next

.gitignore

@@ -2,4 +2,5 @@
 *.npy
 data/*
 output/*
-*.jpg
+*.jpg
+*.png

code/hopenet.py

@@ -340,93 +340,3 @@ def forward(self, x):
         angles.append(preangles)
 
         return pre_yaw, pre_pitch, pre_roll, angles, sr_output
-
-class Hopenet_LSTM(nn.Module):
-    # This is just Hopenet with 3 output layers for yaw, pitch and roll.
-    def __init__(self, block, layers, num_bins):
-        self.inplanes = 64
-        super(Hopenet_LSTM, 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.softmax = nn.Softmax()
-        self.fc_finetune = nn.Linear(512 * block.expansion + 3, 3)
-
-        self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda()
-
-        self.lstm = nn.LSTM(512 * block.expansion + 3, 256 * block.expansion, 2, batch_first=True)
-        self.fc_lstm = nn.Linear(256 * block.expansion, 3)
-
-        self.block_expansion = block.expansion
-
-        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)
-        pre_yaw = self.fc_yaw(x)
-        pre_pitch = self.fc_pitch(x)
-        pre_roll = self.fc_roll(x)
-
-        # Yaw, pitch, roll
-        yaw = self.softmax(pre_yaw)
-        yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99
-        pitch = self.softmax(pre_pitch)
-        pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99
-        roll = self.softmax(pre_roll)
-        roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99
-        yaw = yaw.view(yaw.size(0), 1)
-        pitch = pitch.view(pitch.size(0), 1)
-        roll = roll.view(roll.size(0), 1)
-        preangles = torch.cat([yaw, pitch, roll], 1)
-
-        residuals, _ = self.lstm(torch.cat((preangles, x), 1), (h0, c0))
-        residuals = self.fc_lstm(residuals[:, -1, :])
-        final_angles = preangles + residuals
-
-        return pre_yaw, pre_pitch, pre_roll, preangles, final_angles