| |
| |
| |
|
|
| |
|
|
| import math |
|
|
| import torch.nn as nn |
|
|
| import utils.ops as ops |
|
|
|
|
| class BasicBlock(nn.Module): |
| expansion = 1 |
| def __init__(self, inplanes, planes, stride=1, downsample=None): |
| super(BasicBlock, self).__init__() |
| self.conv1 = ops.conv3x3(inplanes, planes, stride) |
| self.bn1 = nn.BatchNorm2d(planes) |
| self.conv2 = ops.conv3x3(planes, planes) |
| self.bn2 = nn.BatchNorm2d(planes) |
| 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) |
|
|
| if self.downsample is not None: |
| residual = self.downsample(x) |
|
|
| out += residual |
| out = self.relu(out) |
| return out |
|
|
|
|
| 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 * Bottleneck.expansion, kernel_size=1, bias=False) |
| self.bn3 = nn.BatchNorm2d(planes * Bottleneck.expansion) |
| 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, dataset, depth, num_classes, bottleneck=False): |
| super(ResNet, self).__init__() |
| self.dataset = dataset |
| if self.dataset.startswith("CIFAR10"): |
| self.inplanes = 16 |
| if bottleneck == True: |
| n = int((depth - 2) / 9) |
| block = Bottleneck |
| else: |
| n = int((depth - 2) / 6) |
| block = BasicBlock |
|
|
| self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False) |
| self.bn1 = nn.BatchNorm2d(self.inplanes) |
| self.relu = nn.ReLU(inplace=True) |
| self.layer1 = self._make_layer(block, 16, n) |
| self.layer2 = self._make_layer(block, 32, n, stride=2) |
| self.layer3 = self._make_layer(block, 64, n, stride=2) |
| self.avgpool = nn.AvgPool2d(8) |
| self.fc = nn.Linear(64 * block.expansion, num_classes) |
|
|
| elif dataset == "ImageNet": |
| 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 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) |
| self.bn1 = nn.BatchNorm2d(64) |
| self.relu = nn.ReLU(inplace=True) |
| |
| 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.layer3 = self._make_layer(blocks[depth], 256, layers[depth][2], stride=2) |
| self.layer4 = self._make_layer(blocks[depth], 512, layers[depth][3], stride=2) |
| self.avgpool = nn.AvgPool2d(7) |
| 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)) |
| 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): |
| if self.dataset == "CIFAR10" or self.dataset == "CIFAR100": |
| x = self.conv1(x) |
| x = self.bn1(x) |
| x = self.relu(x) |
|
|
| x = self.layer1(x) |
| x = self.layer2(x) |
| x = self.layer3(x) |
|
|
| x = self.avgpool(x) |
| x = x.view(x.size(0), -1) |
| x = self.fc(x) |
|
|
| elif self.dataset == "ImageNet" or self.dataset == "Tiny_ImageNet": |
| x = self.conv1(x) |
| x = self.bn1(x) |
| x = self.relu(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 |
|
|
