Hi, I notice that the last fc layer in resnet38_cls.py is defined as self.fc8 = nn.Conv2d(4096, 20, 1, bias=False), while I found another implementation define the last layer as a linear self.fc = nn.Linear(2048, num_classes), I wonder why do you use convolution instead, and is there any difference?
Hi, I notice that the last fc layer in resnet38_cls.py is defined as
self.fc8 = nn.Conv2d(4096, 20, 1, bias=False)
, while I found another implementation define the last layer as a linearself.fc = nn.Linear(2048, num_classes)
, I wonder why do you use convolution instead, and is there any difference?