mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 05:46:00 +08:00
c448646a92
## Motivation - Create the `main` branch ## Modification Modify links from `dev-1.x` to `main`
110 lines
4.6 KiB
YAML
110 lines
4.6 KiB
YAML
Collections:
|
|
- Name: SegNeXt
|
|
License: Apache License 2.0
|
|
Metadata:
|
|
Training Data:
|
|
- ADE20K
|
|
Paper:
|
|
Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
|
|
URL: https://arxiv.org/abs/2209.08575
|
|
README: configs/segnext/README.md
|
|
Frameworks:
|
|
- PyTorch
|
|
Models:
|
|
- Name: segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512
|
|
In Collection: SegNeXt
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 41.5
|
|
mIoU(ms+flip): 42.59
|
|
Config: configs/segnext/segnext_mscan-t_1xb16-adamw-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- MSCAN-T
|
|
- SegNeXt
|
|
Training Resources: 1x A100 GPUS
|
|
Memory (GB): 17.88
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244-05bd8466.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k/segnext_mscan-t_1x16_512x512_adamw_160k_ade20k_20230210_140244.log.json
|
|
Paper:
|
|
Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
|
|
URL: https://arxiv.org/abs/2209.08575
|
|
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
|
|
Framework: PyTorch
|
|
- Name: segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512
|
|
In Collection: SegNeXt
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 44.16
|
|
mIoU(ms+flip): 45.81
|
|
Config: configs/segnext/segnext_mscan-s_1xb16-adamw-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- MSCAN-S
|
|
- SegNeXt
|
|
Training Resources: 1x A100 GPUS
|
|
Memory (GB): 21.47
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014-43013668.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k/segnext_mscan-s_1x16_512x512_adamw_160k_ade20k_20230214_113014.log.json
|
|
Paper:
|
|
Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
|
|
URL: https://arxiv.org/abs/2209.08575
|
|
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
|
|
Framework: PyTorch
|
|
- Name: segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512
|
|
In Collection: SegNeXt
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 48.03
|
|
mIoU(ms+flip): 49.68
|
|
Config: configs/segnext/segnext_mscan-b_1xb16-adamw-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- MSCAN-B
|
|
- SegNeXt
|
|
Training Resources: 1x A100 GPUS
|
|
Memory (GB): 31.03
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053-b6f6c70c.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k/segnext_mscan-b_1x16_512x512_adamw_160k_ade20k_20230209_172053.log.json
|
|
Paper:
|
|
Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
|
|
URL: https://arxiv.org/abs/2209.08575
|
|
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
|
|
Framework: PyTorch
|
|
- Name: segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512
|
|
In Collection: SegNeXt
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 50.99
|
|
mIoU(ms+flip): 52.1
|
|
Config: configs/segnext/segnext_mscan-l_1xb16-adamw-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- MSCAN-L
|
|
- SegNeXt
|
|
Training Resources: 1x A100 GPUS
|
|
Memory (GB): 43.32
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055-19b14b63.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/segnext/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k/segnext_mscan-l_1x16_512x512_adamw_160k_ade20k_20230209_172055.log.json
|
|
Paper:
|
|
Title: 'SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation'
|
|
URL: https://arxiv.org/abs/2209.08575
|
|
Code: https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/mscan.py#L328
|
|
Framework: PyTorch
|