[Fix] Remove the inplace operation in uper_head and fpn_neck (#1103)

* [Fix] Remove the inplace operation in  uper_head

* remove the inplace operation in fpn neck

* fix conflict

* increase the coverage

mmseg/models/backbones/mit.py

@@ -22,7 +22,6 @@ class MixFFN(BaseModule):
     The differences between MixFFN & FFN:
         1. Use 1X1 Conv to replace Linear layer.
         2. Introduce 3X3 Conv to encode positional information.
-
     Args:
         embed_dims (int): The feature dimension. Same as
             `MultiheadAttention`. Defaults: 256.
@@ -94,7 +93,6 @@ class EfficientMultiheadAttention(MultiheadAttention):
 
     This module is modified from MultiheadAttention which is a module from
     mmcv.cnn.bricks.transformer.
-
     Args:
         embed_dims (int): The embedding dimension.
         num_heads (int): Parallel attention heads.
@@ -291,7 +289,6 @@ class MixVisionTransformer(BaseModule):
     This backbone is the implementation of `SegFormer: Simple and
     Efficient Design for Semantic Segmentation with
     Transformers <https://arxiv.org/abs/2105.15203>`_.
-
     Args:
         in_channels (int): Number of input channels. Default: 3.
         embed_dims (int): Embedding dimension. Default: 768.

mmseg/models/decode_heads/uper_head.py

@@ -101,7 +101,7 @@ class UPerHead(BaseDecodeHead):
         used_backbone_levels = len(laterals)
         for i in range(used_backbone_levels - 1, 0, -1):
             prev_shape = laterals[i - 1].shape[2:]
-            laterals[i - 1] += resize(
+            laterals[i - 1] = laterals[i - 1] + resize(
                 laterals[i],
                 size=prev_shape,
                 mode='bilinear',

mmseg/models/necks/fpn.py

@@ -175,10 +175,11 @@ class FPN(BaseModule):
             # In some cases, fixing `scale factor` (e.g. 2) is preferred, but
             #  it cannot co-exist with `size` in `F.interpolate`.
             if 'scale_factor' in self.upsample_cfg:
-                laterals[i - 1] += resize(laterals[i], **self.upsample_cfg)
+                laterals[i - 1] = laterals[i - 1] + resize(
+                    laterals[i], **self.upsample_cfg)
             else:
                 prev_shape = laterals[i - 1].shape[2:]
-                laterals[i - 1] += resize(
+                laterals[i - 1] = laterals[i - 1] + resize(
                     laterals[i], size=prev_shape, **self.upsample_cfg)
 
         # build outputs

tests/test_models/test_necks/test_fpn.py

@@ -17,3 +17,14 @@ def test_fpn():
     assert outputs[1].shape == torch.Size([1, 64, 28, 28])
     assert outputs[2].shape == torch.Size([1, 64, 14, 14])
     assert outputs[3].shape == torch.Size([1, 64, 7, 7])
+
+    fpn = FPN(
+        in_channels,
+        64,
+        len(in_channels),
+        upsample_cfg=dict(mode='nearest', scale_factor=2.0))
+    outputs = fpn(inputs)
+    assert outputs[0].shape == torch.Size([1, 64, 56, 56])
+    assert outputs[1].shape == torch.Size([1, 64, 28, 28])
+    assert outputs[2].shape == torch.Size([1, 64, 14, 14])
+    assert outputs[3].shape == torch.Size([1, 64, 7, 7])