Open haoyu12S opened 5 years ago
under the official pytorch code is def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( *conv1x1(self.inplanes, planes block.expansion, stride),* nn.BatchNorm2d(planes block.expansion), )
But if you check the paper https://arxiv.org/abs/1512.03385 the downsample convolution kernel size is 3x3
what is the difference influence the output? Pytorch change the idea or there is the incorrect codes. Thanks
under the official pytorch code is def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( *conv1x1(self.inplanes, planes block.expansion, stride),* nn.BatchNorm2d(planes block.expansion), )
But if you check the paper https://arxiv.org/abs/1512.03385 the downsample convolution kernel size is 3x3
what is the difference influence the output? Pytorch change the idea or there is the incorrect codes. Thanks