mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

[Feature] Support ISPRS Vaihingen Dataset. (#1171)

Browse Source 
* Add Vaihingen

* upload models&logs of vaihingen

* fix unit test

* fix dataset pipeline

* fix unit test coverage

* fix vaihingen docstring
This commit is contained in:
MengzhangLI 2022-01-22 20:27:51 +08:00 committed by GitHub
parent 6a22c428c2
commit 4b905cbe2f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
25 changed files with 609 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
configs/_base_/datasets/vaihingen.py Normal file
View File

@ -0,0 +1,54 @@
# dataset settings
dataset_type = 'ISPRSDataset'
data_root = 'data/vaihingen'
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))

8
configs/deeplabv3plus/README.md
View File

@ -112,6 +112,14 @@ Spatial pyramid pooling module or encode-decoder structure are used in deep neur
| 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) |
### Vaihingen
| 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 | 72.79 | 72.50 | 74.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805.log.json) |
| DeepLabV3+ | R-50-D8 | 512x512 | 80000 | 7.36 | 26.91 | 73.97 | 75.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
| DeepLabV3+ | R-101-D8 | 512x512 | 80000 | 10.83 | 18.59 | 73.06 | 74.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816.log.json) |
Note:
- `FP16` means Mixed Precision (FP16) is adopted in training.

67
configs/deeplabv3plus/deeplabv3plus.yml
View File

@ -9,6 +9,7 @@ Collections:
- Pascal Context 59
- LoveDA
- Potsdam
- Vaihingen
Paper:
URL: https://arxiv.org/abs/1802.02611
Title: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
@ -736,3 +737,69 @@ Models:
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
- Name: deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen
In Collection: deeplabv3plus
Metadata:
backbone: R-18-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 13.74
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.91
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 72.5
mIoU(ms+flip): 74.13
Config: configs/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen_20211231_230805-7626a263.pth
- Name: deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen
In Collection: deeplabv3plus
Metadata:
backbone: R-50-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 37.16
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 7.36
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 73.97
mIoU(ms+flip): 75.05
Config: configs/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen_20211231_230816-5040938d.pth
- Name: deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen
In Collection: deeplabv3plus
Metadata:
backbone: R-101-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 53.79
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 10.83
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 73.06
mIoU(ms+flip): 74.14
Config: configs/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen_20211231_230816-8a095afa.pth

2
configs/deeplabv3plus/deeplabv3plus_r101-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,2 @@
_base_ = './deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

11
configs/deeplabv3plus/deeplabv3plus_r18-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,11 @@
_base_ = './deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen.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))

7
configs/deeplabv3plus/deeplabv3plus_r50-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

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

8
configs/hrnet/README.md
View File

@ -100,3 +100,11 @@ High-resolution representations are essential for position-sensitive vision prob
| 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) |
### Vaihingen
| 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 | 38.11 | 71.81 | 73.1 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909.log.json) |
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 2.76 | 19.55 | 72.57 | 74.09 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216.log.json) |
| FCN | HRNetV2p-W48 | 512x512 | 80000 | 6.20 | 17.25 | 72.50 | 73.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244.log.json) |

5
configs/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen.py Normal file
View File

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

9
configs/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,9 @@
_base_ = './fcn_hr18_4x4_512x512_80k_vaihingen.py'
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w18_small',
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)))))

10
configs/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,10 @@
_base_ = './fcn_hr18_4x4_512x512_80k_vaihingen.py'
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w48',
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])))

67
configs/hrnet/hrnet.yml
View File

@ -9,6 +9,7 @@ Collections:
- Pascal Context 59
- LoveDA
- Potsdam
- Vaihingen
Paper:
URL: https://arxiv.org/abs/1908.07919
Title: Deep High-Resolution Representation Learning for Human Pose Estimation
@ -581,3 +582,69 @@ Models:
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
- Name: fcn_hr18s_4x4_512x512_80k_vaihingen
In Collection: hrnet
Metadata:
backbone: HRNetV2p-W18-Small
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 26.24
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.58
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 71.81
mIoU(ms+flip): 73.1
Config: configs/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_4x4_512x512_80k_vaihingen/fcn_hr18s_4x4_512x512_80k_vaihingen_20211231_230909-b23aae02.pth
- Name: fcn_hr18_4x4_512x512_80k_vaihingen
In Collection: hrnet
Metadata:
backbone: HRNetV2p-W18
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 51.15
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 2.76
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 72.57
mIoU(ms+flip): 74.09
Config: configs/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_4x4_512x512_80k_vaihingen/fcn_hr18_4x4_512x512_80k_vaihingen_20211231_231216-2ec3ae8a.pth
- Name: fcn_hr48_4x4_512x512_80k_vaihingen
In Collection: hrnet
Metadata:
backbone: HRNetV2p-W48
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 57.97
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 6.2
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 72.5
mIoU(ms+flip): 73.52
Config: configs/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_4x4_512x512_80k_vaihingen/fcn_hr48_4x4_512x512_80k_vaihingen_20211231_231244-7133cb22.pth

8
configs/pspnet/README.md
View File

@ -141,6 +141,14 @@ We support evaluation results on these two datasets using models above trained o
| PSPNet | R-50-D8 | 512x512 | 80000 | 6.14 | 30.21 | 78.12 | 78.98 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541-2dd5fe67.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_potsdam/pspnet_r50-d8_4x4_512x512_80k_potsdam_20211219_043541.log.json) |
| PSPNet | R-101-D8 | 512x512 | 80000 | 9.61 | 19.40 | 78.62 | 79.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612.log.json) |
### Vaihingen
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| PSPNet | R-18-D8 | 512x512 | 80000 | 1.45 | 85.06 | 71.46 | 73.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json) |
| PSPNet | R-50-D8 | 512x512 | 80000 | 6.14 | 30.29 | 72.36 | 73.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355.log.json) |
| PSPNet | R-101-D8 | 512x512 | 80000 | 9.61 | 19.97 | 72.61 | 74.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806.log.json) |
Note:
- `FP16` means Mixed Precision (FP16) is adopted in training.

67
configs/pspnet/pspnet.yml
View File

@ -12,6 +12,7 @@ Collections:
- COCO-Stuff 164k
- LoveDA
- Potsdam
- Vaihingen
Paper:
URL: https://arxiv.org/abs/1612.01105
Title: Pyramid Scene Parsing Network
@ -875,3 +876,69 @@ Models:
mIoU(ms+flip): 79.47
Config: configs/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_potsdam/pspnet_r101-d8_4x4_512x512_80k_potsdam_20211220_125612-aed036c4.pth
- Name: pspnet_r18-d8_4x4_512x512_80k_vaihingen
In Collection: pspnet
Metadata:
backbone: R-18-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 11.76
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.45
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 71.46
mIoU(ms+flip): 73.36
Config: configs/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen/pspnet_r18-d8_4x4_512x512_80k_vaihingen_20211228_160355-52a8a6f6.pth
- Name: pspnet_r50-d8_4x4_512x512_80k_vaihingen
In Collection: pspnet
Metadata:
backbone: R-50-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 33.01
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 6.14
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 72.36
mIoU(ms+flip): 73.75
Config: configs/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen/pspnet_r50-d8_4x4_512x512_80k_vaihingen_20211228_160355-382f8f5b.pth
- Name: pspnet_r101-d8_4x4_512x512_80k_vaihingen
In Collection: pspnet
Metadata:
backbone: R-101-D8
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 50.08
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 9.61
Results:
- Task: Semantic Segmentation
Dataset: Vaihingen
Metrics:
mIoU: 72.61
mIoU(ms+flip): 74.18
Config: configs/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen/pspnet_r101-d8_4x4_512x512_80k_vaihingen_20211231_230806-8eba0a09.pth

2
configs/pspnet/pspnet_r101-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,2 @@
_base_ = './pspnet_r50-d8_4x4_512x512_80k_vaihingen.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

9
configs/pspnet/pspnet_r18-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,9 @@
_base_ = './pspnet_r50-d8_4x4_512x512_80k_vaihingen.py'
model = dict(
pretrained='open-mmlab://resnet18_v1c',
backbone=dict(depth=18),
decode_head=dict(
in_channels=512,
channels=128,
),
auxiliary_head=dict(in_channels=256, channels=64))

6
configs/pspnet/pspnet_r50-d8_4x4_512x512_80k_vaihingen.py Normal file
View File

@ -0,0 +1,6 @@
_base_ = [
'../_base_/models/pspnet_r50-d8.py', '../_base_/datasets/vaihingen.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
model = dict(
decode_head=dict(num_classes=6), auxiliary_head=dict(num_classes=6))

16
docs/en/dataset_prepare.md
View File

@ -309,3 +309,19 @@ python tools/convert_datasets/potsdam.py /path/to/potsdam
```
In our default setting, it will generate 3456 images for training and 2016 images for validation.
### ISPRS Vaihingen
The [Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/)
dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Vaihingen.
The dataset can be requested at the challenge [homepage](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/).
The 'ISPRS_semantic_labeling_Vaihingen.zip' and 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip' are required.
For Vaihingen dataset, please run the following command to download and re-organize the dataset.
```shell
python tools/convert_datasets/vaihingen.py /path/to/vaihingen
```
In our default setting (`clip_size` =512, `stride_size`=256), it will generate 344 images for training and 398 images for validation.

16
docs/zh_cn/dataset_prepare.md
View File

@ -250,3 +250,19 @@ python tools/convert_datasets/potsdam.py /path/to/potsdam
```
使用我们默认的配置， 将生成 3456 张图片的训练集和 2016 张图片的验证集。
### ISPRS Vaihingen
[Vaihingen](https://www2.isprs.org/commissions/comm2/wg4/benchmark/2d-sem-label-vaihingen/)
数据集是一个有着2D 语义分割内容标注的城市遥感数据集。
数据集可以从挑战 [主页](https://www2.isprs.org/commissions/comm2/wg4/benchmark/data-request-form/).
需要其中的 'ISPRS_semantic_labeling_Vaihingen.zip' 和 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip'。
对于 Vaihingen 数据集，请运行以下命令下载并重新组织数据集
```shell
python tools/convert_datasets/vaihingen.py /path/to/vaihingen
```
使用我们默认的配置 (`clip_size` =512, `stride_size`=256)， 将生成 344 张图片的训练集和 398 张图片的验证集。

71
mmseg/core/evaluation/class_names.py
View File

@ -52,22 +52,6 @@ def voc_classes():
]
def loveda_classes():
"""LoveDA class names for external use."""
return [
'background', 'building', 'road', 'water', 'barren', 'forest',
'agricultural'
]
def potsdam_classes():
"""Potsdam class names for external use."""
return [
'impervious_surface', 'building', 'low_vegetation', 'tree', 'car',
'clutter'
]
def cocostuff_classes():
"""CocoStuff class names for external use."""
return [
@ -103,6 +87,30 @@ def cocostuff_classes():
]
def loveda_classes():
"""LoveDA class names for external use."""
return [
'background', 'building', 'road', 'water', 'barren', 'forest',
'agricultural'
]
def potsdam_classes():
"""Potsdam class names for external use."""
return [
'impervious_surface', 'building', 'low_vegetation', 'tree', 'car',
'clutter'
]
def vaihingen_classes():
"""Vaihingen class names for external use."""
return [
'impervious_surface', 'building', 'low_vegetation', 'tree', 'car',
'clutter'
]
def cityscapes_palette():
"""Cityscapes palette for external use."""
return [[128, 64, 128], [244, 35, 232], [70, 70, 70], [102, 102, 156],
@ -163,18 +171,6 @@ def voc_palette():
[128, 64, 0], [0, 192, 0], [128, 192, 0], [0, 64, 128]]
def loveda_palette():
"""LoveDA palette for external use."""
return [[255, 255, 255], [255, 0, 0], [255, 255, 0], [0, 0, 255],
[159, 129, 183], [0, 255, 0], [255, 195, 128]]
def potsdam_palette():
"""Potsdam palette for external use."""
return [[255, 255, 255], [0, 0, 255], [0, 255, 255], [0, 255, 0],
[255, 255, 0], [255, 0, 0]]
def cocostuff_palette():
"""CocoStuff palette for external use."""
return [[0, 192, 64], [0, 192, 64], [0, 64, 96], [128, 192, 192],
@ -222,12 +218,31 @@ def cocostuff_palette():
[64, 160, 64], [64, 64, 0]]
def loveda_palette():
"""LoveDA palette for external use."""
return [[255, 255, 255], [255, 0, 0], [255, 255, 0], [0, 0, 255],
[159, 129, 183], [0, 255, 0], [255, 195, 128]]
def potsdam_palette():
"""Potsdam palette for external use."""
return [[255, 255, 255], [0, 0, 255], [0, 255, 255], [0, 255, 0],
[255, 255, 0], [255, 0, 0]]
def vaihingen_palette():
"""Vaihingen palette for external use."""
return [[255, 255, 255], [0, 0, 255], [0, 0, 255], [0, 255, 0],
[255, 255, 0], [255, 0, 0]]
dataset_aliases = {
'cityscapes': ['cityscapes'],
'ade': ['ade', 'ade20k'],
'voc': ['voc', 'pascal_voc', 'voc12', 'voc12aug'],
'loveda': ['loveda'],
'potsdam': ['potsdam'],
'vaihingen': ['vaihingen'],
'cocostuff': [
'cocostuff', 'cocostuff10k', 'cocostuff164k', 'coco-stuff',
'coco-stuff10k', 'coco-stuff164k', 'coco_stuff', 'coco_stuff10k',

3
mmseg/datasets/__init__.py
View File

@ -10,6 +10,7 @@ from .dataset_wrappers import (ConcatDataset, MultiImageMixDataset,
RepeatDataset)
from .drive import DRIVEDataset
from .hrf import HRFDataset
from .isprs import ISPRSDataset
from .loveda import LoveDADataset
from .night_driving import NightDrivingDataset
from .pascal_context import PascalContextDataset, PascalContextDataset59
@ -24,5 +25,5 @@ __all__ = [
'PascalContextDataset59', 'ChaseDB1Dataset', 'DRIVEDataset', 'HRFDataset',
'STAREDataset', 'DarkZurichDataset', 'NightDrivingDataset',
'COCOStuffDataset', 'LoveDADataset', 'MultiImageMixDataset',
'PotsdamDataset'
'ISPRSDataset', 'PotsdamDataset'
]

25
mmseg/datasets/isprs.py Normal file
View File

@ -0,0 +1,25 @@
# Copyright (c) OpenMMLab. All rights reserved.
from .builder import DATASETS
from .custom import CustomDataset
@DATASETS.register_module()
class ISPRSDataset(CustomDataset):
"""ISPRS dataset.
In segmentation map annotation for LoveDA, 0 is the ignore index.
``reduce_zero_label`` should be set to True. The ``img_suffix`` and
``seg_map_suffix`` are both fixed to '.png'.
"""
CLASSES = ('impervious_surface', 'building', 'low_vegetation', 'tree',
'car', 'clutter')
PALETTE = [[255, 255, 255], [0, 0, 255], [0, 0, 255], [0, 255, 0],
[255, 255, 0], [255, 0, 0]]
def __init__(self, **kwargs):
super(ISPRSDataset, self).__init__(
img_suffix='.png',
seg_map_suffix='.png',
reduce_zero_label=True,
**kwargs)

BIN
tests/data/pseudo_vaihingen_dataset/ann_dir/area1_0_0_512_512.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 12 KiB

BIN
tests/data/pseudo_vaihingen_dataset/img_dir/area1_0_0_512_512.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 393 KiB

13
tests/test_data/test_dataset.py
View File

@ -14,7 +14,7 @@ from PIL import Image
from mmseg.core.evaluation import get_classes, get_palette
from mmseg.datasets import (DATASETS, ADE20KDataset, CityscapesDataset,
COCOStuffDataset, ConcatDataset, CustomDataset,
LoveDADataset, MultiImageMixDataset,
ISPRSDataset, LoveDADataset, MultiImageMixDataset,
PascalVOCDataset, PotsdamDataset, RepeatDataset,
build_dataset)
@ -27,6 +27,7 @@ def test_classes():
ADE20KDataset.CLASSES) == get_classes('ade') == get_classes('ade20k')
assert list(LoveDADataset.CLASSES) == get_classes('loveda')
assert list(PotsdamDataset.CLASSES) == get_classes('potsdam')
assert list(ISPRSDataset.CLASSES) == get_classes('vaihingen')
assert list(COCOStuffDataset.CLASSES) == get_classes('cocostuff')
with pytest.raises(ValueError):
@ -719,6 +720,16 @@ def test_potsdam():
assert len(test_dataset) == 1
def test_vaihingen():
test_dataset = ISPRSDataset(
pipeline=[],
img_dir=osp.join(
osp.dirname(__file__), '../data/pseudo_vaihingen_dataset/img_dir'),
ann_dir=osp.join(
osp.dirname(__file__), '../data/pseudo_vaihingen_dataset/ann_dir'))
assert len(test_dataset) == 1
@patch('mmseg.datasets.CustomDataset.load_annotations', MagicMock)
@patch('mmseg.datasets.CustomDataset.__getitem__',
MagicMock(side_effect=lambda idx: idx))

155
tools/convert_datasets/vaihingen.py Normal file
View File

@ -0,0 +1,155 @@
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import glob
import math
import os
import os.path as osp
import tempfile
import zipfile
import mmcv
import numpy as np
def parse_args():
parser = argparse.ArgumentParser(
description='Convert vaihingen dataset to mmsegmentation format')
parser.add_argument('dataset_path', help='vaihingen folder path')
parser.add_argument('--tmp_dir', help='path of the temporary directory')
parser.add_argument('-o', '--out_dir', help='output path')
parser.add_argument(
'--clip_size',
type=int,
help='clipped size of image after preparation',
default=512)
parser.add_argument(
'--stride_size',
type=int,
help='stride of clipping original images',
default=256)
args = parser.parse_args()
return args
def clip_big_image(image_path, clip_save_dir, to_label=False):
# Original image of Vaihingen dataset is very large, thus pre-processing
# of them is adopted. Given fixed clip size and stride size to generate
# clipped image, the intersection　of width and height is determined.
# For example, given one 5120 x 5120 original image, the clip size is
# 512 and stride size is 256, thus it would generate 20x20 = 400 images
# whose size are all 512x512.
image = mmcv.imread(image_path)
h, w, c = image.shape
cs = args.clip_size
ss = args.stride_size
num_rows = math.ceil((h - cs) / ss) if math.ceil(
(h - cs) / ss) * ss + cs >= h else math.ceil((h - cs) / ss) + 1
num_cols = math.ceil((w - cs) / ss) if math.ceil(
(w - cs) / ss) * ss + cs >= w else math.ceil((w - cs) / ss) + 1
x, y = np.meshgrid(np.arange(num_cols + 1), np.arange(num_rows + 1))
xmin = x * cs
ymin = y * cs
xmin = xmin.ravel()
ymin = ymin.ravel()
xmin_offset = np.where(xmin + cs > w, w - xmin - cs, np.zeros_like(xmin))
ymin_offset = np.where(ymin + cs > h, h - ymin - cs, np.zeros_like(ymin))
boxes = np.stack([
xmin + xmin_offset, ymin + ymin_offset,
np.minimum(xmin + cs, w),
np.minimum(ymin + cs, h)
],
axis=1)
if to_label:
color_map = np.array([[0, 0, 0], [255, 255, 255], [255, 0, 0],
[255, 255, 0], [0, 255, 0], [0, 255, 255],
[0, 0, 255]])
flatten_v = np.matmul(
image.reshape(-1, c),
np.array([2, 3, 4]).reshape(3, 1))
out = np.zeros_like(flatten_v)
for idx, class_color in enumerate(color_map):
value_idx = np.matmul(class_color,
np.array([2, 3, 4]).reshape(3, 1))
out[flatten_v == value_idx] = idx
image = out.reshape(h, w)
for box in boxes:
start_x, start_y, end_x, end_y = box
clipped_image = image[start_y:end_y,
start_x:end_x] if to_label else image[
start_y:end_y, start_x:end_x, :]
area_idx = osp.basename(image_path).split('_')[3].strip('.tif')
mmcv.imwrite(
clipped_image.astype(np.uint8),
osp.join(clip_save_dir,
f'{area_idx}_{start_x}_{start_y}_{end_x}_{end_y}.png'))
def main():
splits = {
'train': [
'area1', 'area11', 'area13', 'area15', 'area17', 'area21',
'area23', 'area26', 'area28', 'area3', 'area30', 'area32',
'area34', 'area37', 'area5', 'area7'
],
'val': [
'area6', 'area24', 'area35', 'area16', 'area14', 'area22',
'area10', 'area4', 'area2', 'area20', 'area8', 'area31', 'area33',
'area27', 'area38', 'area12', 'area29'
],
}
dataset_path = args.dataset_path
if args.out_dir is None:
out_dir = osp.join('data', 'vaihingen')
else:
out_dir = args.out_dir
print('Making directories...')
mmcv.mkdir_or_exist(osp.join(out_dir, 'img_dir', 'train'))
mmcv.mkdir_or_exist(osp.join(out_dir, 'img_dir', 'val'))
mmcv.mkdir_or_exist(osp.join(out_dir, 'ann_dir', 'train'))
mmcv.mkdir_or_exist(osp.join(out_dir, 'ann_dir', 'val'))
zipp_list = glob.glob(os.path.join(dataset_path, '*.zip'))
print('Find the data', zipp_list)
with tempfile.TemporaryDirectory(dir=args.tmp_dir) as tmp_dir:
for zipp in zipp_list:
zip_file = zipfile.ZipFile(zipp)
zip_file.extractall(tmp_dir)
src_path_list = glob.glob(os.path.join(tmp_dir, '*.tif'))
if 'ISPRS_semantic_labeling_Vaihingen' in zipp:
src_path_list = glob.glob(
os.path.join(os.path.join(tmp_dir, 'top'), '*.tif'))
if 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE' in zipp: # noqa
src_path_list = glob.glob(os.path.join(tmp_dir, '*.tif'))
# delete unused area9 ground truth
for area_ann in src_path_list:
if 'area9' in area_ann:
src_path_list.remove(area_ann)
prog_bar = mmcv.ProgressBar(len(src_path_list))
for i, src_path in enumerate(src_path_list):
area_idx = osp.basename(src_path).split('_')[3].strip('.tif')
data_type = 'train' if area_idx in splits['train'] else 'val'
if 'noBoundary' in src_path:
dst_dir = osp.join(out_dir, 'ann_dir', data_type)
clip_big_image(src_path, dst_dir, to_label=True)
else:
dst_dir = osp.join(out_dir, 'img_dir', data_type)
clip_big_image(src_path, dst_dir, to_label=False)
prog_bar.update()
print('Removing the temporary files...')
print('Done!')
if __name__ == '__main__':
args = parse_args()
main()