open-mmlab · Junjun2016 · Nov 24, 2021 · Oct 31, 2021 · Oct 31, 2021 · Oct 31, 2021
diff --git a/configs/_base_/datasets/loveda.py b/configs/_base_/datasets/loveda.py
@@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'LoveDADataset'
+data_root = 'data/loveDA'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2048, 512), 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'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='img_dir/train',
+        ann_dir='ann_dir/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='img_dir/val',
+        ann_dir='ann_dir/val',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='img_dir/val',
+        ann_dir='ann_dir/val',
+        pipeline=test_pipeline))
diff --git a/configs/deeplabv3plus/README.md b/configs/deeplabv3plus/README.md
@@ -85,6 +85,14 @@
 | DeepLabV3+ | R-101-D8 | 480x480   |   40000 | -        | -           | 52.86 |         54.54 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59_20210416_111233-ed937f15.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59/deeplabv3plus_r101-d8_480x480_40k_pascal_context_59-20210416_111233.log.json) |
 | DeepLabV3+ | R-101-D8 | 480x480   |   80000 | -        | -              | 53.2 |         54.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59-20210416_111127.log.json) |
 
+#### LoveDA
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.93      | 25.57             | 50.28 |         50.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.37      | 6.00             | 50.99 |         50.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.84       | 4.33          | 51.47 |         51.32 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759.log.json) |
+
 Note:
 
 - `FP16` means Mixed Precision (FP16) is adopted in training.
diff --git a/configs/deeplabv3plus/deeplabv3plus.yml b/configs/deeplabv3plus/deeplabv3plus.yml
@@ -599,3 +599,69 @@ Models:
       mIoU(ms+flip): 54.67
   Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59/deeplabv3plus_r101-d8_480x480_80k_pascal_context_59_20210416_111127-7ca0331d.pth
+- Name: deeplabv3plus_r18-d8_512x512_80k_loveda
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-18-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 39.11
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 1.93
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.28
+      mIoU(ms+flip): 50.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda/deeplabv3plus_r18-d8_512x512_80k_loveda_20211104_132800-ce0fa0ca.pth
+- Name: deeplabv3plus_r50-d8_512x512_80k_loveda
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-50-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 166.67
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 7.37
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 50.99
+      mIoU(ms+flip): 50.65
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda/deeplabv3plus_r50-d8_512x512_80k_loveda_20211105_080442-f0720392.pth
+- Name: deeplabv3plus_r101-d8_512x512_80k_loveda
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-101-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 230.95
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 10.84
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: ADE20K
+    Metrics:
+      mIoU: 51.47
+      mIoU(ms+flip): 51.32
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda/deeplabv3plus_r101-d8_512x512_80k_loveda_20211105_110759-4c1f297e.pth
diff --git a/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda.py b/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_loveda.py
@@ -0,0 +1,6 @@
+_base_ = './deeplabv3plus_r50-d8_512x512_80k_loveda.py'
+model = dict(
+    backbone=dict(
+        depth=101,
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://resnet101_v1c')))
diff --git a/configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda.py b/configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_loveda.py
@@ -0,0 +1,13 @@
+_base_ = './deeplabv3plus_r50-d8_512x512_80k_loveda.py'
+model = dict(
+    backbone=dict(
+        depth=18,
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://resnet18_v1c')),
+    decode_head=dict(
+        c1_in_channels=64,
+        c1_channels=12,
+        in_channels=512,
+        channels=128,
+    ),
+    auxiliary_head=dict(in_channels=256, channels=64))
diff --git a/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda.py b/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_loveda.py
@@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/deeplabv3plus_r50-d8.py', '../_base_/datasets/loveda.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=7), auxiliary_head=dict(num_classes=7))
diff --git a/configs/hrnet/README.md b/configs/hrnet/README.md
@@ -73,3 +73,11 @@
 | ------ | ------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | FCN    | HRNetV2p-W48 | 480x480   |   40000 | -     | -           | 50.33 |         52.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_40k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json) |
 | FCN    | HRNetV2p-W48 | 480x480   |   80000 | -        | -              | 51.12 |         53.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json) |
+
+#### LoveDA
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN | HRNetV2p-W18-Small  | 512x512   |   80000 | 1.72      | 30.07             | 49.3 |         49.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_loveda.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211105_180825-41dcc5dc.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211105_180825.log.json)     |
+| FCN | HRNetV2p-W18  | 512x512   |   80000 | 2.90      | 16.77             | 50.87 |         51.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_loveda.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211105_165542-95be4d2b.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211105_165542.log.json)     |
+| FCN | HRNetV2p-W48 | 512x512   |   80000 | 6.25       | 9.09          | 51.04 |         51.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_loveda.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211105_131509-f07e47c6.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211105_131509.log.json) |
diff --git a/configs/hrnet/fcn_hr18_512x512_80k_loveda.py b/configs/hrnet/fcn_hr18_512x512_80k_loveda.py
@@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/fcn_hr18.py', '../_base_/datasets/loveda.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
diff --git a/configs/hrnet/fcn_hr18s_512x512_80k_loveda.py b/configs/hrnet/fcn_hr18s_512x512_80k_loveda.py
@@ -0,0 +1,11 @@
+_base_ = './fcn_hr18_512x512_80k_loveda.py'
+model = dict(
+    backbone=dict(
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://msra/hrnetv2_w18_small'),
+        extra=dict(
+            stage1=dict(num_blocks=(2, )),
+            stage2=dict(num_blocks=(2, 2)),
+            stage3=dict(num_modules=3, num_blocks=(2, 2, 2)),
+            stage4=dict(num_modules=2, num_blocks=(2, 2, 2, 2)))))
diff --git a/configs/hrnet/fcn_hr48_512x512_80k_loveda.py b/configs/hrnet/fcn_hr48_512x512_80k_loveda.py
@@ -0,0 +1,11 @@
+_base_ = './fcn_hr18_512x512_80k_loveda.py'
+model = dict(
+    backbone=dict(
+        init_cfg=dict(
+            type='Pretrained', checkpoint='open-mmlab://msra/hrnetv2_w48'),
+        extra=dict(
+            stage2=dict(num_channels=(48, 96)),
+            stage3=dict(num_channels=(48, 96, 192)),
+            stage4=dict(num_channels=(48, 96, 192, 384)))),
+    decode_head=dict(
+        in_channels=[48, 96, 192, 384], channels=sum([48, 96, 192, 384])))
diff --git a/configs/hrnet/hrnet.yml b/configs/hrnet/hrnet.yml
@@ -447,3 +447,69 @@ Models:
       mIoU(ms+flip): 53.56
   Config: configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth
+- Name: fcn_hr18s_512x512_80k_loveda
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W18-Small
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 33.26
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 1.72
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 49.3
+      mIoU(ms+flip): 49.23
+  Config: configs/hrnet/fcn_hr18s_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211105_180825-41dcc5dc.pth
+- Name: fcn_hr18_512x512_80k_loveda
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W18
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 59.63
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 2.9
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 50.87
+      mIoU(ms+flip): 51.24
+  Config: configs/hrnet/fcn_hr18_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211105_165542-95be4d2b.pth
+- Name: fcn_hr48_512x512_80k_loveda
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W48
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 110.01
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 6.25
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Pascal Context 59
+    Metrics:
+      mIoU: 51.04
+      mIoU(ms+flip): 51.12
+  Config: configs/hrnet/fcn_hr48_512x512_80k_loveda.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211105_131509-f07e47c6.pth