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

[Fix] Fix correct num_classes of HRNet in LoveDA dataset #1136

Browse Source
This commit is contained in:
MengzhangLI 2021-12-14 19:49:24 +08:00 committed by GitHub
parent f7ae7245d6
commit e9c41c3e60
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
configs/hrnet/README.md
View File

@ -89,6 +89,6 @@ High-resolution representations are essential for position-sensitive vision prob
| 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) | [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) | [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) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211105_131509.log.json) |
| 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) |

1
configs/hrnet/fcn_hr18_512x512_80k_loveda.py
View File

@ -2,3 +2,4 @@ _base_ = [
'../_base_/models/fcn_hr18.py', '../_base_/datasets/loveda.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
]
model = dict(decode_head=dict(num_classes=7))

30
configs/hrnet/hrnet.yml
View File

@ -455,21 +455,21 @@ Models:
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 33.26
- value: 40.21
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.72
Training Memory (GB): 1.59
Results:
- Task: Semantic Segmentation
Dataset: LoveDA
Metrics:
mIoU: 49.3
mIoU(ms+flip): 49.23
mIoU: 49.28
mIoU(ms+flip): 49.42
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
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth
- Name: fcn_hr18_512x512_80k_loveda
In Collection: hrnet
Metadata:
@ -477,21 +477,21 @@ Models:
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 59.63
- value: 77.4
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 2.9
Training Memory (GB): 2.76
Results:
- Task: Semantic Segmentation
Dataset: LoveDA
Metrics:
mIoU: 50.87
mIoU(ms+flip): 51.24
mIoU: 50.81
mIoU(ms+flip): 50.95
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
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth
- Name: fcn_hr48_512x512_80k_loveda
In Collection: hrnet
Metadata:
@ -499,18 +499,18 @@ Models:
crop size: (512,512)
lr schd: 80000
inference time (ms/im):
- value: 110.01
- value: 104.06
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 6.25
Training Memory (GB): 6.2
Results:
- Task: Semantic Segmentation
Dataset: LoveDA
Metrics:
mIoU: 51.04
mIoU(ms+flip): 51.12
mIoU: 51.42
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_20211105_131509-f07e47c6.pth
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth