class ResNet(nn.Module):
def init(self, dataset, depth, num_classes, bottleneck=False):
super(ResNet, self).init()
self.dataset = dataset
blocks ={18: BasicBlock, 34: BasicBlock, 50: Bottleneck, 101: Bottleneck, 152: Bottleneck, 200: Bottleneck}
layers ={18: [2, 2, 2, 2], 34: [3, 4, 6, 3], 50: [3, 4, 6, 3], 101: [3, 4, 23, 3], 152: [3, 8, 36, 3], 200: [3, 24, 36, 3]}
assert layers[depth], 'invalid detph for ResNet (depth should be one of 18, 34, 50, 101, 152, and 200)'
self.inplanes = 64
self.conv1_3d = nn.Conv3d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False)
self.aveadpool1_3d = nn.AdaptiveAvgPool3d((128,128,1))
self.conv1 = nn.Conv2d(self.inplanes, self.inplanes, 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(blocks[depth], 64, layers[depth][0])
self.layer2 = self._make_layer(blocks[depth], 128, layers[depth][1], stride=2)
self.dropout20 = nn.Dropout(p=0.2)
self.layer3 = self._make_layer(blocks[depth], 256, layers[depth][2], stride=2)
self.dropout30 = nn.Dropout(p=0.3)
self.layer4 = self._make_layer(blocks[depth], 512, layers[depth][3], stride=2)
self.dropout40 = nn.Dropout(p=0.4)
# self.avgpool = nn.AvgPool2d(7)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout50 = nn.Dropout(p=0.5)
self.fc = nn.Linear(512 * blocks[depth].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))
if isinstance(m, nn.Conv3d):
n = m.kernel_size[0] * m.kernel_size[1] *m.kernel_size[2]* 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_3d(x)
x = self.aveadpool1_3d(x)
x = torch.squeeze(x, -1)
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.dropout20(x)
x = self.layer3(x)
#x = self.dropout30(x)
x = self.layer4(x)
#x = self.dropout40(x)
x = self.avgpool(x)
x = self.dropout50(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
