MogaNet-ImageNet-Weights
·
27 commits
to main
since this release
A collection of args.yaml, summary.csv, and model.pth.tar for image classification experiments of MogaNet on ImageNet-1K (download). You can download all files from Baidu Cloud: MogaNet (z8mf) at MogaNet/Classification_MogaNet.
- We reproduce the results of MogaNet for 300-epoch training according to the DeiT setting on ImageNet-1K in TRAINING.md. Refer to OpenMixup for more image classification results.
- The best top-1 accuracy of image classification of 3 trials is reported for all experiments. Note that we report the classification accuracy of EMA weights for MogaNet-S, MogaNet-B, and MogaNet-L (please evaluate their EMA models).
- To evaluate the pre-trained weights, use
validate.pywith scripts for the classification performance.
Image Classification on ImageNet-1K
| Model | resolution | Params | Flops | Top-1 (%) | Top-5 (%) | Config | Download |
|---|---|---|---|---|---|---|---|
| MogaNet-XT | 224x224 | 2.97M | 0.80G | 76.5 | 93.4 | args / config / script | model / log |
| MogaNet-T | 224x224 | 5.20M | 1.10G | 79.0 | 94.6 | args / config / script | model / log |
| MogaNet-T | 256x256 | 5.20M | 1.44G | 79.6 | 94.9 | args / config / script | model / log |
| MogaNet-S | 224x224 | 25.3M | 4.97G | 83.4 | 96.9 | args / config / script | model / log |
| MogaNet-B | 224x224 | 43.9M | 9.93G | 84.3 | 97.0 | args / config / script | model / log |
| MogaNet-L | 224x224 | 82.5M | 15.9G | 84.7 | 97.1 | args / config / script | model / log |
| MogaNet-XL | 224x224 | 180.8M | 34.5G | 85.1 | 97.4 | args / config / script | model / log |