1.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 morepytorchresnetpretrained-modelspretrained-weightsdistributed-trainingmobile-deep-learning+14 morePythonAPACHE-2.037K total5.2K forks+703 starsfrom 36,560 · score 6.56
2.qubvel-org / segmentation_models.pytorchSemantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.segmentationimage-processingpspnetunetunet-pytorchpytorch+14 morePythonMIT12K total1.9K forks+332 starsfrom 11,459 · score 5.81