[Fix] Fix ResizeToMultiple transform in MMSeg 1.x (#2185)

configs/segformer/README.md

@@ -77,20 +77,13 @@ using `AlignedResize`, you can change the dataset pipeline like this:
 ```python
 test_pipeline = [
     dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(2048, 512),
-        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            # resize image to multiple of 32, improve SegFormer by 0.5-1.0 mIoU.
-            dict(type='ResizeToMultiple', size_divisor=32),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
+    dict(type='Resize', scale=(2048, 512), keep_ratio=True),
+    # resize image to multiple of 32, improve SegFormer by 0.5-1.0 mIoU.
+    dict(type='ResizeToMultiple', size_divisor=32),
+    # add loading annotation after ``Resize`` because ground truth
+    # does not need to do resize data transform
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='PackSegInputs')
 ]
 ```
 

mmseg/datasets/transforms/transforms.py

@@ -59,8 +59,8 @@ class ResizeToMultiple(BaseTransform):
             if self.interpolation else 'bilinear')
 
         results['img'] = img
-        results['img_shape'] = img.shape
-        results['pad_shape'] = img.shape
+        results['img_shape'] = img.shape[:2]
+        results['pad_shape'] = img.shape[:2]
 
         # Align segmentation map to multiple of size divisor.
         for key in results.get('seg_fields', []):

tests/test_datasets/test_transform.py

@@ -678,4 +678,4 @@ def test_resize_to_multiple():
     results = transform(results)
     assert results['img'].shape == (224, 256, 3)
     assert results['gt_semantic_seg'].shape == (224, 256)
-    assert results['img_shape'] == (224, 256, 3)
+    assert results['img_shape'] == (224, 256)