deep-learning

Implementation of Danijar's latest iteration for his Dreamer line of work

A curated, comprehensive collection of open-source AI tools, frameworks, datasets, courses, and seminal papers.

Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks.

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Train very large language models in Jax.

Collection of Tools and Papers related to Adapters / Parameter-Efficient Transfer Learning/ Fine-Tuning

medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat pipeline.

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

Official implementation of 'Transformer-VQ: Linear-Time Transformers via Vector Quantization' (ICLR 2024)

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.

Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model

Collection of free Notes,Courses,Videos,Projects,Articles and Repos Links To learn Machine learning ,Deep learning,Python,SQL,CNN,NLP,GAN,GNN,Transfomers,Flask,Django,and End to End Machine learning Projects

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

[ACM TOMM 2023] - Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features

Explore LangChain and build powerful chatbots that interact with your own data. Gain insights into document loading, splitting, retrieval, question answering, and more.

[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation

DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022

A codebase that makes differentially private training of transformers easy.