waifu2x converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

RealSR super resolution implemented with ncnn library

RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library

real-cugan converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan

A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion

DAIN, Depth-Aware Video Frame Interpolation implemented with ncnn library

SRMD super resolution implemented with ncnn library

The Upscayl backend powered by the NCNN framework and Real-ESRGAN architecture.

加入关键点的darknet训练框架，轻量级的人脸检测，支持ncnn推理

CAIN, Channel Attention Is All You Need for Video Frame Interpolation implemented with ncnn library

The style transfer android example

ffcnn is a cnn neural network inference framework, written in 600 lines C language.

Code for ACM MobiCom 2024 paper "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices"

移动端实时疲劳驾驶检测

add tensorflow ops to ncnn

A demo of real-time face recognition on Android.

An example for porting nerual network to vapoursynth.

This project can easily test the ncnn model and even deploy ncnn projects on python to speed up