69 lines
2.2 KiB
YAML
69 lines
2.2 KiB
YAML
Collections:
|
|
- Name: ResNeXt
|
|
Metadata:
|
|
Training Data: ImageNet
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Resources: 8x V100 GPUs
|
|
Epochs: 100
|
|
Batch Size: 256
|
|
Architecture:
|
|
- ResNeXt
|
|
Paper: https://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html
|
|
README: configs/resnext/README.md
|
|
|
|
Models:
|
|
- Config: configs/resnext/resnext50_32x4d_b32x8_imagenet.py
|
|
In Collection: ResNeXt
|
|
Metadata:
|
|
FLOPs: 4270000000
|
|
Parameters: 25030000
|
|
Name: resnext50_32x4d_b32x8_imagenet
|
|
Results:
|
|
- Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 77.92
|
|
Top 5 Accuracy: 93.74
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_batch256_imagenet_20200708-c07adbb7.pth
|
|
- Config: configs/resnext/resnext101_32x4d_b32x8_imagenet.py
|
|
In Collection: ResNeXt
|
|
Metadata:
|
|
FLOPs: 8030000000
|
|
Parameters: 44180000
|
|
Name: resnext101_32x4d_b32x8_imagenet
|
|
Results:
|
|
- Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 78.7
|
|
Top 5 Accuracy: 94.34
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_batch256_imagenet_20200708-87f2d1c9.pth
|
|
- Config: configs/resnext/resnext101_32x8d_b32x8_imagenet.py
|
|
In Collection: ResNeXt
|
|
Metadata:
|
|
FLOPs: 16500000000
|
|
Parameters: 88790000
|
|
Name: resnext101_32x8d_b32x8_imagenet
|
|
Results:
|
|
- Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 79.22
|
|
Top 5 Accuracy: 94.52
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_batch256_imagenet_20200708-1ec34aa7.pth
|
|
- Config: configs/resnext/resnext152_32x4d_b32x8_imagenet.py
|
|
In Collection: ResNeXt
|
|
Metadata:
|
|
FLOPs: 11800000000
|
|
Parameters: 59950000
|
|
Name: resnext152_32x4d_b32x8_imagenet
|
|
Results:
|
|
- Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 79.06
|
|
Top 5 Accuracy: 94.47
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_batch256_imagenet_20200708-aab5034c.pth
|