Stars
Examples and guides for using the OpenAI API
🔊 Text-Prompted Generative Audio Model
A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)
LangGPT: Empowering everyone to become a prompt expert! 🚀 📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者 📌 最流行的提示词落地范式 | Language of GPT The pioneering framework for structured & meta-prompt…
Book_1_《编程不难》 | 鸢尾花书：从加减乘除到机器学习；请多多批评指正！
【🔞🔞🔞 内含不适合未成年人阅读的图片】基于我擅长的编程、绘画、写作展开的 AI 探索和总结：StableDiffusion 是一种强大的图像生成模型，能够通过对一张图片进行演化来生成新的图片。ChatGPT 是一个基于 Transformer 的语言生成模型，它能够自动为输入的主题生成合适的文章。而 Github Copilot 是一个智能编程助手，能够加速日常编程活动。
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Quantitative research and educational materials
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.
Implementations of CNNs, RNNs, GANs, etc
Use Tensorflow to run CNN for predict stock movement. Hope to find out which pattern will follow the price rising.
Deep Learning and Unsupervised Feature Learning Tutorial Solutions
tensorflow学习笔记，来源于电子书：《Tensorflow实战Google深度学习框架》
中文文本错别字检测以及自动纠错 / Autochecker & autocorrecter for chinese
Official ImageNet Model repository
InfiniteBoost: building infinite ensembles with gradient descent
Analysis of High Frequency Trading on Bitcoin exchanges
A collection of analysis, and machine learning techniques for time series forecasting w/ Prometheus metrics
ClaSPy: A Python package for time series segmentation.
2019年大创项目和2019年新苗人才计划项目，针对翻拍的图片进行检测与识别，主要使用lbp算法，前期准确率在80.08%左右，后不断扩大优化图片数据库，准确率提升到97.4%结题。