| | |
| | | angles.append(self.fc_finetune(torch.cat((preangles, x), 1))) |
| | | |
| | | return pre_yaw, pre_pitch, pre_roll, angles |
| | | |
| | | class Hopenet_shape(nn.Module): |
| | | # This is just Hopenet with 3 output layers for yaw, pitch and roll. |
| | | def __init__(self, block, layers, num_bins, shape_bins): |
| | | self.inplanes = 64 |
| | | super(Hopenet_shape, 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) |
| | | self.fc_yaw = nn.Linear(512 * block.expansion, num_bins) |
| | | self.fc_pitch = nn.Linear(512 * block.expansion, num_bins) |
| | | self.fc_roll = nn.Linear(512 * block.expansion, num_bins) |
| | | self.fc_shape_0 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_1 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_2 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_3 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_4 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_5 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_6 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_7 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_8 = nn.Linear(512 * block.expansion, shape_bins) |
| | | self.fc_shape_9 = nn.Linear(512 * block.expansion, shape_bins) |
| | | |
| | | 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) |
| | | yaw = self.fc_yaw(x) |
| | | pitch = self.fc_pitch(x) |
| | | roll = self.fc_roll(x) |
| | | |
| | | shape = [] |
| | | shape.append(self.fc_shape_0(x)) |
| | | shape.append(self.fc_shape_1(x)) |
| | | shape.append(self.fc_shape_2(x)) |
| | | shape.append(self.fc_shape_3(x)) |
| | | shape.append(self.fc_shape_4(x)) |
| | | shape.append(self.fc_shape_5(x)) |
| | | shape.append(self.fc_shape_6(x)) |
| | | shape.append(self.fc_shape_7(x)) |
| | | shape.append(self.fc_shape_8(x)) |
| | | shape.append(self.fc_shape_9(x)) |
| | | |
| | | return yaw, pitch, roll, shape |