add feature smoothing

models/pose_encoder.py

@@ -42,6 +42,11 @@ class ConvNeXtReverseMaskPose(nn.Module):
         if norm_layer is None:
             norm_layer = partial(LayerNorm2d, eps=1e-6)
 
+        stage: List[nn.Module] = []
+        for _ in range(3):
+            stage.append(block(block_setting[0].input_channels, layer_scale, 0))
+        self.stage_smooth = nn.Sequential(*stage).to(device)
+
         self.first = nn.Sequential(
                         nn.ConvTranspose2d(block_setting[0].input_channels, block_setting[0].out_channels, kernel_size=2, stride=2),
                         norm_layer(block_setting[0].out_channels),
@@ -111,7 +116,8 @@ class ConvNeXtReverseMaskPose(nn.Module):
             input, features = x
         else:
             input = x
-        x = self.first(input)
+        x = self.stage_smooth(input)
+        x = self.first(x)
         f = self.layers(x)
         x = self.stage_pose(f)
         pose = torch.sigmoid(self.last(x))