
ncnn 是一个为移动平台极致优化的高性能神经网络推理框架。ncnn 从设计之初就充分考虑了移动端的部署和使用。它无第三方依赖,跨平台,在手机端 CPU 上的运行速度快于目前所有已知的开源框架。开发者可以基于高效的 ncnn 实现,轻松将深度学习算法模型移植到移动平台,开发出智能应用,将 AI 带到你的指尖。ncnn 目前已在腾讯多款应用中使用,如 QQ、Qzone、微信、天天 P 图等。
|
技术交流 QQ 群 637093648 (超多大佬) 答案:卷卷卷卷卷(已满) |
Telegram Group
|
Discord Channel
|
|
Pocky QQ 群(MLIR YES!) 677104663 (超多大佬) 答案:multi-level intermediate representation |
||
|
他们都不知道 pnnx 有多好用群 818998520 (新群!) |
https://github.com/Tencent/ncnn/releases/latest
|
**[如何在 Linux / Windows / macOS / Raspberry Pi3, Pi4 / POWER / Android / NVIDIA Jetson / iOS / WebAssembly / AllWinner D1 / Loongson 2K1000 上构建 ncnn 库](https://github.com/Tencent/ncnn/wiki/how-to-build)** | ||
| 源代码 |
[ |
||
|
- [为 Android 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-android) - [为 Android 上的 Termux 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-termux-on-android) | ||
| Android |
[ |
[ |
|
| Android 动态库 |
[ |
||
|
|
- [为 HarmonyOS 交叉编译构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-harmonyos-with-cross-compiling) | ||
| HarmonyOS |
[ |
||
| HarmonyOS 动态库 | |||
|
- [在 macOS 上使用 xcode 为 iOS 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-ios-on-macos-with-xcode) | ||
| iOS |
[ |
[ |
|
| iOS 模拟器 |
[ |
||
|
- [为 macOS 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-macos) | ||
| macOS |
[ |
[ |
|
| Mac Catalyst |
[ |
[ |
|
| watchOS |
[ |
[ |
|
| watchOS 模拟器 |
[ |
||
| tvOS |
[ |
[ |
|
| tvOS 模拟器 |
[ |
||
| visionOS |
[ |
[ |
|
| visionOS 模拟器 |
[ |
||
| Apple xcframework |
[ |
||
|
- [为 Linux / NVIDIA Jetson / Raspberry Pi3, Pi4 / POWER 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-linux) | ||
| Ubuntu 22.04 |
[ |
[ |
|
| Ubuntu 24.04 |
[ |
||
|
- [使用 VS2017 为 Windows x64 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-windows-x64-using-visual-studio-community-2017) - [使用 MinGW-w64 为 Windows x64 构建](https://github.com/Tencent/ncnn/wiki/how-to-build#build-for-windows-x64-using-mingw-w64) | ||
| VS2015 |
[ |
[
目前尚无回复
| |