Junjun2016
GitHub
parent
170a9d1f7c
commit
36c81441c1
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 301.2
|
||||
inference time (ms/im):
|
||||
- value: 301.2
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 432.9
|
||||
inference time (ms/im):
|
||||
- value: 432.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 699.3
|
||||
inference time (ms/im):
|
||||
- value: 699.3
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 990.1
|
||||
inference time (ms/im):
|
||||
- value: 990.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 301.2
|
||||
inference time (ms/im):
|
||||
- value: 301.2
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 432.9
|
||||
inference time (ms/im):
|
||||
- value: 432.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 699.3
|
||||
inference time (ms/im):
|
||||
- value: 699.3
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 990.1
|
||||
inference time (ms/im):
|
||||
- value: 990.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.87
|
||||
inference time (ms/im):
|
||||
- value: 47.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 70.87
|
||||
inference time (ms/im):
|
||||
- value: 70.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.87
|
||||
inference time (ms/im):
|
||||
- value: 47.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 70.87
|
||||
inference time (ms/im):
|
||||
- value: 70.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 48.9
|
||||
inference time (ms/im):
|
||||
- value: 48.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 73.31
|
||||
inference time (ms/im):
|
||||
- value: 73.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: ccnet_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 48.9
|
||||
inference time (ms/im):
|
||||
- value: 48.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: ccnet_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: CCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 73.31
|
||||
inference time (ms/im):
|
||||
- value: 73.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -9,7 +9,12 @@ Models:
|
|||
- Name: cgnet_680x680_60k_cityscapes
|
||||
In Collection: CGNet
|
||||
Metadata:
|
||||
inference time (ms/im): 32.78
|
||||
inference time (ms/im):
|
||||
- value: 32.78
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -23,7 +28,12 @@ Models:
|
|||
- Name: cgnet_512x1024_60k_cityscapes
|
||||
In Collection: CGNet
|
||||
Metadata:
|
||||
inference time (ms/im): 32.11
|
||||
inference time (ms/im):
|
||||
- value: 32.11
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 502.51
|
||||
inference time (ms/im):
|
||||
- value: 502.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: danet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 641.03
|
||||
inference time (ms/im):
|
||||
- value: 641.03
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: danet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 934.58
|
||||
inference time (ms/im):
|
||||
- value: 934.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 502.51
|
||||
inference time (ms/im):
|
||||
- value: 502.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: danet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 641.03
|
||||
inference time (ms/im):
|
||||
- value: 641.03
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: danet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 934.58
|
||||
inference time (ms/im):
|
||||
- value: 934.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.17
|
||||
inference time (ms/im):
|
||||
- value: 47.17
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 70.52
|
||||
inference time (ms/im):
|
||||
- value: 70.52
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.17
|
||||
inference time (ms/im):
|
||||
- value: 47.17
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 70.52
|
||||
inference time (ms/im):
|
||||
- value: 70.52
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.76
|
||||
inference time (ms/im):
|
||||
- value: 47.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 72.67
|
||||
inference time (ms/im):
|
||||
- value: 72.67
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: danet_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.76
|
||||
inference time (ms/im):
|
||||
- value: 47.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: danet_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: DANet
|
||||
Metadata:
|
||||
inference time (ms/im): 72.67
|
||||
inference time (ms/im):
|
||||
- value: 72.67
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -12,7 +12,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 389.11
|
||||
inference time (ms/im):
|
||||
- value: 389.11
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -26,7 +31,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 520.83
|
||||
inference time (ms/im):
|
||||
- value: 520.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -40,7 +50,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 900.9
|
||||
inference time (ms/im):
|
||||
- value: 900.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -54,7 +69,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 1204.82
|
||||
inference time (ms/im):
|
||||
- value: 1204.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -68,7 +88,12 @@ Models:
|
|||
- Name: deeplabv3_r18-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 72.57
|
||||
inference time (ms/im):
|
||||
- value: 72.57
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -82,7 +107,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 389.11
|
||||
inference time (ms/im):
|
||||
- value: 389.11
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -96,7 +126,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 520.83
|
||||
inference time (ms/im):
|
||||
- value: 520.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -110,7 +145,12 @@ Models:
|
|||
- Name: deeplabv3_r18-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 180.18
|
||||
inference time (ms/im):
|
||||
- value: 180.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -124,7 +164,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 900.9
|
||||
inference time (ms/im):
|
||||
- value: 900.9
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -138,7 +183,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 1204.82
|
||||
inference time (ms/im):
|
||||
- value: 1204.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -152,7 +202,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d16-mg124_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 143.68
|
||||
inference time (ms/im):
|
||||
- value: 143.68
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -166,7 +221,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d16-mg124_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 143.68
|
||||
inference time (ms/im):
|
||||
- value: 143.68
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -180,7 +240,12 @@ Models:
|
|||
- Name: deeplabv3_r18b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 71.79
|
||||
inference time (ms/im):
|
||||
- value: 71.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -194,7 +259,12 @@ Models:
|
|||
- Name: deeplabv3_r50b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 364.96
|
||||
inference time (ms/im):
|
||||
- value: 364.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -208,7 +278,12 @@ Models:
|
|||
- Name: deeplabv3_r101b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 552.49
|
||||
inference time (ms/im):
|
||||
- value: 552.49
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -222,7 +297,12 @@ Models:
|
|||
- Name: deeplabv3_r18b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 172.71
|
||||
inference time (ms/im):
|
||||
- value: 172.71
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -236,7 +316,12 @@ Models:
|
|||
- Name: deeplabv3_r50b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 862.07
|
||||
inference time (ms/im):
|
||||
- value: 862.07
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -250,7 +335,12 @@ Models:
|
|||
- Name: deeplabv3_r101b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 1219.51
|
||||
inference time (ms/im):
|
||||
- value: 1219.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -264,7 +354,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x512_80k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 67.75
|
||||
inference time (ms/im):
|
||||
- value: 67.75
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -278,7 +373,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x512_80k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 98.62
|
||||
inference time (ms/im):
|
||||
- value: 98.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -292,7 +392,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 67.75
|
||||
inference time (ms/im):
|
||||
- value: 67.75
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -306,7 +411,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 98.62
|
||||
inference time (ms/im):
|
||||
- value: 98.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -320,7 +430,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -334,7 +449,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 101.94
|
||||
inference time (ms/im):
|
||||
- value: 101.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -348,7 +468,12 @@ Models:
|
|||
- Name: deeplabv3_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -362,7 +487,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 101.94
|
||||
inference time (ms/im):
|
||||
- value: 101.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -376,7 +506,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 141.04
|
||||
inference time (ms/im):
|
||||
- value: 141.04
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -390,7 +525,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_480x480_80k_pascal_context
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 141.04
|
||||
inference time (ms/im):
|
||||
- value: 141.04
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -404,7 +544,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -418,7 +563,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_480x480_80k_pascal_context_59
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
|
|||
|
|
@ -12,7 +12,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 253.81
|
||||
inference time (ms/im):
|
||||
- value: 253.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -26,7 +31,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 384.62
|
||||
inference time (ms/im):
|
||||
- value: 384.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -40,7 +50,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 581.4
|
||||
inference time (ms/im):
|
||||
- value: 581.4
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -54,7 +69,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
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
|
||||
|
|
@ -68,7 +88,12 @@ Models:
|
|||
- Name: deeplabv3plus_r18-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 70.08
|
||||
inference time (ms/im):
|
||||
- value: 70.08
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -82,7 +107,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 253.81
|
||||
inference time (ms/im):
|
||||
- value: 253.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -96,7 +126,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 384.62
|
||||
inference time (ms/im):
|
||||
- value: 384.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -110,7 +145,12 @@ Models:
|
|||
- Name: deeplabv3plus_r18-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 174.22
|
||||
inference time (ms/im):
|
||||
- value: 174.22
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -124,7 +164,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 581.4
|
||||
inference time (ms/im):
|
||||
- value: 581.4
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -138,7 +183,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
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
|
||||
|
|
@ -152,7 +202,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d16-mg124_512x1024_40k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 133.69
|
||||
inference time (ms/im):
|
||||
- value: 133.69
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -166,7 +221,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d16-mg124_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 133.69
|
||||
inference time (ms/im):
|
||||
- value: 133.69
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -180,7 +240,12 @@ Models:
|
|||
- Name: deeplabv3plus_r18b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 66.89
|
||||
inference time (ms/im):
|
||||
- value: 66.89
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -194,7 +259,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 253.81
|
||||
inference time (ms/im):
|
||||
- value: 253.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -208,7 +278,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101b-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 384.62
|
||||
inference time (ms/im):
|
||||
- value: 384.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -222,7 +297,12 @@ Models:
|
|||
- Name: deeplabv3plus_r18b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 167.79
|
||||
inference time (ms/im):
|
||||
- value: 167.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -236,7 +316,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 581.4
|
||||
inference time (ms/im):
|
||||
- value: 581.4
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -250,7 +335,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101b-d8_769x769_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 909.09
|
||||
inference time (ms/im):
|
||||
- value: 909.09
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -264,7 +354,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x512_80k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
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
|
||||
|
|
@ -278,7 +373,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x512_80k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 70.62
|
||||
inference time (ms/im):
|
||||
- value: 70.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -292,7 +392,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
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
|
||||
|
|
@ -306,7 +411,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 70.62
|
||||
inference time (ms/im):
|
||||
- value: 70.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -320,7 +430,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 47.62
|
||||
inference time (ms/im):
|
||||
- value: 47.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -334,7 +449,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -348,7 +468,12 @@ Models:
|
|||
- Name: deeplabv3plus_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 47.62
|
||||
inference time (ms/im):
|
||||
- value: 47.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -362,7 +487,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -376,7 +506,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 110.01
|
||||
inference time (ms/im):
|
||||
- value: 110.01
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -390,7 +525,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 110.01
|
||||
inference time (ms/im):
|
||||
- value: 110.01
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -404,7 +544,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -418,7 +563,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_480x480_80k_pascal_context
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
|
|||
|
|
@ -10,7 +10,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 273.22
|
||||
inference time (ms/im):
|
||||
- value: 273.22
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -24,7 +29,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 393.7
|
||||
inference time (ms/im):
|
||||
- value: 393.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -38,7 +48,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 636.94
|
||||
inference time (ms/im):
|
||||
- value: 636.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -52,7 +67,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 990.1
|
||||
inference time (ms/im):
|
||||
- value: 990.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -66,7 +86,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 273.22
|
||||
inference time (ms/im):
|
||||
- value: 273.22
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -80,7 +105,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 393.7
|
||||
inference time (ms/im):
|
||||
- value: 393.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -94,7 +124,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 636.94
|
||||
inference time (ms/im):
|
||||
- value: 636.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -108,7 +143,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 990.1
|
||||
inference time (ms/im):
|
||||
- value: 990.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -122,7 +162,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.73
|
||||
inference time (ms/im):
|
||||
- value: 47.73
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -136,7 +181,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -150,7 +200,12 @@ Models:
|
|||
- Name: dmnet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 47.73
|
||||
inference time (ms/im):
|
||||
- value: 47.73
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -164,7 +219,12 @@ Models:
|
|||
- Name: dmnet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: DMNet
|
||||
Metadata:
|
||||
inference time (ms/im): 72.05
|
||||
inference time (ms/im):
|
||||
- value: 72.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -10,7 +10,12 @@ Models:
|
|||
- Name: dnl_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 390.62
|
||||
inference time (ms/im):
|
||||
- value: 390.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -24,7 +29,12 @@ Models:
|
|||
- Name: dnl_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 510.2
|
||||
inference time (ms/im):
|
||||
- value: 510.2
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -38,7 +48,12 @@ Models:
|
|||
- Name: dnl_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 666.67
|
||||
inference time (ms/im):
|
||||
- value: 666.67
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -52,7 +67,12 @@ Models:
|
|||
- Name: dnl_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 980.39
|
||||
inference time (ms/im):
|
||||
- value: 980.39
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -66,7 +86,12 @@ Models:
|
|||
- Name: dnl_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 390.62
|
||||
inference time (ms/im):
|
||||
- value: 390.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -80,7 +105,12 @@ Models:
|
|||
- Name: dnl_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 510.2
|
||||
inference time (ms/im):
|
||||
- value: 510.2
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -94,7 +124,12 @@ Models:
|
|||
- Name: dnl_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 666.67
|
||||
inference time (ms/im):
|
||||
- value: 666.67
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -108,7 +143,12 @@ Models:
|
|||
- Name: dnl_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 980.39
|
||||
inference time (ms/im):
|
||||
- value: 980.39
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -122,7 +162,12 @@ Models:
|
|||
- Name: dnl_r50-d8_512x512_80k_ade20k
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 48.4
|
||||
inference time (ms/im):
|
||||
- value: 48.4
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -136,7 +181,12 @@ Models:
|
|||
- Name: dnl_r101-d8_512x512_80k_ade20k
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 79.74
|
||||
inference time (ms/im):
|
||||
- value: 79.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -150,7 +200,12 @@ Models:
|
|||
- Name: dnl_r50-d8_512x512_160k_ade20k
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 48.4
|
||||
inference time (ms/im):
|
||||
- value: 48.4
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -164,7 +219,12 @@ Models:
|
|||
- Name: dnl_r101-d8_512x512_160k_ade20k
|
||||
In Collection: dnl
|
||||
Metadata:
|
||||
inference time (ms/im): 79.74
|
||||
inference time (ms/im):
|
||||
- value: 79.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -9,7 +9,12 @@ Models:
|
|||
- Name: emanet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: EMANet
|
||||
Metadata:
|
||||
inference time (ms/im): 218.34
|
||||
inference time (ms/im):
|
||||
- value: 218.34
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -23,7 +28,12 @@ Models:
|
|||
- Name: emanet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: EMANet
|
||||
Metadata:
|
||||
inference time (ms/im): 348.43
|
||||
inference time (ms/im):
|
||||
- value: 348.43
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -37,7 +47,12 @@ Models:
|
|||
- Name: emanet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: EMANet
|
||||
Metadata:
|
||||
inference time (ms/im): 507.61
|
||||
inference time (ms/im):
|
||||
- value: 507.61
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -51,7 +66,12 @@ Models:
|
|||
- Name: emanet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: EMANet
|
||||
Metadata:
|
||||
inference time (ms/im): 819.67
|
||||
inference time (ms/im):
|
||||
- value: 819.67
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: encnet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 218.34
|
||||
inference time (ms/im):
|
||||
- value: 218.34
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: encnet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: encnet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 549.45
|
||||
inference time (ms/im):
|
||||
- value: 549.45
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: encnet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 793.65
|
||||
inference time (ms/im):
|
||||
- value: 793.65
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: encnet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 218.34
|
||||
inference time (ms/im):
|
||||
- value: 218.34
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: encnet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: encnet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 549.45
|
||||
inference time (ms/im):
|
||||
- value: 549.45
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: encnet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 793.65
|
||||
inference time (ms/im):
|
||||
- value: 793.65
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: encnet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 43.84
|
||||
inference time (ms/im):
|
||||
- value: 43.84
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: encnet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 67.25
|
||||
inference time (ms/im):
|
||||
- value: 67.25
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: encnet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 43.84
|
||||
inference time (ms/im):
|
||||
- value: 43.84
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: encnet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: encnet
|
||||
Metadata:
|
||||
inference time (ms/im): 67.25
|
||||
inference time (ms/im):
|
||||
- value: 67.25
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -9,7 +9,12 @@ Models:
|
|||
- Name: fast_scnn_4x8_80k_lr0.12_cityscapes
|
||||
In Collection: Fast-SCNN
|
||||
Metadata:
|
||||
inference time (ms/im): 15.72
|
||||
inference time (ms/im):
|
||||
- value: 15.72
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
|
|||
|
|
@ -19,7 +19,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 239.81
|
||||
inference time (ms/im):
|
||||
- value: 239.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -33,7 +38,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -47,7 +57,12 @@ Models:
|
|||
- Name: fcn_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 555.56
|
||||
inference time (ms/im):
|
||||
- value: 555.56
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -61,7 +76,12 @@ Models:
|
|||
- Name: fcn_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 840.34
|
||||
inference time (ms/im):
|
||||
- value: 840.34
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -75,7 +95,12 @@ Models:
|
|||
- Name: fcn_r18-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 68.26
|
||||
inference time (ms/im):
|
||||
- value: 68.26
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -89,7 +114,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 239.81
|
||||
inference time (ms/im):
|
||||
- value: 239.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -103,7 +133,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 375.94
|
||||
inference time (ms/im):
|
||||
- value: 375.94
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -117,7 +152,12 @@ Models:
|
|||
- Name: fcn_r18-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 156.25
|
||||
inference time (ms/im):
|
||||
- value: 156.25
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -131,7 +171,12 @@ Models:
|
|||
- Name: fcn_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 555.56
|
||||
inference time (ms/im):
|
||||
- value: 555.56
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -145,7 +190,12 @@ Models:
|
|||
- Name: fcn_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 840.34
|
||||
inference time (ms/im):
|
||||
- value: 840.34
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -159,7 +209,12 @@ Models:
|
|||
- Name: fcn_r18b-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 59.74
|
||||
inference time (ms/im):
|
||||
- value: 59.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -173,7 +228,12 @@ Models:
|
|||
- Name: fcn_r50b-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 238.1
|
||||
inference time (ms/im):
|
||||
- value: 238.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -187,7 +247,12 @@ Models:
|
|||
- Name: fcn_r101b-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 366.3
|
||||
inference time (ms/im):
|
||||
- value: 366.3
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -201,7 +266,12 @@ Models:
|
|||
- Name: fcn_r18b-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 149.25
|
||||
inference time (ms/im):
|
||||
- value: 149.25
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -215,7 +285,12 @@ Models:
|
|||
- Name: fcn_r50b-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 549.45
|
||||
inference time (ms/im):
|
||||
- value: 549.45
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -229,7 +304,12 @@ Models:
|
|||
- Name: fcn_r101b-d8_769x769_80k_cityscapes
|
||||
In Collection: FCN
|
||||
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
|
||||
|
|
@ -243,7 +323,12 @@ Models:
|
|||
- Name: fcn_d6_r50-d16_512x1024_40k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 97.85
|
||||
inference time (ms/im):
|
||||
- value: 97.85
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -257,7 +342,12 @@ Models:
|
|||
- Name: fcn_d6_r50-d16_512x1024_80k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 96.62
|
||||
inference time (ms/im):
|
||||
- value: 96.62
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -271,7 +361,12 @@ Models:
|
|||
- Name: fcn_d6_r50-d16_769x769_40k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 239.81
|
||||
inference time (ms/im):
|
||||
- value: 239.81
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -285,7 +380,12 @@ Models:
|
|||
- Name: fcn_d6_r50-d16_769x769_80k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 240.96
|
||||
inference time (ms/im):
|
||||
- value: 240.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -299,7 +399,12 @@ Models:
|
|||
- Name: fcn_d6_r101-d16_512x1024_40k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 124.38
|
||||
inference time (ms/im):
|
||||
- value: 124.38
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -313,7 +418,12 @@ Models:
|
|||
- Name: fcn_d6_r101-d16_512x1024_80k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 121.07
|
||||
inference time (ms/im):
|
||||
- value: 121.07
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -327,7 +437,12 @@ Models:
|
|||
- Name: fcn_d6_r101-d16_769x769_40k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 320.51
|
||||
inference time (ms/im):
|
||||
- value: 320.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -341,7 +456,12 @@ Models:
|
|||
- Name: fcn_d6_r101-d16_769x769_80k_cityscapes
|
||||
In Collection: FCN-D6
|
||||
Metadata:
|
||||
inference time (ms/im): 311.53
|
||||
inference time (ms/im):
|
||||
- value: 311.53
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -355,7 +475,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x512_80k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.57
|
||||
inference time (ms/im):
|
||||
- value: 42.57
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -369,7 +494,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x512_80k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 67.66
|
||||
inference time (ms/im):
|
||||
- value: 67.66
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -383,7 +513,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.57
|
||||
inference time (ms/im):
|
||||
- value: 42.57
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -397,7 +532,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 67.66
|
||||
inference time (ms/im):
|
||||
- value: 67.66
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -411,7 +551,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.96
|
||||
inference time (ms/im):
|
||||
- value: 42.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -425,7 +570,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 67.52
|
||||
inference time (ms/im):
|
||||
- value: 67.52
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -439,7 +589,12 @@ Models:
|
|||
- Name: fcn_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.96
|
||||
inference time (ms/im):
|
||||
- value: 42.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -453,7 +608,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 67.52
|
||||
inference time (ms/im):
|
||||
- value: 67.52
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -467,7 +627,12 @@ Models:
|
|||
- Name: fcn_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 100.7
|
||||
inference time (ms/im):
|
||||
- value: 100.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -481,7 +646,12 @@ Models:
|
|||
- Name: fcn_r101-d8_480x480_80k_pascal_context
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 100.7
|
||||
inference time (ms/im):
|
||||
- value: 100.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -495,7 +665,12 @@ Models:
|
|||
- Name: fcn_r101-d8_480x480_40k_pascal_context_59
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -509,7 +684,12 @@ Models:
|
|||
- Name: fcn_r101-d8_480x480_80k_pascal_context_59
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
|
|||
|
|
@ -4,7 +4,12 @@ Models:
|
|||
- Name: fcn_r101-d8_512x1024_80k_fp16_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 115.74
|
||||
inference time (ms/im):
|
||||
- value: 115.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -18,7 +23,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x1024_80k_fp16_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 114.03
|
||||
inference time (ms/im):
|
||||
- value: 114.03
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -32,7 +42,12 @@ Models:
|
|||
- Name: deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 259.07
|
||||
inference time (ms/im):
|
||||
- value: 259.07
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -46,7 +61,12 @@ Models:
|
|||
- Name: deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 127.06
|
||||
inference time (ms/im):
|
||||
- value: 127.06
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 254.45
|
||||
inference time (ms/im):
|
||||
- value: 254.45
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 383.14
|
||||
inference time (ms/im):
|
||||
- value: 383.14
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 598.8
|
||||
inference time (ms/im):
|
||||
- value: 598.8
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 884.96
|
||||
inference time (ms/im):
|
||||
- value: 884.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 254.45
|
||||
inference time (ms/im):
|
||||
- value: 254.45
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 383.14
|
||||
inference time (ms/im):
|
||||
- value: 383.14
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 598.8
|
||||
inference time (ms/im):
|
||||
- value: 598.8
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 884.96
|
||||
inference time (ms/im):
|
||||
- value: 884.96
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.77
|
||||
inference time (ms/im):
|
||||
- value: 42.77
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 65.79
|
||||
inference time (ms/im):
|
||||
- value: 65.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.77
|
||||
inference time (ms/im):
|
||||
- value: 42.77
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 65.79
|
||||
inference time (ms/im):
|
||||
- value: 65.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.83
|
||||
inference time (ms/im):
|
||||
- value: 42.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 67.57
|
||||
inference time (ms/im):
|
||||
- value: 67.57
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: gcnet_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.83
|
||||
inference time (ms/im):
|
||||
- value: 42.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: gcnet_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: GCNet
|
||||
Metadata:
|
||||
inference time (ms/im): 67.57
|
||||
inference time (ms/im):
|
||||
- value: 67.57
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -2,7 +2,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x1024_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.12
|
||||
inference time (ms/im):
|
||||
- value: 42.12
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -16,7 +21,12 @@ Models:
|
|||
- Name: fcn_hr18_512x1024_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 77.1
|
||||
inference time (ms/im):
|
||||
- value: 77.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -30,7 +40,12 @@ Models:
|
|||
- Name: fcn_hr48_512x1024_40k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 155.76
|
||||
inference time (ms/im):
|
||||
- value: 155.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -44,7 +59,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.12
|
||||
inference time (ms/im):
|
||||
- value: 42.12
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -58,7 +78,12 @@ Models:
|
|||
- Name: fcn_hr18_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 77.1
|
||||
inference time (ms/im):
|
||||
- value: 77.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -72,7 +97,12 @@ Models:
|
|||
- Name: fcn_hr48_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 155.76
|
||||
inference time (ms/im):
|
||||
- value: 155.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -86,7 +116,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x1024_160k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.12
|
||||
inference time (ms/im):
|
||||
- value: 42.12
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -100,7 +135,12 @@ Models:
|
|||
- Name: fcn_hr18_512x1024_160k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 77.1
|
||||
inference time (ms/im):
|
||||
- value: 77.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -114,7 +154,12 @@ Models:
|
|||
- Name: fcn_hr48_512x1024_160k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 155.76
|
||||
inference time (ms/im):
|
||||
- value: 155.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -128,7 +173,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x512_80k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 25.87
|
||||
inference time (ms/im):
|
||||
- value: 25.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -142,7 +192,12 @@ Models:
|
|||
- Name: fcn_hr18_512x512_80k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 44.31
|
||||
inference time (ms/im):
|
||||
- value: 44.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -156,7 +211,12 @@ Models:
|
|||
- Name: fcn_hr48_512x512_80k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 47.1
|
||||
inference time (ms/im):
|
||||
- value: 47.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -170,7 +230,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 25.87
|
||||
inference time (ms/im):
|
||||
- value: 25.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -184,7 +249,12 @@ Models:
|
|||
- Name: fcn_hr18_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 44.31
|
||||
inference time (ms/im):
|
||||
- value: 44.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -198,7 +268,12 @@ Models:
|
|||
- Name: fcn_hr48_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 47.1
|
||||
inference time (ms/im):
|
||||
- value: 47.1
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -212,7 +287,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x512_20k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 23.06
|
||||
inference time (ms/im):
|
||||
- value: 23.06
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -226,7 +306,12 @@ Models:
|
|||
- Name: fcn_hr18_512x512_20k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.59
|
||||
inference time (ms/im):
|
||||
- value: 42.59
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -240,7 +325,12 @@ Models:
|
|||
- Name: fcn_hr48_512x512_20k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 45.35
|
||||
inference time (ms/im):
|
||||
- value: 45.35
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -254,7 +344,12 @@ Models:
|
|||
- Name: fcn_hr18s_512x512_40k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 23.06
|
||||
inference time (ms/im):
|
||||
- value: 23.06
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -268,7 +363,12 @@ Models:
|
|||
- Name: fcn_hr18_512x512_40k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 42.59
|
||||
inference time (ms/im):
|
||||
- value: 42.59
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -282,7 +382,12 @@ Models:
|
|||
- Name: fcn_hr48_512x512_40k_voc12aug
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 45.35
|
||||
inference time (ms/im):
|
||||
- value: 45.35
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -296,7 +401,12 @@ Models:
|
|||
- Name: fcn_hr48_480x480_40k_pascal_context
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 112.87
|
||||
inference time (ms/im):
|
||||
- value: 112.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -310,7 +420,12 @@ Models:
|
|||
- Name: fcn_hr48_480x480_80k_pascal_context
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 112.87
|
||||
inference time (ms/im):
|
||||
- value: 112.87
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -324,7 +439,12 @@ Models:
|
|||
- Name: fcn_hr48_480x480_40k_pascal_context_59
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -338,7 +458,12 @@ Models:
|
|||
- Name: fcn_hr48_480x480_80k_pascal_context
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
|
|||
|
|
@ -4,7 +4,12 @@ Models:
|
|||
- Name: fcn_m-v2-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 70.42
|
||||
inference time (ms/im):
|
||||
- value: 70.42
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -18,7 +23,12 @@ Models:
|
|||
- Name: pspnet_m-v2-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 89.29
|
||||
inference time (ms/im):
|
||||
- value: 89.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -32,7 +42,12 @@ Models:
|
|||
- Name: deeplabv3_m-v2-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 119.05
|
||||
inference time (ms/im):
|
||||
- value: 119.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -46,7 +61,12 @@ Models:
|
|||
- Name: deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 119.05
|
||||
inference time (ms/im):
|
||||
- value: 119.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -60,7 +80,12 @@ Models:
|
|||
- Name: fcn_m-v2-d8_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 15.53
|
||||
inference time (ms/im):
|
||||
- value: 15.53
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -74,7 +99,12 @@ Models:
|
|||
- Name: pspnet_m-v2-d8_512x512_160k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 17.33
|
||||
inference time (ms/im):
|
||||
- value: 17.33
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -88,7 +118,12 @@ Models:
|
|||
- Name: deeplabv3_m-v2-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 25.06
|
||||
inference time (ms/im):
|
||||
- value: 25.06
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -102,7 +137,12 @@ Models:
|
|||
- Name: deeplabv3plus_m-v2-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 23.2
|
||||
inference time (ms/im):
|
||||
- value: 23.2
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -9,7 +9,12 @@ Models:
|
|||
- Name: lraspp_m-v3-d8_512x1024_320k_cityscapes
|
||||
In Collection: LRASPP
|
||||
Metadata:
|
||||
inference time (ms/im): 65.7
|
||||
inference time (ms/im):
|
||||
- value: 65.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -23,7 +28,12 @@ Models:
|
|||
- Name: lraspp_m-v3-d8_scratch_512x1024_320k_cityscapes
|
||||
In Collection: LRASPP
|
||||
Metadata:
|
||||
inference time (ms/im): 67.7
|
||||
inference time (ms/im):
|
||||
- value: 67.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -37,7 +47,12 @@ Models:
|
|||
- Name: lraspp_m-v3s-d8_512x1024_320k_cityscapes
|
||||
In Collection: LRASPP
|
||||
Metadata:
|
||||
inference time (ms/im): 42.3
|
||||
inference time (ms/im):
|
||||
- value: 42.3
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -51,7 +66,12 @@ Models:
|
|||
- Name: lraspp_m-v3s-d8_scratch_512x1024_320k_cityscapes
|
||||
In Collection: LRASPP
|
||||
Metadata:
|
||||
inference time (ms/im): 40.82
|
||||
inference time (ms/im):
|
||||
- value: 40.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 367.65
|
||||
inference time (ms/im):
|
||||
- value: 367.65
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 512.82
|
||||
inference time (ms/im):
|
||||
- value: 512.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: NonLocal
|
||||
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
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 952.38
|
||||
inference time (ms/im):
|
||||
- value: 952.38
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 367.65
|
||||
inference time (ms/im):
|
||||
- value: 367.65
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 512.82
|
||||
inference time (ms/im):
|
||||
- value: 512.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: NonLocal
|
||||
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
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 952.38
|
||||
inference time (ms/im):
|
||||
- value: 952.38
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x512_80k_ade20k
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 46.79
|
||||
inference time (ms/im):
|
||||
- value: 46.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x512_80k_ade20k
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 71.58
|
||||
inference time (ms/im):
|
||||
- value: 71.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x512_160k_ade20k
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 46.79
|
||||
inference time (ms/im):
|
||||
- value: 46.79
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x512_160k_ade20k
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 71.58
|
||||
inference time (ms/im):
|
||||
- value: 71.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 47.15
|
||||
inference time (ms/im):
|
||||
- value: 47.15
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 71.38
|
||||
inference time (ms/im):
|
||||
- value: 71.38
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: nonlocal_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 47.15
|
||||
inference time (ms/im):
|
||||
- value: 47.15
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: nonlocal_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: NonLocal
|
||||
Metadata:
|
||||
inference time (ms/im): 71.38
|
||||
inference time (ms/im):
|
||||
- value: 71.38
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x1024_40k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 95.69
|
||||
inference time (ms/im):
|
||||
- value: 95.69
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x1024_40k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 133.33
|
||||
inference time (ms/im):
|
||||
- value: 133.33
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x1024_40k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 236.97
|
||||
inference time (ms/im):
|
||||
- value: 236.97
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x1024_80k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 95.69
|
||||
inference time (ms/im):
|
||||
- value: 95.69
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x1024_80k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 133.33
|
||||
inference time (ms/im):
|
||||
- value: 133.33
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x1024_80k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 236.97
|
||||
inference time (ms/im):
|
||||
- value: 236.97
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x1024_160k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 95.69
|
||||
inference time (ms/im):
|
||||
- value: 95.69
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x1024_160k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 133.33
|
||||
inference time (ms/im):
|
||||
- value: 133.33
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x1024_160k_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 236.97
|
||||
inference time (ms/im):
|
||||
- value: 236.97
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: ocrnet_r101-d8_512x1024_40k_b8_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: ocrnet_r101-d8_512x1024_40k_b16_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 113.64
|
||||
inference time (ms/im):
|
||||
- value: 113.64
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: ocrnet_r101-d8_512x1024_80k_b16_cityscapes
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 113.64
|
||||
inference time (ms/im):
|
||||
- value: 113.64
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x512_80k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 34.51
|
||||
inference time (ms/im):
|
||||
- value: 34.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x512_80k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 52.83
|
||||
inference time (ms/im):
|
||||
- value: 52.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x512_80k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 58.86
|
||||
inference time (ms/im):
|
||||
- value: 58.86
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x512_160k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 34.51
|
||||
inference time (ms/im):
|
||||
- value: 34.51
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -235,7 +315,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x512_160k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 52.83
|
||||
inference time (ms/im):
|
||||
- value: 52.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -249,7 +334,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x512_160k_ade20k
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 58.86
|
||||
inference time (ms/im):
|
||||
- value: 58.86
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -263,7 +353,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x512_20k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 31.7
|
||||
inference time (ms/im):
|
||||
- value: 31.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -277,7 +372,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x512_20k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 50.23
|
||||
inference time (ms/im):
|
||||
- value: 50.23
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -291,7 +391,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x512_20k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 56.09
|
||||
inference time (ms/im):
|
||||
- value: 56.09
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -305,7 +410,12 @@ Models:
|
|||
- Name: ocrnet_hr18s_512x512_40k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 31.7
|
||||
inference time (ms/im):
|
||||
- value: 31.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -319,7 +429,12 @@ Models:
|
|||
- Name: ocrnet_hr18_512x512_40k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 50.23
|
||||
inference time (ms/im):
|
||||
- value: 50.23
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -333,7 +448,12 @@ Models:
|
|||
- Name: ocrnet_hr48_512x512_40k_voc12aug
|
||||
In Collection: OCRNet
|
||||
Metadata:
|
||||
inference time (ms/im): 56.09
|
||||
inference time (ms/im):
|
||||
- value: 56.09
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -10,7 +10,12 @@ Models:
|
|||
- Name: pointrend_r50_512x1024_80k_cityscapes
|
||||
In Collection: PointRend
|
||||
Metadata:
|
||||
inference time (ms/im): 117.92
|
||||
inference time (ms/im):
|
||||
- value: 117.92
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -24,7 +29,12 @@ Models:
|
|||
- Name: pointrend_r101_512x1024_80k_cityscapes
|
||||
In Collection: PointRend
|
||||
Metadata:
|
||||
inference time (ms/im): 142.86
|
||||
inference time (ms/im):
|
||||
- value: 142.86
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -38,7 +48,12 @@ Models:
|
|||
- Name: pointrend_r50_512x512_160k_ade20k
|
||||
In Collection: PointRend
|
||||
Metadata:
|
||||
inference time (ms/im): 57.77
|
||||
inference time (ms/im):
|
||||
- value: 57.77
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -52,7 +67,12 @@ Models:
|
|||
- Name: pointrend_r101_512x512_160k_ade20k
|
||||
In Collection: PointRend
|
||||
Metadata:
|
||||
inference time (ms/im): 64.52
|
||||
inference time (ms/im):
|
||||
- value: 64.52
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 315.46
|
||||
inference time (ms/im):
|
||||
- value: 315.46
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 454.55
|
||||
inference time (ms/im):
|
||||
- value: 454.55
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: psanet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 714.29
|
||||
inference time (ms/im):
|
||||
- value: 714.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: psanet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 1020.41
|
||||
inference time (ms/im):
|
||||
- value: 1020.41
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 315.46
|
||||
inference time (ms/im):
|
||||
- value: 315.46
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 454.55
|
||||
inference time (ms/im):
|
||||
- value: 454.55
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: psanet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 714.29
|
||||
inference time (ms/im):
|
||||
- value: 714.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: psanet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 1020.41
|
||||
inference time (ms/im):
|
||||
- value: 1020.41
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 52.88
|
||||
inference time (ms/im):
|
||||
- value: 52.88
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 76.16
|
||||
inference time (ms/im):
|
||||
- value: 76.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 52.88
|
||||
inference time (ms/im):
|
||||
- value: 52.88
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 76.16
|
||||
inference time (ms/im):
|
||||
- value: 76.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 54.82
|
||||
inference time (ms/im):
|
||||
- value: 54.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 79.18
|
||||
inference time (ms/im):
|
||||
- value: 79.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: psanet_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 54.82
|
||||
inference time (ms/im):
|
||||
- value: 54.82
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: psanet_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: PSANet
|
||||
Metadata:
|
||||
inference time (ms/im): 79.18
|
||||
inference time (ms/im):
|
||||
- value: 79.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
|
|
@ -12,7 +12,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x1024_40k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 245.7
|
||||
inference time (ms/im):
|
||||
- value: 245.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -26,7 +31,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x1024_40k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 373.13
|
||||
inference time (ms/im):
|
||||
- value: 373.13
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -40,7 +50,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_769x769_40k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 568.18
|
||||
inference time (ms/im):
|
||||
- value: 568.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -54,7 +69,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_769x769_40k_cityscapes
|
||||
In Collection: PSPNet
|
||||
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
|
||||
|
|
@ -68,7 +88,12 @@ Models:
|
|||
- Name: pspnet_r18-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 63.65
|
||||
inference time (ms/im):
|
||||
- value: 63.65
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -82,7 +107,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 245.7
|
||||
inference time (ms/im):
|
||||
- value: 245.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -96,7 +126,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 373.13
|
||||
inference time (ms/im):
|
||||
- value: 373.13
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -110,7 +145,12 @@ Models:
|
|||
- Name: pspnet_r18-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 161.29
|
||||
inference time (ms/im):
|
||||
- value: 161.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -124,7 +164,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 568.18
|
||||
inference time (ms/im):
|
||||
- value: 568.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -138,7 +183,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
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
|
||||
|
|
@ -152,7 +202,12 @@ Models:
|
|||
- Name: pspnet_r18b-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 61.43
|
||||
inference time (ms/im):
|
||||
- value: 61.43
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -166,7 +221,12 @@ Models:
|
|||
- Name: pspnet_r50b-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 232.56
|
||||
inference time (ms/im):
|
||||
- value: 232.56
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -180,7 +240,12 @@ Models:
|
|||
- Name: pspnet_r101b-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 362.32
|
||||
inference time (ms/im):
|
||||
- value: 362.32
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -194,7 +259,12 @@ Models:
|
|||
- Name: pspnet_r18b-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 156.01
|
||||
inference time (ms/im):
|
||||
- value: 156.01
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -208,7 +278,12 @@ Models:
|
|||
- Name: pspnet_r50b-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 531.91
|
||||
inference time (ms/im):
|
||||
- value: 531.91
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -222,7 +297,12 @@ Models:
|
|||
- Name: pspnet_r101b-d8_769x769_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 854.7
|
||||
inference time (ms/im):
|
||||
- value: 854.7
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -236,7 +316,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x512_80k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.5
|
||||
inference time (ms/im):
|
||||
- value: 42.5
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -250,7 +335,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x512_80k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 65.36
|
||||
inference time (ms/im):
|
||||
- value: 65.36
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -264,7 +354,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x512_160k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.5
|
||||
inference time (ms/im):
|
||||
- value: 42.5
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -278,7 +373,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x512_160k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 65.36
|
||||
inference time (ms/im):
|
||||
- value: 65.36
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -292,7 +392,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x512_20k_voc12aug
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.39
|
||||
inference time (ms/im):
|
||||
- value: 42.39
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -306,7 +411,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x512_20k_voc12aug
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 66.58
|
||||
inference time (ms/im):
|
||||
- value: 66.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -320,7 +430,12 @@ Models:
|
|||
- Name: pspnet_r50-d8_512x512_40k_voc12aug
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.39
|
||||
inference time (ms/im):
|
||||
- value: 42.39
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -334,7 +449,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_512x512_40k_voc12aug
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 66.58
|
||||
inference time (ms/im):
|
||||
- value: 66.58
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -348,7 +468,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 103.31
|
||||
inference time (ms/im):
|
||||
- value: 103.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -362,7 +487,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_480x480_80k_pascal_context
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 103.31
|
||||
inference time (ms/im):
|
||||
- value: 103.31
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -376,7 +506,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_480x480_40k_pascal_context
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
@ -390,7 +525,12 @@ Models:
|
|||
- Name: pspnet_r101-d8_480x480_80k_pascal_context_59
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal Context
|
||||
|
|
|
|||
|
|
@ -10,7 +10,12 @@ Models:
|
|||
- Name: fcn_s101-d8_512x1024_80k_cityscapes
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 418.41
|
||||
inference time (ms/im):
|
||||
- value: 418.41
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -24,7 +29,12 @@ Models:
|
|||
- Name: pspnet_s101-d8_512x1024_80k_cityscapes
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 396.83
|
||||
inference time (ms/im):
|
||||
- value: 396.83
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -38,7 +48,12 @@ Models:
|
|||
- Name: deeplabv3_s101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 531.91
|
||||
inference time (ms/im):
|
||||
- value: 531.91
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -52,7 +67,12 @@ Models:
|
|||
- Name: deeplabv3plus_s101-d8_512x1024_80k_cityscapes
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 423.73
|
||||
inference time (ms/im):
|
||||
- value: 423.73
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -66,7 +86,12 @@ Models:
|
|||
- Name: fcn_s101-d8_512x512_160k_ade20k
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): 77.76
|
||||
inference time (ms/im):
|
||||
- value: 77.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -80,7 +105,12 @@ Models:
|
|||
- Name: pspnet_s101-d8_512x512_160k_ade20k
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): 76.8
|
||||
inference time (ms/im):
|
||||
- value: 76.8
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -94,7 +124,12 @@ Models:
|
|||
- Name: deeplabv3_s101-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): 107.76
|
||||
inference time (ms/im):
|
||||
- value: 107.76
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -108,7 +143,12 @@ Models:
|
|||
- Name: deeplabv3plus_s101-d8_512x512_160k_ade20k
|
||||
In Collection: DeepLabV3+
|
||||
Metadata:
|
||||
inference time (ms/im): 83.61
|
||||
inference time (ms/im):
|
||||
- value: 83.61
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: fpn_r50_512x1024_80k_cityscapes
|
||||
In Collection: FPN
|
||||
Metadata:
|
||||
inference time (ms/im): 73.86
|
||||
inference time (ms/im):
|
||||
- value: 73.86
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: fpn_r101_512x1024_80k_cityscapes
|
||||
In Collection: FPN
|
||||
Metadata:
|
||||
inference time (ms/im): 97.18
|
||||
inference time (ms/im):
|
||||
- value: 97.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: fpn_r50_512x512_160k_ade20k
|
||||
In Collection: FPN
|
||||
Metadata:
|
||||
inference time (ms/im): 17.93
|
||||
inference time (ms/im):
|
||||
- value: 17.93
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: fpn_r101_512x512_160k_ade20k
|
||||
In Collection: FPN
|
||||
Metadata:
|
||||
inference time (ms/im): 24.64
|
||||
inference time (ms/im):
|
||||
- value: 24.64
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
|
|||
|
|
@ -3,7 +3,12 @@ Models:
|
|||
- Name: fcn_unet_s5-d16_64x64_40k_drive
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: DRIVE
|
||||
|
|
@ -17,7 +22,12 @@ Models:
|
|||
- Name: pspnet_unet_s5-d16_64x64_40k_drive
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: DRIVE
|
||||
|
|
@ -31,7 +41,12 @@ Models:
|
|||
- Name: deeplabv3_unet_s5-d16_64x64_40k_drive
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: DRIVE
|
||||
|
|
@ -45,7 +60,12 @@ Models:
|
|||
- Name: fcn_unet_s5-d16_128x128_40k_stare
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: STARE
|
||||
|
|
@ -59,7 +79,12 @@ Models:
|
|||
- Name: pspnet_unet_s5-d16_128x128_40k_stare
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: STARE
|
||||
|
|
@ -73,7 +98,12 @@ Models:
|
|||
- Name: deeplabv3_unet_s5-d16_128x128_40k_stare
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: STARE
|
||||
|
|
@ -87,7 +117,12 @@ Models:
|
|||
- Name: fcn_unet_s5-d16_128x128_40k_chase_db1
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: CHASE_DB1
|
||||
|
|
@ -101,7 +136,12 @@ Models:
|
|||
- Name: pspnet_unet_s5-d16_128x128_40k_chase_db1
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: CHASE_DB1
|
||||
|
|
@ -115,7 +155,12 @@ Models:
|
|||
- Name: deeplabv3_unet_s5-d16_128x128_40k_chase_db1
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: CHASE_DB1
|
||||
|
|
@ -129,7 +174,12 @@ Models:
|
|||
- Name: fcn_unet_s5-d16_256x256_40k_hrf
|
||||
In Collection: FCN
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: HRF
|
||||
|
|
@ -143,7 +193,12 @@ Models:
|
|||
- Name: pspnet_unet_s5-d16_256x256_40k_hrf
|
||||
In Collection: PSPNet
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: HRF
|
||||
|
|
@ -157,7 +212,12 @@ Models:
|
|||
- Name: deeplabv3_unet_s5-d16_256x256_40k_hrf
|
||||
In Collection: DeepLabV3
|
||||
Metadata:
|
||||
inference time (ms/im): None
|
||||
inference time (ms/im):
|
||||
- value: None
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: HRF
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ Models:
|
|||
- Name: upernet_r50_512x1024_40k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 235.29
|
||||
inference time (ms/im):
|
||||
- value: 235.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -25,7 +30,12 @@ Models:
|
|||
- Name: upernet_r101_512x1024_40k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 263.85
|
||||
inference time (ms/im):
|
||||
- value: 263.85
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -39,7 +49,12 @@ Models:
|
|||
- Name: upernet_r50_769x769_40k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 568.18
|
||||
inference time (ms/im):
|
||||
- value: 568.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -53,7 +68,12 @@ Models:
|
|||
- Name: upernet_r101_769x769_40k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 641.03
|
||||
inference time (ms/im):
|
||||
- value: 641.03
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -67,7 +87,12 @@ Models:
|
|||
- Name: upernet_r50_512x1024_80k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 235.29
|
||||
inference time (ms/im):
|
||||
- value: 235.29
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -81,7 +106,12 @@ Models:
|
|||
- Name: upernet_r101_512x1024_80k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 263.85
|
||||
inference time (ms/im):
|
||||
- value: 263.85
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -95,7 +125,12 @@ Models:
|
|||
- Name: upernet_r50_769x769_80k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 568.18
|
||||
inference time (ms/im):
|
||||
- value: 568.18
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -109,7 +144,12 @@ Models:
|
|||
- Name: upernet_r101_769x769_80k_cityscapes
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 641.03
|
||||
inference time (ms/im):
|
||||
- value: 641.03
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Cityscapes
|
||||
|
|
@ -123,7 +163,12 @@ Models:
|
|||
- Name: upernet_r50_512x512_80k_ade20k
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.74
|
||||
inference time (ms/im):
|
||||
- value: 42.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -137,7 +182,12 @@ Models:
|
|||
- Name: upernet_r101_512x512_80k_ade20k
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 49.16
|
||||
inference time (ms/im):
|
||||
- value: 49.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -151,7 +201,12 @@ Models:
|
|||
- Name: upernet_r50_512x512_160k_ade20k
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 42.74
|
||||
inference time (ms/im):
|
||||
- value: 42.74
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -165,7 +220,12 @@ Models:
|
|||
- Name: upernet_r101_512x512_160k_ade20k
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 49.16
|
||||
inference time (ms/im):
|
||||
- value: 49.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: ADE20K
|
||||
|
|
@ -179,7 +239,12 @@ Models:
|
|||
- Name: upernet_r50_512x512_20k_voc12aug
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 43.16
|
||||
inference time (ms/im):
|
||||
- value: 43.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -193,7 +258,12 @@ Models:
|
|||
- Name: upernet_r101_512x512_20k_voc12aug
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 50.05
|
||||
inference time (ms/im):
|
||||
- value: 50.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -207,7 +277,12 @@ Models:
|
|||
- Name: upernet_r50_512x512_40k_voc12aug
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 43.16
|
||||
inference time (ms/im):
|
||||
- value: 43.16
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
@ -221,7 +296,12 @@ Models:
|
|||
- Name: upernet_r101_512x512_40k_voc12aug
|
||||
In Collection: UPerNet
|
||||
Metadata:
|
||||
inference time (ms/im): 50.05
|
||||
inference time (ms/im):
|
||||
- value: 50.05
|
||||
hardware: V100
|
||||
backend: PyTorch
|
||||
batch size: 1
|
||||
mode: FP32
|
||||
Results:
|
||||
- Task: Semantic Segmentation
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
|
|
|
|||
Loading…
Reference in New Issue