[Feature] Support ISPRS Potsdam Dataset.

configs/_base_/datasets/potsdam.py

@@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'PotsdamDataset'
+data_root = 'data/potsdam'
+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=(512, 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=(512, 512),
+        # 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))

configs/deeplabv3plus/README.md

@@ -104,6 +104,14 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
 | 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) | [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) | [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) |
 
+### Potsdam
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| DeepLabV3+ | R-18-D8  | 512x512   |   80000 | 1.91      | 81.68             | 77.09 |         78.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601.log.json)     |
+| DeepLabV3+ | R-50-D8  | 512x512   |   80000 | 7.36      | 26.44             | 78.33 |         79.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508.log.json)     |
+| DeepLabV3+ | R-101-D8 | 512x512   |   80000 | 10.83       | 17.56          | 78.7 |         79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508.log.json) |
+
 Note:
 
 - `FP16` means Mixed Precision (FP16) is adopted in training.

configs/deeplabv3plus/deeplabv3plus.yml

@@ -8,6 +8,7 @@ Collections:
     - Pascal Context
     - Pascal Context 59
     - LoveDA
+    - Potsdam
   Paper:
     URL: https://arxiv.org/abs/1802.02611
     Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
@@ -669,3 +670,69 @@ Models:
       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
+- Name: deeplabv3plus_r18-d8_512x512_80k_potsdam
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-18-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 12.24
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 1.91
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 77.09
+      mIoU(ms+flip): 78.44
+  Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam/deeplabv3plus_r18-d8_512x512_80k_potsdam_20211219_020601-75fd5bc3.pth
+- Name: deeplabv3plus_r50-d8_512x512_80k_potsdam
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-50-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 37.82
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 7.36
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.33
+      mIoU(ms+flip): 79.27
+  Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam/deeplabv3plus_r50-d8_512x512_80k_potsdam_20211219_031508-7e7a2b24.pth
+- Name: deeplabv3plus_r101-d8_512x512_80k_potsdam
+  In Collection: deeplabv3plus
+  Metadata:
+    backbone: R-101-D8
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 56.95
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 10.83
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.7
+      mIoU(ms+flip): 79.47
+  Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam/deeplabv3plus_r101-d8_512x512_80k_potsdam_20211219_031508-8b112708.pth

configs/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_potsdam.py

@@ -0,0 +1,2 @@
+_base_ = './deeplabv3plus_r50-d8_512x512_80k_potsdam.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

configs/deeplabv3plus/deeplabv3plus_r18-d8_512x512_80k_potsdam.py

@@ -0,0 +1,11 @@
+_base_ = './deeplabv3plus_r50-d8_512x512_80k_potsdam.py'
+model = dict(
+    pretrained='open-mmlab://resnet18_v1c',
+    backbone=dict(depth=18),
+    decode_head=dict(
+        c1_in_channels=64,
+        c1_channels=12,
+        in_channels=512,
+        channels=128,
+    ),
+    auxiliary_head=dict(in_channels=256, channels=64))

configs/deeplabv3plus/deeplabv3plus_r50-d8_512x512_80k_potsdam.py

@@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/deeplabv3plus_r50-d8.py',
+    '../_base_/datasets/potsdam.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=6), auxiliary_head=dict(num_classes=6))

configs/hrnet/README.md

@@ -92,3 +92,11 @@ High-resolution representations are essential for position-sensitive vision prob
 | FCN | HRNetV2p-W18-Small  | 512x512   |   80000 | 1.59      | 24.87             | 49.28 |         49.42 | [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_20211210_203228-60a86a7a.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json)     |
 | FCN | HRNetV2p-W18  | 512x512   |   80000 | 2.76      | 12.92             | 50.81 |         50.95 | [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_20211210_203952-93d9c3b3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json)     |
 | FCN | HRNetV2p-W48 | 512x512   |   80000 | 6.20       | 9.61          | 51.42 |         51.64 | [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_20211211_044756-67072f55.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json) |
+
+### Potsdam
+
+| Method     | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                                 | download                                                                                                                                                                                                                                                                                                                                                                                   |
+| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| FCN | HRNetV2p-W18-Small  | 512x512   |   80000 | 1.58      | 36.00             | 77.64 |         78.8 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_potsdam.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json)     |
+| FCN | HRNetV2p-W18  | 512x512   |   80000 | 2.76      | 19.25             | 78.26 |         79.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_potsdam.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json)     |
+| FCN | HRNetV2p-W48 | 512x512   |   80000 | 6.20       | 16.42          | 78.39 |         79.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_potsdam.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json) |

configs/hrnet/fcn_hr18_512x512_80k_potsdam.py

@@ -0,0 +1,5 @@
+_base_ = [
+    '../_base_/models/fcn_hr18.py', '../_base_/datasets/potsdam.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(decode_head=dict(num_classes=6))

configs/hrnet/fcn_hr18s_512x512_80k_potsdam.py

@@ -0,0 +1,10 @@
+_base_ = './fcn_hr18_512x512_80k_potsdam.py'
+model = dict(
+    # pretrained='open-mmlab://msra/hrnetv2_w18_small',
+    pretrained='./pretrained/hrnetv2_w18_small-b5a04e21.pth',
+    backbone=dict(
+        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)))))

configs/hrnet/fcn_hr48_512x512_80k_potsdam.py

@@ -0,0 +1,11 @@
+_base_ = './fcn_hr18_512x512_80k_potsdam.py'
+model = dict(
+    # pretrained='open-mmlab://msra/hrnetv2_w48',
+    pretrained='./pretrained/hrnetv2_w48-d2186c55.pth',
+    backbone=dict(
+        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])))

configs/hrnet/hrnet.yml

@@ -8,6 +8,7 @@ Collections:
     - Pascal Context
     - Pascal Context 59
     - LoveDA
+    - Potsdam
   Paper:
     URL: https://arxiv.org/abs/1908.07919
     Title: Deep High-Resolution Representation Learning for Human Pose Estimation
@@ -514,3 +515,69 @@ Models:
       mIoU(ms+flip): 51.64
   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_20211211_044756-67072f55.pth
+- Name: fcn_hr18s_512x512_80k_potsdam
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W18-Small
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 27.78
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 1.58
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 77.64
+      mIoU(ms+flip): 78.8
+  Config: configs/hrnet/fcn_hr18s_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth
+- Name: fcn_hr18_512x512_80k_potsdam
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W18
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 51.95
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 2.76
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.26
+      mIoU(ms+flip): 79.24
+  Config: configs/hrnet/fcn_hr18_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth
+- Name: fcn_hr48_512x512_80k_potsdam
+  In Collection: hrnet
+  Metadata:
+    backbone: HRNetV2p-W48
+    crop size: (512,512)
+    lr schd: 80000
+    inference time (ms/im):
+    - value: 60.9
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    Training Memory (GB): 6.2
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: Potsdam
+    Metrics:
+      mIoU: 78.39
+      mIoU(ms+flip): 79.34
+  Config: configs/hrnet/fcn_hr48_512x512_80k_potsdam.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth