ResNet18 #3
Description
class ResNet(nn.Module):
def __init__(self, ResBlock, layer_list, num_classes, num_channels=3, stride=2): #<- fixed
super(ResNet, self).__init__()
self.in_channels = 64
self.stride = stride #<- fixed
self.conv1 = nn.Conv2d(num_channels, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.batch_norm1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU()
self.max_pool = nn.MaxPool2d(kernel_size = 3, stride=2, padding=1)
self.layer1 = self._make_layer(ResBlock, layer_list[0], planes=64)
self.layer2 = self._make_layer(ResBlock, layer_list[1], planes=128, stride=self.stride) #<- fixed
self.layer3 = self._make_layer(ResBlock, layer_list[2], planes=256, stride=self.stride) #<- fixed
self.layer4 = self._make_layer(ResBlock, layer_list[3], planes=512, stride=self.stride) #<- fixed
self.avgpool = nn.AdaptiveAvgPool2d((1,1))
self.fc = nn.Linear(512*ResBlock.expansion, num_classes)
def forward(self, x):
x = self.relu(self.batch_norm1(self.conv1(x)))
x = self.max_pool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.reshape(x.shape[0], -1)
x = self.fc(x)
return x
def _make_layer(self, ResBlock, blocks, planes, stride=1):
ii_downsample = None
layers = []
if stride != 1 or self.in_channels != planes*ResBlock.expansion:
ii_downsample = nn.Sequential(
nn.Conv2d(self.in_channels, planes*ResBlock.expansion, kernel_size=1, stride=stride),
nn.BatchNorm2d(planes*ResBlock.expansion)
)
layers.append(ResBlock(self.in_channels, planes, i_downsample=ii_downsample, stride=stride))
self.in_channels = planes*ResBlock.expansion
for i in range(blocks-1):
layers.append(ResBlock(self.in_channels, planes))
return nn.Sequential(*layers)
def ResNet18(num_classes, channels=3):
return ResNet(Block, [2,2,2,2], num_classes, channels, stride=1)
If you fix the code like that, it would work.