heivens
Follow
Stars
AI桌宠2.2（网页端toklen白嫖国产大模型服务器（glm4，kimi，deepseekv2），语音识别，屏幕识别自动发送，live2d 2.0和3.0模型，gpt-sovits语音，coysvoice语音，edge-tts语音（支持多语言音色），本地ollama模型无限制聊天）（主流国产大模型api接口支持）
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
deploy the YOLO model on C++ with Opencv4.8 or onnxruntime
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.
Python implementation of Poisson image editing
An implementation of gradient domain blending for images
Simple pytorch implementation of focal loss
Non-Maximum Suppression for Object Detection in Python
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Effortless data labeling with AI support from Segment Anything and other awesome models.
Included the standard NMS, Rotate NMS，standard SoftNMS, Rotate SoftNMS, Weighted NMS, Rotate Weighted NMS, Weighted-Boxes-Fusion, Rotate Weighted-Boxes-Fusion
This library reads and writes ESRI Shapefiles in pure Python.
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the i…
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
[ECCV 2022] Flow-Guided Transformer for Video Inpainting
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
the code of the mulit-instance multi-label algorithm proposed in Multi-instance Multi-label Learning Based on Parallel Attention and Local Label Manifold Correlation
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Pytorch implementation of three Multiple Instance Learning or Multi-classification papers
A Keras implementation of the DeepMIML Network for multi-instance multi-label learning