Spaces:
Runtime error
A newer version of the Gradio SDK is available:
5.27.1
Download the pretrained checkpoints
To facilitate the model training, we also provide some checkpoints that are pretrained on ImageNet.
After downloading the desired pretrained checkpoint, remember to update
the initial_checkpoint path in the config files.
Checkpoints
Simple Training Strategy: This training strategy yields a similar performance to the original ResNet paper [2].
| Backbone | Pretrained Dataset |
|---|---|
| ResNet-50 (initial_checkpoint) | ImageNet-1K |
Strong Training Strategy: This training strategy additionally employs AutoAugment [3], label-smoothing [4], and drop-path [5], yielding a stronger performance on ImageNet than the original ResNet paper [2].
| Backbone | Pretrained Dataset |
|---|---|
| ResNet-50 (initial_checkpoint) | ImageNet-1K |
| ResNet-50-Beta (initial_checkpoint) | ImageNet-1K |
| Wide-ResNet-41 (initial_checkpoint) | ImageNet-1K |
| SWideRNet-SAC-(1, 1, 1) (initial_checkpoint) | ImageNet-1K |
| SWideRNet-SAC-(1, 1, 3) (initial_checkpoint) | ImageNet-1K |
| SWideRNet-SAC-(1, 1, 4.5) (initial_checkpoint) | ImageNet-1K |
| Axial-SWideRNet-(1, 1, 1) (initial_checkpoint) | ImageNet-1K |
| Axial-SWideRNet-(1, 1, 3) (initial_checkpoint) | ImageNet-1K |
| Axial-SWideRNet-(1, 1, 4.5) (initial_checkpoint) | ImageNet-1K |
| MaX-DeepLab-S-Backbone (initial_checkpoint) | ImageNet-1K |
| MaX-DeepLab-L-Backbone (initial_checkpoint) | ImageNet-1K |
References
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. "ImageNet Large Scale Visual Recognition Challenge". IJCV, 2015.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep residual learning for image recognition. In CVPR, 2016.
Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc V Le. "Autoaugment: Learning augmentation policies from data". In CVPR, 2019.
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. "Rethinking the inception architecture for computer vision." In CVPR, 2016.
Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, and Kilian Q Weinberger. "Deep networks with stochastic depth." In ECCV, 2016.