def fuse_conv_and_bn(conv, bn):
     # prepare filters
     w_conv = conv.weight.clone().view(conv.out_channels, -1)
     w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
-    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size()))
+    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
 
     # prepare spatial bias
     b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias