Apprentissage automatique · GitHub

Materials for following along with Hands-On Data Analysis with Pandas – Second Edition

AI-powered, camera-based mouse cursor control written in C++. Turn your webcam into a hands-free pointing device — built for gaming, perfect for everyday use and accessibility.

A framework for unified end-to-end autonomous driving datasets processing

• Unified Dataset Interface: Work with multiple datasets through a single API
• Multimodal Support: Cameras, LiDAR (point cloud + BEV histogram), HD maps (BEV raster), trajectories, detections and more

Various Algorithms for Short Text Mining

ZED SDK Unity plugin

Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN

Arabic to English machine translation with Transformers and Pytorch

Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow

NLP tokenizers written in Go language

• Post-processing
• Word level model

Unofficial implementation of ZipNeRF

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

• 🔥 3.93% improved zero-shot ImageNet classification accuracy when providing foreground alpha-map.
• 🔥 Plug-in and play with region focus in any work that use CLIP vision encoder.

Implementation of Chinese ChatGPT

• LLM模型预训练：支持常见模型的预训练，包括：decoder结构（LLaMA、GPT）、encoder结构（GLM）
• LLM模型评测：参考GPT类模型，基于ZeroShot和FewShot实现

Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779