112 lines
4.6 KiB
YAML
112 lines
4.6 KiB
YAML
Collections:
|
|
- Name: MaskFormer
|
|
License: Apache License 2.0
|
|
Metadata:
|
|
Training Data:
|
|
- Usage
|
|
- ADE20K
|
|
Paper:
|
|
Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
|
|
Segmentation'
|
|
URL: https://arxiv.org/abs/2107.06278
|
|
README: configs/maskformer/README.md
|
|
Frameworks:
|
|
- PyTorch
|
|
Models:
|
|
- Name: maskformer_r50-d32_8xb2-160k_ade20k-512x512
|
|
In Collection: MaskFormer
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 44.29
|
|
Config: configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- R-50-D32
|
|
- MaskFormer
|
|
Training Resources: 8x 42.20 GPUS
|
|
Memory (GB): 3.29
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-3a9cfe45.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.json
|
|
Paper:
|
|
Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
|
|
Segmentation'
|
|
URL: https://arxiv.org/abs/2107.06278
|
|
Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
|
|
Framework: PyTorch
|
|
- Name: maskformer_r101-d32_8xb2-160k_ade20k-512x512
|
|
In Collection: MaskFormer
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 45.11
|
|
Config: configs/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- R-101-D32
|
|
- MaskFormer
|
|
Training Resources: 8x 34.90 GPUS
|
|
Memory (GB): 4.12
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053-84adbfcb.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_r101-d32_8xb2-160k_ade20k-512x512/maskformer_r101-d32_8xb2-160k_ade20k-512x512_20221031_223053.json
|
|
Paper:
|
|
Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
|
|
Segmentation'
|
|
URL: https://arxiv.org/abs/2107.06278
|
|
Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
|
|
Framework: PyTorch
|
|
- Name: maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512
|
|
In Collection: MaskFormer
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 46.69
|
|
Config: configs/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- Swin-T
|
|
- MaskFormer
|
|
Training Resources: 8x 40.53 GPUS
|
|
Memory (GB): 3.73
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813-f14e7ce0.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-t_upernet_8xb2-160k_ade20k-512x512_20221114_232813.json
|
|
Paper:
|
|
Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
|
|
Segmentation'
|
|
URL: https://arxiv.org/abs/2107.06278
|
|
Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
|
|
Framework: PyTorch
|
|
- Name: maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512
|
|
In Collection: MaskFormer
|
|
Results:
|
|
Task: Semantic Segmentation
|
|
Dataset: ADE20K
|
|
Metrics:
|
|
mIoU: 49.36
|
|
Config: configs/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512.py
|
|
Metadata:
|
|
Training Data: ADE20K
|
|
Batch Size: 16
|
|
Architecture:
|
|
- Swin-S
|
|
- MaskFormer
|
|
Training Resources: 8x 26.98 GPUS
|
|
Memory (GB): 5.33
|
|
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710-723512c7.pth
|
|
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/maskformer/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512/maskformer_swin-s_upernet_8xb2-160k_ade20k-512x512_20221115_114710.json
|
|
Paper:
|
|
Title: 'MaskFormer: Per-Pixel Classification is Not All You Need for Semantic
|
|
Segmentation'
|
|
URL: https://arxiv.org/abs/2107.06278
|
|
Code: https://github.com/open-mmlab/mmdetection/blob/dev-3.x/mmdet/models/dense_heads/maskformer_head.py#L21
|
|
Framework: PyTorch
|