Open victor000000 opened 4 years ago
for the stride 2 conv in class SPP_NET, we have to ensure that the size of tensor > 26 * 26
otherwise, the kernal(4 4) of self.conv5 will larger than the conv5 input i.e. the conv5 input will < 4 4 if the input x in forward < 26 * 26
for the stride 2 conv in class SPP_NET, we have to ensure that the size of tensor > 26 * 26
otherwise, the kernal(4 4) of self.conv5 will larger than the conv5 input i.e. the conv5 input will < 4 4 if the input x in forward < 26 * 26