mirror of
https://github.com/open-mmlab/mmpretrain.git
synced 2025-06-03 14:59:18 +08:00
7977dc8e2d
* Update tnt config * Rename config files * Update docs * Update metafile in dev_scripts * Fix some files * Remove fp16 metafile and README. * Fix names in metafiles.
43 lines
1.3 KiB
YAML
43 lines
1.3 KiB
YAML
Collections:
|
|
- Name: MobileNet V3
|
|
Metadata:
|
|
Training Data: ImageNet-1k
|
|
Training Techniques:
|
|
- RMSprop with Momentum
|
|
- Weight Decay
|
|
Training Resources: 8x V100 GPUs
|
|
Epochs: 600
|
|
Batch Size: 1024
|
|
Architecture:
|
|
- MobileNet V3
|
|
Paper: https://arxiv.org/abs/1905.02244
|
|
README: configs/mobilenet_v3/README.md
|
|
|
|
Models:
|
|
- Name: mobilenet_v3_small_imagenet
|
|
Metadata:
|
|
FLOPs: 60000000
|
|
Parameters: 2540000
|
|
In Collection: MobileNet V3
|
|
Results:
|
|
- Dataset: ImageNet-1k
|
|
Metrics:
|
|
Top 1 Accuracy: 67.66
|
|
Top 5 Accuracy: 87.41
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_small-8427ecf0.pth
|
|
Config: configs/mobilenet_v3/mobilenet-v3-small_8xb32_in1k.py
|
|
- Name: mobilenet_v3_large_imagenet
|
|
Metadata:
|
|
FLOPs: 230000000
|
|
Parameters: 5480000
|
|
In Collection: MobileNet V3
|
|
Results:
|
|
- Dataset: ImageNet-1k
|
|
Metrics:
|
|
Top 1 Accuracy: 74.04
|
|
Top 5 Accuracy: 91.34
|
|
Task: Image Classification
|
|
Weights: https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_large-3ea3c186.pth
|
|
Config: configs/mobilenet_v3/mobilenet-v3-large_8xb32_in1k.py
|