Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

中文文本分类实践，基于搜狗新闻语料库，采用传统机器学习方法以及预训练模型等方法

PyTorch implementation of the CVPR 2019 paper “Pyramid Feature Attention Network for Saliency Detection”

PyTorch implementation of Darknet53

Pretrained SimCLRv2 models in Pytorch

Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

Pytorch implementation of Noisy Student Training for Automatic Speech Recognition and Automatic Pronunciation Error Detection problem

Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available

This is an Image Super Resolution model implemented in python using keras. This model comes with a GUI to allow users to make use of the model easily.

自监督目标检测。针对目标检测任务，提出无需标签数据的自监督算法预训练 backbone，检测性能优于有标签的预训练。

DenseCL + regionCL-D

This GitHub repository contains converted models in ONNX, TensorRT, and PyTorch formats, along with inference scripts and demos. These models can be used for efficient deployment and inference in machine learning applications.

Xception V1 model in Tensorflow with pretrained weights on ImageNet

Code and data for the paper "Pretrained Language Models are Symbolic Mathematics Solvers too!", arXiv:2110.03501

Extract features and bounding boxes using the original Bottom-up Attention Faster-RCNN in a few lines of Python code

基于 torchvision 编写的针对 COCO 数据集的 Faster-RCNN 快速训练与推理框架，支持多 batchsize。

使用自己的tokenizer继续预训练大语言模型。

keras implementation of unet & vnet