机器学习 · GitHub

AI实战-practicalAI 中文版

用于训练大型多模态模型的开源框架。

An implementation of the BERT model and its related downstream tasks based on the PyTorch framework. @跟我学机器学习

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

• Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).
• Speaker Encoder to compute speaker embeddings efficiently.

Transformer related optimization, including BERT, GPT

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

StyleGAN2 - Official TensorFlow Implementation

StyleGAN2-ADA - Official PyTorch implementation

Official PyTorch implementation of StyleGAN3

xLSTM as Generic Vision Backbone

OpenMMLab 多模态高级、生成式与智能创作工具箱。解锁魔法 🪄：生成式 AI（AIGC）、易用的 API、出色的模型库、扩散模型，适用于文本生成图像以及图像与视频的修复和增强等。

• State of the Art Models MMagic provides state-of-the-art generative models to process, edit and synthesize images and videos.

《Machine Learning Systems: Design and Implementation》（V2 即将发布）

LLM agents as your hyperparameter optimizer.

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

• LoRA LoRA is a parameter-efficient finetuning algorithm and is more efficient than full finetuning. Check out finetuning-lora for more details.
• FlashAttention LMFlow supports both FlashAttention-1 and the latest FlashAttention-2. Check out flash_attention for more details.

基于条件对抗网络的图像到图像转换

Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

🔥 A library for cropping image in a smart way that can identify the border and correct the cropped image. 智能图片裁剪框架。自动识别边框，手动调节选区，使用透视变换裁剪并矫正选区；适用于身份证，名片，文档等照片的裁剪。

• CropImageView 选区放大镜效果
• CropImageView xml属性配置

A powerful tool that translates ComfyUI workflows into executable Python code.