12 skills found
huggingface / Pytorch Image ModelsThe 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
leondgarse / Keras Cv Attention ModelsKeras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam
google-research / Maxvit[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...
ChristophReich1996 / MaxViTPyTorch reimplementation of the paper "MaxViT: Multi-Axis Vision Transformer" [ECCV 2022].
ZFTurbo / Timm 3dPyTorch Volume Models for 3D data
anpc849 / QMaxViT UnetQMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images
qwopqwop200 / MaxVIT PytorchMaxVIT implementation(MaxViT: Multi-Axis Vision Transformer) This is an unofficial implementation. https://arxiv.org/abs/2204.01697
RooKichenn / Pytorch MaxViTpytorch实现MaxViT，可以在ImageNet或自己的数据集上训练，支持apex混合精度，各种图像增强技术
hankyul2 / Maxvit Pytorch[ECCV 2022] unofficial pytorch implementation of the paper "MaxViT: Multi-Axis Vision Transformer"
nengwp / 3D MaxViT PytorchExtending MaxViT (Multi-Axis Vision Transformer) to 3D Space
pablo-reyes8 / Outgrid Vision TransformerHybrid vision backbone: VOLO-style Outlook local mixing + MaxViT grid attention + MBConv. Two variants (front-only vs per-block Outlook), FP16 training CLI with CutMix, and reproducible CIFAR-100 64×64 benchmarks.
pablo-reyes8 / Multiscale Vision TransformersMultiScale Vision Transformers: hands-on lab for Hierarchical ViT, Swin, MaxViT & VOLO with a shared CIFAR-100 pipeline (loaders + train/eval CLIs), plus Docker and pytest for fast, reproducible, side-by-side comparisons.
