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

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

Classification models trained on ImageNet. Keras.

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

Pretrained TorchVision models on CIFAR10 dataset (with weights)

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

YOLOv3 implementation in TensorFlow 2.3.1

Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)

A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.

Code for "Real-time self-adaptive deep stereo" - CVPR 2019 (ORAL)

An Out-of-the-Box Replication of GANimation using PyTorch, pretrained weights are available!

Top 1 solution of Chexpert

A Beautiful Flask Web API for Yolov7 (and custom) models

https://towardsdatascience.com/tutorial-build-an-object-detection-system-using-yolo-9a930513643a

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)

A native Tensorflow implementation of semantic segmentation according to Multi-Scale Context Aggregation by Dilated Convolutions (2016). Optionally uses the pretrained weights by the authors.

Pretrained is the most complete and frequently updated list of pretrained top-performing models. Tensorflow, Theano and others. Want to add your model? File an issue, and we will add it.

Multi-label classification based on timm.

C++ trainable detection library based on libtorch (or pytorch c++). Yolov4 tiny provided now.

End-to-End Vietnamese Speech Recognition using wav2vec 2.0