[FEATURE] When would you consider adding MLP-Mixer model?

huggingface / pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

https://huggingface.co/docs/timm

Apache License 2.0

32.18k stars 4.75k forks source link

[FEATURE] When would you consider adding MLP-Mixer model? #639

Closed jikerWRN closed 3 years ago

jikerWRN commented 3 years ago

Is your feature request related to a problem? Please describe. When would you consider adding MLP-Mixer model?

Describe the solution you'd like A model that can load pretrained model or not.

rwightman commented 3 years ago

@jikerWRN It's already there with converted weights