mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/twins/metafile.yaml

290 lines
13 KiB
YAML
Raw Permalink Blame History

Models:
- Name: twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 43.26
mIoU(ms+flip): 44.11
Config: configs/twins/twins_pcpvt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-PCPVT-S
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 6.6
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132-41acd132.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_204132.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 46.04
mIoU(ms+flip): 46.92
Config: configs/twins/twins_pcpvt-s_uperhead_8xb4-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-PCPVT-S
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 9.67
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537-8e99c07a.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k/twins_pcpvt-s_uperhead_8x4_512x512_160k_ade20k_20211201_233537.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 45.66
mIoU(ms+flip): 46.48
Config: configs/twins/twins_pcpvt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-PCPVT-B
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 8.41
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019-d396db72.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141019.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 47.91
mIoU(ms+flip): 48.64
Config: configs/twins/twins_pcpvt-b_uperhead_8xb2-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- Twins-PCPVT-B
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 6.46
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020-02094ea5.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-b_uperhead_8x2_512x512_160k_ade20k_20211130_141020.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 45.94
mIoU(ms+flip): 46.7
Config: configs/twins/twins_pcpvt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-PCPVT-L
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 10.78
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226-bc6d61dc.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_pcpvt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_105226.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 49.35
mIoU(ms+flip): 50.08
Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- Twins-PCPVT-L
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 7.82
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053-c6095c07.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k/twins_pcpvt-l_uperhead_8x2_512x512_160k_ade20k_20211201_075053.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 44.47
mIoU(ms+flip): 45.42
Config: configs/twins/twins_svt-s_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-SVT-S
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 5.8
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006-0a0d3317.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-s_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141006.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_svt-s_uperhead_8xb2-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 46.08
mIoU(ms+flip): 46.96
Config: configs/twins/twins_svt-s_uperhead_8xb2-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- SVT-S
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 4.93
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005-e48a2d94.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-s_uperhead_8x2_512x512_160k_ade20k/twins_svt-s_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 46.77
mIoU(ms+flip): 47.47
Config: configs/twins/twins_svt-b_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-SVT-B
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 8.75
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849-88b2907c.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-b_fpn_fpnhead_8x4_512x512_80k_ade20k_20211201_113849.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_svt-b_uperhead_8xb2-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 48.04
mIoU(ms+flip): 48.87
Config: configs/twins/twins_svt-b_uperhead_8xb2-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- Twins-SVT-B
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 6.77
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826-0943a1f1.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-b_uperhead_8x2_512x512_160k_ade20k/twins_svt-b_uperhead_8x2_512x512_160k_ade20k_20211202_040826.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512
In Collection: FPN
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 46.55
mIoU(ms+flip): 47.74
Config: configs/twins/twins_svt-l_fpn_fpnhead_8xb4-80k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 32
Architecture:
- Twins-SVT-L
- FPN
Training Resources: 8x V100 GPUS
Memory (GB): 11.2
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005-1d59bee2.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k/twins_svt-l_fpn_fpnhead_8x4_512x512_80k_ade20k_20211130_141005.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
- Name: twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512
In Collection: UPerNet
Results:
Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 49.65
mIoU(ms+flip): 50.63
Config: configs/twins/twins_pcpvt-l_uperhead_8xb2-160k_ade20k-512x512.py
Metadata:
Training Data: ADE20K
Batch Size: 16
Architecture:
- Twins-SVT-L
- UPerNet
Training Resources: 8x V100 GPUS
Memory (GB): 8.41
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005-3e2cae61.pth
Training log: https://download.openmmlab.com/mmsegmentation/v0.5/twins/twins_svt-l_uperhead_8x2_512x512_160k_ade20k/twins_svt-l_uperhead_8x2_512x512_160k_ade20k_20211130_141005.log.json
Paper:
Title: 'Twins: Revisiting the Design of Spatial Attention in Vision Transformers'
URL: https://arxiv.org/pdf/2104.13840.pdf
Code: https://github.com/open-mmlab/mmsegmentation/blob/v0.20.0/mmseg/models/backbones/twins.py#L352
Framework: PyTorch
Reference in New Issue View Git Blame Copy Permalink