mmsegmentation/configs/segmenter/segmenter.yml

126 lines
4.0 KiB
YAML

Collections:
- Name: Segmenter
Metadata:
Training Data:
- ADE20K
Paper:
URL: https://arxiv.org/abs/2105.05633
Title: 'Segmenter: Transformer for Semantic Segmentation'
README: configs/segmenter/README.md
Code:
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.21.0/mmseg/models/decode_heads/segmenter_mask_head.py#L15
Version: v0.21.0
Converted From:
Code: https://github.com/rstrudel/segmenter
Models:
- Name: segmenter_vit-t_mask_8x1_512x512_160k_ade20k
In Collection: Segmenter
Metadata:
backbone: ViT-T_16
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 35.74
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.21
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 39.99
mIoU(ms+flip): 40.83
Config: configs/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-t_mask_8x1_512x512_160k_ade20k/segmenter_vit-t_mask_8x1_512x512_160k_ade20k_20220105_151706-ffcf7509.pth
- Name: segmenter_vit-s_linear_8x1_512x512_160k_ade20k
In Collection: Segmenter
Metadata:
backbone: ViT-S_16
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 35.63
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 1.78
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 45.75
mIoU(ms+flip): 46.82
Config: configs/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_linear_8x1_512x512_160k_ade20k/segmenter_vit-s_linear_8x1_512x512_160k_ade20k_20220105_151713-39658c46.pth
- Name: segmenter_vit-s_mask_8x1_512x512_160k_ade20k
In Collection: Segmenter
Metadata:
backbone: ViT-S_16
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 40.32
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 2.03
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 46.19
mIoU(ms+flip): 47.85
Config: configs/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-s_mask_8x1_512x512_160k_ade20k/segmenter_vit-s_mask_8x1_512x512_160k_ade20k_20220105_151706-511bb103.pth
- Name: segmenter_vit-b_mask_8x1_512x512_160k_ade20k
In Collection: Segmenter
Metadata:
backbone: ViT-B_16
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 75.76
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 4.2
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 49.6
mIoU(ms+flip): 51.07
Config: configs/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-b_mask_8x1_512x512_160k_ade20k/segmenter_vit-b_mask_8x1_512x512_160k_ade20k_20220105_151706-bc533b08.pth
- Name: segmenter_vit-l_mask_8x1_640x640_160k_ade20k
In Collection: Segmenter
Metadata:
backbone: ViT-L_16
crop size: (640,640)
lr schd: 160000
inference time (ms/im):
- value: 330.03
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (640,640)
Training Memory (GB): 16.99
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 51.65
mIoU(ms+flip): 53.58
Config: configs/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/segmenter/segmenter_vit-l_mask_8x1_640x640_160k_ade20k/segmenter_vit-l_mask_8x1_640x640_160k_ade20k_20220614_024513-4783a347.pth