The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.
-
Updated
May 4, 2024 - Python
The Pytorch implementation of sound classification supports EcapaTdnn, PANNS, TDNN, Res2Net, ResNetSE and other models, as well as a variety of preprocessing methods.
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
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.
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
PyTorch-based framework for high-level development of image models. Customize your model with combinations and replacement on classification / detection modules.
Res2Net for Pose Estimation using Simple Baselines as the baseline
Res2Net for Instance segmentation and Object detection using MaskRCNN
Res2Net for Panoptic Segmentation based on detectron2 (SOTA results).
Implement a few key architectures for image classification by using neural network
Add a description, image, and links to the res2net topic page so that developers can more easily learn about it.
To associate your repository with the res2net topic, visit your repo's landing page and select "manage topics."