#transformer Repositories
208 repositories total
Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
Deep Learning introductory courses, advanced courses, featured courses, academic cases, industry practice cases, deep learning knowledge encyclopedia and interview question bank The course, case and knowledge of Deep Learning and AI
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2, ...)
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!
we want to create a repo to illustrate usage of transformers in chinese
Covers pre-training data, Tokenizers, Transformers, MoE, distributed training, scaling laws, inference, and alignment. 6 progressive coding assignments for full-stack LLM learning.
๐ฅ๐ฅ๐ฅ Focusing on YOLO11, YOLOv8, TYOLOv12, YOLOv10, RT-DETR, YOLOv7, YOLOv5 improved models, Support to improve backbone, neck, head, loss, IoU, NMS and other modules๐
A professionally curated list of awesome resources (paper, code, data, etc.) on transformers in time series.
A computer vision closed-loop learning platform where code can be run interactively online. Learning closed-loop "Computer Vision in Action: Algorithms and Applications" Chinese ebook, source code, reader exchange community (continuously updating...) ๐ Online ebook https://charmve.github.io/computer-vision-in-action/ ๐Project homepage
Research papers and blogs to transition to AI Engineering
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
Graphormer is a general-purpose deep learning backbone for molecular modeling.
Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BER
๐ ๐ ๐ YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
๐ฐ Must-read papers and blogs on LLM based Long Context Modeling ๐ฅ
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
QuantMind (Quantitative Brain) Open Source Edition is an AI-native, multi-market quantitative trading platform designed for individual developers and quantitative research and investment teams. It deeply integrates Microsoft Qlib, RD-Agent factor evolution, and the all-in-one QuantBot Workbench, providing a complete closed loop covering the mining of 300+ dimensional factors, a model factory with 13 machine learning and deep learning models, high-performance Qlib backtesting, batch cross-sectional inference, 24/7 real-time public-opinion sentiment analysis, deep integration with TongdaXin (sector push notifications, alert radar, and lightning order placement), and live and simulated trading. It supports A-shares, Hong Kong stocks, U.S. stocks, futures, and blockchain. It is free for commercial use and can be deployed privately with a single click using Docker Compose. Data and models are fully localized to safeguard strategy privacy, with all features available without entry barriers or limitations.
Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project
A curated list of Graph/Transformer-based fraud, anomaly, and outlier detection papers & resources
An Easy-to-Use and High-Performance AI Deployment Framework | An Easy-to-Use and High-Performance AI Deployment Framework
Chinese long text classification, short sentence classification, multi-label classification, two-sentence similarity (Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short), character/word/sentence vector embedding layer (embeddings) and network layer (graph) construction base class, FastText, TextCNN, CharCNN, TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, Capsule Network-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN
Import SVG files in your React Native project the same way that you would in a Web application.
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. ๐ 28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc. have been implemented so far. ๐ Trained models, training logs, and configurations are available to ensure reproducibility and benchmarking.
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
PaddleSlim is an open-source library for deep model compression and architecture search.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.