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
31.94k stars 4.73k forks source link

Adding ParC-Net in Timm #1459

Closed hkzhang-git closed 2 years ago

hkzhang-git commented 2 years ago

Is your feature request related to a problem? Please describe. Is there a plan for adding ParC-Net as part of timm library?

ParC-Net is a pure-conv version of MobileViT, which has better performance than MobileViT v1 and v2.

Describe the solution you'd like Code is available at: https://github.com/hkzhang91/ParC-Net. I am anticipating your reply.

rwightman commented 2 years ago

duplicate of #1395 , not on my priority list right now, just did a batch of models and have other things to focus on, will look at PR if one is submitted that passes all tests, etc