(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.

PyTorch implementation of Res2Net

Res2Net for Instance segmentation and Object detection using MaskRCNN

基于PaddlePaddle实现的音频分类，支持EcapaTdnn、PANNS、TDNN、Res2Net、ResNetSE等各种模型，还有多种预处理方法

Res2Net for Panoptic Segmentation based on detectron2 (SOTA results).

ImageNet training code of Res2Net

Res2Net for Pose Estimation using Simple Baselines as the baseline

Unofficial implementation of the Res2Net module in pytorch

Use pytorch to implement some classifer network

Implement a few key architectures for image classification by using neural network

The mxnet implemention of the paper Res2Net with gluon interface.

PyTorch-based framework for high-level development of image models. Customize your model with combinations and replacement on classification / detection modules.

This project partially embodies the state-of-the-art practices in speaker verification technology up until 2020, while attaining the state-of-the-art performance on the VoxCeleb1 test sets.

Modular framework for developing image models based on PyTorch. Customize your model with combinations and replacement on classification / detection modules.