Upload mask_predictor.py

refer/lib/mask_predictor.py

@@ -0,0 +1,72 @@
+import torch
+from torch import nn
+from torch.nn import functional as F
+from collections import OrderedDict
+
+
+class SimpleDecoding(nn.Module):
+    def __init__(self, dims, factor=2):
+        super(SimpleDecoding, self).__init__()
+
+        hidden_size = dims[-1]//factor
+        c4_size = dims[-1] 
+        c3_size = dims[-2]
+        c2_size = dims[-3]
+        c1_size = dims[-4]
+
+        self.conv1_4 = nn.Conv2d(c4_size+c3_size, hidden_size, 3, padding=1, bias=False)
+        self.bn1_4 = nn.BatchNorm2d(hidden_size)
+        self.relu1_4 = nn.ReLU()
+        self.conv2_4 = nn.Conv2d(hidden_size, hidden_size, 3, padding=1, bias=False)
+        self.bn2_4 = nn.BatchNorm2d(hidden_size)
+        self.relu2_4 = nn.ReLU()
+
+        self.conv1_3 = nn.Conv2d(hidden_size + c2_size, hidden_size, 3, padding=1, bias=False)
+        self.bn1_3 = nn.BatchNorm2d(hidden_size)
+        self.relu1_3 = nn.ReLU()
+        self.conv2_3 = nn.Conv2d(hidden_size, hidden_size, 3, padding=1, bias=False)
+        self.bn2_3 = nn.BatchNorm2d(hidden_size)
+        self.relu2_3 = nn.ReLU()
+
+        self.conv1_2 = nn.Conv2d(hidden_size + c1_size, hidden_size, 3, padding=1, bias=False)
+        self.bn1_2 = nn.BatchNorm2d(hidden_size)
+        self.relu1_2 = nn.ReLU()
+        self.conv2_2 = nn.Conv2d(hidden_size, hidden_size, 3, padding=1, bias=False)
+        self.bn2_2 = nn.BatchNorm2d(hidden_size)
+        self.relu2_2 = nn.ReLU()
+
+        self.conv1_1 = nn.Conv2d(hidden_size, 2, 1)
+
+    def forward(self, x_c4, x_c3, x_c2, x_c1):
+        # fuse Y4 and Y3
+        if x_c4.size(-2) < x_c3.size(-2) or x_c4.size(-1) < x_c3.size(-1):
+            x_c4 = F.interpolate(input=x_c4, size=(x_c3.size(-2), x_c3.size(-1)), mode='bilinear', align_corners=True)
+        x = torch.cat([x_c4, x_c3], dim=1)
+        x = self.conv1_4(x)
+        x = self.bn1_4(x)
+        x = self.relu1_4(x)
+        x = self.conv2_4(x)
+        x = self.bn2_4(x)
+        x = self.relu2_4(x)
+        # fuse top-down features and Y2 features
+        if x.size(-2) < x_c2.size(-2) or x.size(-1) < x_c2.size(-1):
+            x = F.interpolate(input=x, size=(x_c2.size(-2), x_c2.size(-1)), mode='bilinear', align_corners=True)
+        x = torch.cat([x, x_c2], dim=1)
+        x = self.conv1_3(x)
+        x = self.bn1_3(x)
+        x = self.relu1_3(x)
+        x = self.conv2_3(x)
+        x = self.bn2_3(x)
+        x = self.relu2_3(x)
+        # fuse top-down features and Y1 features
+        if x.size(-2) < x_c1.size(-2) or x.size(-1) < x_c1.size(-1):
+            x = F.interpolate(input=x, size=(x_c1.size(-2), x_c1.size(-1)), mode='bilinear', align_corners=True)
+        x = torch.cat([x, x_c1], dim=1)
+        x = self.conv1_2(x)
+        x = self.bn1_2(x)
+        x = self.relu1_2(x)
+        x = self.conv2_2(x)
+        x = self.bn2_2(x)
+        x = self.relu2_2(x)
+
+        return self.conv1_1(x)