an Android app for deeplearning
(3 stars) (3 forks) (0 indexed issues) (0 open good first issues)
Repositories
lucasjinreal repositories
DeepMimic support tensorflow 2.8
(3 stars) (0 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/EODPython
Easy and Efficient Object Detector
(1 star) (0 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/FCOSPython
FCOS: Fully Convolutional One-Stage Object Detection
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
Transformer related optimization, including BERT, GPT
(0 stars) (0 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/FastestDetPython
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
(2 stars) (0 forks) (0 indexed issues) (0 open good first issues)
financial analysis with python
(2 stars) (0 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/FlashMLLMPython
Quantization and Fast Inference of MLLMs, such as LLaVA, SparkTTS etc.
(10 stars) (0 forks) (0 indexed issues) (0 open good first issues)
detectron2 support self-define data train
(49 stars) (16 forks) (0 indexed issues) (0 open good first issues)
An Edit Version of darknet, and this version you can train and predict on your own datasets! more easily!
(14 stars) (5 forks) (0 indexed issues) (0 open good first issues)
Clustered Forward/Deferred renderer with Physically Based Shading, Image Based Lighting and a whole lot of OpenGL.
(1 star) (0 forks) (0 indexed issues) (0 open good first issues)
imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video.
(40 stars) (0 forks) (0 indexed issues) (0 open good first issues)
🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.
(785 stars) (105 forks) (4 indexed issues) (4 open good first issues)
LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
(39 stars) (2 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/LSTM_learnPython
a implement of LSTM using Keras for time series prediction regression problem
(225 stars) (135 forks) (0 indexed issues) (0 open good first issues)
支持更多中文大模型的langchain助手
(2 stars) (0 forks) (0 indexed issues) (0 open good first issues)
lucasjinreal/LightNetPython
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
lucasjinreal/MICAPython
MICA - Towards Metrical Reconstruction of Human Faces (ECCV 2022)
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series models.
(19 stars) (0 forks) (0 indexed issues) (0 open good first issues)
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
(1 star) (0 forks) (0 indexed issues) (0 open good first issues)