models-pytorch
models-pytorch copied to clipboard
Knight825
This is a torchvision style CNN models collection based on pytorch.
self.transition = _Csp_Transition(trans_in_features,trans_in_features//2) this code snippet replaced by csp_infeatures+trans_in_features because each block gets concatenated x+6dense= >csp transition -- x+12dense=>csp_transition
def forward(self,x): features = [x[:,self.csp_num_features1:,...]] of line 31 stores features as a tuple because of the additional brackets this breaks the code you have to undo the bracket outside :)
num_features ??? 
@Knight825 I also built csp resnet50 from ```csresnet.cfg``` file in ```https://github.com/WongKinYiu/CrossStagePartialNetworks``` repo. And i didn't know that is it correct. Could you help me to check? Thank you. ``` CSPResNet(...
