[Fix] Fix Segmenter-l readme (open-mmlab#1695)

* [Fix] Fix Segmenter-l readme

* fix

Author: linfangjian01

configs/segmenter/README.md

@@ -71,7 +71,7 @@ In our default setting, pretrained models and their corresponding [ViT-AugReg](h
 | Segmenter Linear | ViT-S_16 | 512x512   | 160000  | 1.78     | 28.07          | 45.75 | 46.82         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713.log.json) |
 | Segmenter Mask   | ViT-S_16 | 512x512   | 160000  | 2.03     | 24.80          | 46.19 | 47.85         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
 | Segmenter Mask   | ViT-B_16 | 512x512   | 160000  | 4.20     | 13.20          | 49.60 | 51.07         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706.log.json)         |
-| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.56    | 2.62           | 52.16 | 53.65         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750.log.json)         |
+| Segmenter Mask   | ViT-L_16 | 640x640   | 160000  | 16.99    | 3.03           | 51.65 | 53.58         | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513-4783a347.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513.log.json)         |
 
 Note:
 

configs/segmenter/segmenter.yml

@@ -101,25 +101,25 @@ Models:
       mIoU(ms+flip): 51.07
   Config: configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth
-- Name: segmenter_vit-l_mask_8x1_512x512_160k_ade20k
+- Name: segmenter_vit-l_mask_8x1_640x640_160k_ade20k
   In Collection: Segmenter
   Metadata:
     backbone: ViT-L_16
     crop size: (640,640)
     lr schd: 160000
     inference time (ms/im):
-    - value: 381.68
+    - value: 330.03
       hardware: V100
       backend: PyTorch
       batch size: 1
       mode: FP32
       resolution: (640,640)
-    Training Memory (GB): 16.56
+    Training Memory (GB): 16.99
   Results:
   - Task: Semantic Segmentation
     Dataset: ADE20K
     Metrics:
-      mIoU: 52.16
-      mIoU(ms+flip): 53.65
-  Config: configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py
-  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth
+      mIoU: 51.65
+      mIoU(ms+flip): 53.58
+  Config: configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513-4783a347.pth

configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py renamed to configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py

@@ -1,6 +1,6 @@
 _base_ = [
     '../_base_/models/segmenter_vit-b16_mask.py',
-    '../_base_/datasets/ade20k.py', '../_base_/default_runtime.py',
+    '../_base_/datasets/ade20k_640x640.py', '../_base_/default_runtime.py',
     '../_base_/schedules/schedule_160k.py'
 ]
 checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segmenter/vit_large_p16_384_20220308-d4efb41d.pth'  # noqa
@@ -29,7 +29,7 @@
 train_pipeline = [
     dict(type='LoadImageFromFile'),
     dict(type='LoadAnnotations', reduce_zero_label=True),
-    dict(type='Resize', img_scale=(2048, 640), ratio_range=(0.5, 2.0)),
+    dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)),
     dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
     dict(type='RandomFlip', prob=0.5),
     dict(type='PhotoMetricDistortion'),
@@ -42,7 +42,7 @@
     dict(type='LoadImageFromFile'),
     dict(
         type='MultiScaleFlipAug',
-        img_scale=(2048, 640),
+        img_scale=(2560, 640),
         # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
         flip=False,
         transforms=[