Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update metafiles #661

Merged
merged 2 commits into from
Jul 1, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
112 changes: 96 additions & 16 deletions configs/ann/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,12 @@ Models:
- Name: ann_r50-d8_512x1024_40k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 269.54
inference time (ms/im):
- value: 269.54
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -25,7 +30,12 @@ Models:
- Name: ann_r101-d8_512x1024_40k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 392.16
inference time (ms/im):
- value: 392.16
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -39,7 +49,12 @@ Models:
- Name: ann_r50-d8_769x769_40k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 588.24
inference time (ms/im):
- value: 588.24
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -53,7 +68,12 @@ Models:
- Name: ann_r101-d8_769x769_40k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 869.57
inference time (ms/im):
- value: 869.57
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -67,7 +87,12 @@ Models:
- Name: ann_r50-d8_512x1024_80k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 269.54
inference time (ms/im):
- value: 269.54
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -81,7 +106,12 @@ Models:
- Name: ann_r101-d8_512x1024_80k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 392.16
inference time (ms/im):
- value: 392.16
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -95,7 +125,12 @@ Models:
- Name: ann_r50-d8_769x769_80k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 588.24
inference time (ms/im):
- value: 588.24
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -109,7 +144,12 @@ Models:
- Name: ann_r101-d8_769x769_80k_cityscapes
In Collection: ANN
Metadata:
inference time (ms/im): 869.57
inference time (ms/im):
- value: 869.57
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -123,7 +163,12 @@ Models:
- Name: ann_r50-d8_512x512_80k_ade20k
In Collection: ANN
Metadata:
inference time (ms/im): 47.6
inference time (ms/im):
- value: 47.6
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -137,7 +182,12 @@ Models:
- Name: ann_r101-d8_512x512_80k_ade20k
In Collection: ANN
Metadata:
inference time (ms/im): 70.82
inference time (ms/im):
- value: 70.82
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -151,7 +201,12 @@ Models:
- Name: ann_r50-d8_512x512_160k_ade20k
In Collection: ANN
Metadata:
inference time (ms/im): 47.6
inference time (ms/im):
- value: 47.6
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -165,7 +220,12 @@ Models:
- Name: ann_r101-d8_512x512_160k_ade20k
In Collection: ANN
Metadata:
inference time (ms/im): 70.82
inference time (ms/im):
- value: 70.82
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -179,7 +239,12 @@ Models:
- Name: ann_r50-d8_512x512_20k_voc12aug
In Collection: ANN
Metadata:
inference time (ms/im): 47.8
inference time (ms/im):
- value: 47.8
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Expand All @@ -193,7 +258,12 @@ Models:
- Name: ann_r101-d8_512x512_20k_voc12aug
In Collection: ANN
Metadata:
inference time (ms/im): 71.74
inference time (ms/im):
- value: 71.74
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Expand All @@ -207,7 +277,12 @@ Models:
- Name: ann_r50-d8_512x512_40k_voc12aug
In Collection: ANN
Metadata:
inference time (ms/im): 47.8
inference time (ms/im):
- value: 47.8
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Expand All @@ -221,7 +296,12 @@ Models:
- Name: ann_r101-d8_512x512_40k_voc12aug
In Collection: ANN
Metadata:
inference time (ms/im): 71.74
inference time (ms/im):
- value: 71.74
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Pascal VOC 2012 + Aug
Expand Down
84 changes: 72 additions & 12 deletions configs/apcnet/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,12 @@ Models:
- Name: apcnet_r50-d8_512x1024_40k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 280.11
inference time (ms/im):
- value: 280.11
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -24,7 +29,12 @@ Models:
- Name: apcnet_r101-d8_512x1024_40k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 465.12
inference time (ms/im):
- value: 465.12
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -38,7 +48,12 @@ Models:
- Name: apcnet_r50-d8_769x769_40k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 657.89
inference time (ms/im):
- value: 657.89
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -52,7 +67,12 @@ Models:
- Name: apcnet_r101-d8_769x769_40k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 970.87
inference time (ms/im):
- value: 970.87
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -66,7 +86,12 @@ Models:
- Name: apcnet_r50-d8_512x1024_80k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 280.11
inference time (ms/im):
- value: 280.11
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -80,7 +105,12 @@ Models:
- Name: apcnet_r101-d8_512x1024_80k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 465.12
inference time (ms/im):
- value: 465.12
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -94,7 +124,12 @@ Models:
- Name: apcnet_r50-d8_769x769_80k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 657.89
inference time (ms/im):
- value: 657.89
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -108,7 +143,12 @@ Models:
- Name: apcnet_r101-d8_769x769_80k_cityscapes
In Collection: APCNet
Metadata:
inference time (ms/im): 970.87
inference time (ms/im):
- value: 970.87
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: Cityscapes
Expand All @@ -122,7 +162,12 @@ Models:
- Name: apcnet_r50-d8_512x512_80k_ade20k
In Collection: APCNet
Metadata:
inference time (ms/im): 50.99
inference time (ms/im):
- value: 50.99
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -136,7 +181,12 @@ Models:
- Name: apcnet_r101-d8_512x512_80k_ade20k
In Collection: APCNet
Metadata:
inference time (ms/im): 76.34
inference time (ms/im):
- value: 76.34
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -150,7 +200,12 @@ Models:
- Name: apcnet_r50-d8_512x512_160k_ade20k
In Collection: APCNet
Metadata:
inference time (ms/im): 50.99
inference time (ms/im):
- value: 50.99
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand All @@ -164,7 +219,12 @@ Models:
- Name: apcnet_r101-d8_512x512_160k_ade20k
In Collection: APCNet
Metadata:
inference time (ms/im): 76.34
inference time (ms/im):
- value: 76.34
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Expand Down
Loading