머신러닝 · GitHub

AI book for everyone

Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.

Machine Learning algorithms in pure Mojo 🔥

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

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

:orange_book:慢慢整理所学的机器学习算法，并根据自己所理解的样子叙述出来。(注重数学推导)

pytorch version of neural collaborative filtering

Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]

Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"

该仓库用于构建自托管的12306验证码识别服务器

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021

The Tensorflow, Keras implementation of U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET with optional ImageNet-trained backbones.

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

For beginner, this will be the best start for VAEs, GANs, and CVAE-GAN. This contains AE, DAE, VAE, GAN, CGAN, DCGAN, WGAN, WGAN-GP, VAE-GAN, CVAE-GAN. All use PyTorch.

DenseNet Implementation in Tensorflow

pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...

PyTorch implementation of Image Super-Resolution Using Deep Convolutional Networks (ECCV 2014)

Learning to Cluster Faces (CVPR 2019, CVPR 2020)