There are 3 repositories under pretrained-weights topic.
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.
Pretrained TorchVision models on CIFAR10 dataset (with weights)
YOLOv3 implementation in TensorFlow 2.3.1
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)
Code for "Real-time self-adaptive deep stereo" - CVPR 2019 (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.
An Out-of-the-Box Replication of GANimation using PyTorch, pretrained weights are available!
A Beautiful Flask Web API for Yolov7 (and custom) models
https://towardsdatascience.com/tutorial-build-an-object-detection-system-using-yolo-9a930513643a
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.
Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)
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.
Address book for computer vision models.
An implementation of MobileNetV3 with pyTorch
Pytorch EfficientNetV2 EfficientNetV1 with pretrained weights
Multi-label classification based on timm, and add SimCLR to timm.
Pytorch implements yolov3.Good performance, easy to use, fast speed.
A Pytorch implementation of the 2017 Huang et. al. paper "Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization"
Fight Detection From Surveillance Cameras by fine-tuning a PyTorch Pretrained Model
Concise, Modular, Human-friendly PyTorch implementation of EfficientNet with Pre-trained Weights.
Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".
TensorFlow version of SqueezeNet with converted pretrained weights
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.
This project shows Image Super Resolution using Deep Learning . Seven models are implemented SRCNN, FSRCNN,ESPCN, RDN, RFDN, Autoencoder and ESRGAN.
A deep learning model built to detect cataract in human eyes using the VGG-19 pretrained weights
Tensorflow implementations of ConvNeXt V1 + V2 models w/ weights, including conversion and evaluation scripts.