Pretrained Weights Python Packages

timm

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

segmentation-models-pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

image-classifiers

Classification models trained on ImageNet. Keras.

ptlflow

PyTorch Lightning Optical Flow models, scripts, and pretrained weights.

yolov3-pytorch

Pytorch implements yolov3.Good performance, easy to use, fast speed.

d3m-segmentation-models-pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

segmentation-models-pytorch-deepflash2

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

fight-detection

Fight Detection From Surveillance Cameras by fine-tuning a PyTorch Pretrained Model

timm-ctp

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

jaxnn

Foundation models in JAX/Flax

feight-detection-from-surveillance-cameras

Fight Detection From Surveillance Cameras by fine-tuning a PyTorch Pretrained Model

nbdt

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

timm-clean

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

segmentation-sust

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

timm-eidl

PyTorch Image Models

instances

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