Trick or ResNet Treat
β’
3
timm
model to use before commiting to download or training with a large dataset? Try mini-imagenet:
timm/mini-imagenet diffusers
π§¨bistandbytes
as the official backend but using others like torchao
is already very simple. enable_model_cpu_offload()
timm
release (1.0.11) is out now. A also wrote an article on one of the included models: https://huggingface.co/blog/rwightman/mambaoutpip install gradio --pre
sdk_version
to be 5.0.0b3
in the README.md
file on Spaces.progress=gr.Progress(track_tqdm=True)
)timm
leaderboard
timm/leaderboard has been updated with the ability to select different hardware benchmark sets: RTX4090, RTX3090, two different CPUs along with some NCHW / NHWC layout and torch.compile (dynamo) variations.