面向产业应用的AI开源评测基准
Repositories
daquexian repositories
AndroidRate is a library to help you promote your Android app by prompting users to rate the app after using it for a few days.
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
real time face swap and one-click video deepfake with only a single image (uncensored)
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
AndroidFlux+Retrofit+RxJava+Dagger2
Firebase Cloud Messaging for Mojo-Webqq.
A view showing LaTeX, images, codes... You can customize tags as you want
MNN is a lightweight deep neural network inference engine.
Multi-platform high performance deep learning inference engine (飞桨多端多平台高性能深度学习推理引擎)
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
The friendly PIL fork (Python Imaging Library)
TNN:由腾讯优图实验室打造,移动端高性能、轻量级推理框架,同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化,同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地,欢迎大家参与协同共建,促进TNN推理框架进一步完善。
Tengine is a lite, high performance, modular inference engine for embedded device
Tengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Asynchronous linting/fixing for Vim and Language Server Protocol (LSP) integration
Files received in QQ, telegram, or images downloaded in WeChat, will all appear in download manager
Android NDK samples with Android Studio