I got a modified resnet, it change the latest AVGPool2d layer and remove latest Linear layer. when AVGPool2d's parameter stride not setting , it will be setting with kernel_size.
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7) # official is `nn.AvgPool2d(7, stride=1)`
# self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
# x = self.fc(x)
return x
then, I found a simple way to reconstruct the resnet. just remove latest 2 layer and add a new AvgPool2d with stride is None.
class ResNet50MoveLinear(nn.Module):
def __init__(self):
"""Load the pretrained ResNet-50 and replace top fc layer."""
super(ResNet50MoveLinear, self).__init__()
resnet = models.resnet50(pretrained=True)
modules = list(resnet.children())[:-2] # delete the last fc layer.
self.resnet = nn.Sequential(*modules)
self.avgpool = nn.AvgPool2d(7)
# self.linear = nn.Linear(resnet.fc.in_features, embed_size)
# self.bn = nn.BatchNorm1d(embed_size, momentum=0.01)
def forward(self, images):
"""Extract feature vectors from input images."""
# with torch.no_grad():
# features = self.resnet(images)
# features = features.reshape(features.size(0), -1)
# features = self.bn(self.linear(features))
features = self.resnet(images) # need gradient
features = self.avgpool(features)
features = features.view(features.size(0), -1) # reshape
return features
I think these 2 methods will be same and will get a similar results, but second method get a worse results(accuracy: 0.918 -> 0.895). and I canβt find the difference.
I would greatly appreciate for some suggestions, thanks!