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.

ptlflow

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

image-classifiers

Classification models trained on ImageNet. Keras.

frbench

An easy-to-use, end-to-end differentiable face-recognition module that ships 45+ pretrained weights, covering 25 backbones, 9 loss functions, and 3 training datasets spanning generations since 2015.

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

fight-detection

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

jaxnn

JaxNN: Foundation Models in JAX/Flax

feight-detection-from-surveillance-cameras

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

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-models-pytorch-deepflash2

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

d3m-segmentation-models-pytorch

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

nbdt

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

yolov3-pytorch

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

timm-eidl

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.