Error when changing the torchvision.transforms.RandomCrop((128,64),padding=4) to Resize when training Deep network

[ithmz]

I have changed the torchvision.transforms.RandomCrop((128,64),padding=4) to torchvision.transforms.Resize((128,64)) as in transform_test (because my image size is small) And when I changed it to square, there's problem appears: RuntimeError: mat1 and mat2 shapes cannot be multiplied (64x2560 and 512x256)

I know that I have to modify the structure of the DeepSort network, but don't know exactly where to change it. Any help is appreciated

[sekisek]

yes I also need help with the same thing