Tencent / TNN
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and …
☆4,416Updated last month
Related projects ⓘ
Alternatives and complementary repositories for TNN
- MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba☆8,749Updated this week
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆20,503Updated this week
- MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.☆4,935Updated 5 months ago
- Tengine is a lite, high performance, modular inference engine for embedded device☆4,653Updated 2 months ago
- Simplify your onnx model☆3,865Updated 2 months ago
- FeatherCNN is a high performance inference engine for convolutional neural networks.☆1,210Updated 5 years ago
- 🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。☆1,479Updated 2 years ago
- Bolt is a deep learning library with high performance and heterogeneous flexibility.☆918Updated 3 months ago
- 🛠 A lite C++ toolkit of 100+ awesome AI models, support ONNXRuntime, MNN, TNN, NCNN and TensorRT.☆3,661Updated 3 weeks ago
- Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.☆3,096Updated last week
- 😎 A Collection of Awesome NCNN-based Projects☆713Updated last year
- The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS☆2,555Updated 2 weeks ago
- Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is…☆2,010Updated 3 years ago
- OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.☆5,910Updated this week
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆5,771Updated 3 months ago
- A primitive library for neural network☆1,295Updated 2 weeks ago
- PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）☆6,969Updated this week
- ONNX-TensorRT: TensorRT backend for ONNX☆2,953Updated 2 weeks ago
- 一款推理框架，同时有很多有用的demo，觉得好用请点星啊☆2,220Updated 3 months ago
- Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators☆1,528Updated 5 years ago
- PaddleSlim is an open-source library for deep model compression and architecture search.☆1,562Updated 2 weeks ago
- MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.☆4,310Updated 3 months ago
- MNN applications by MNN, JNI exec, RK3399. Support tflite\tensorflow\caffe\onnx models.☆501Updated 5 years ago
- SeetaFace 2: open source, full stack face recognization toolkit.☆2,138Updated 8 months ago
- PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.☆1,558Updated 7 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆11,798Updated this week
- ONNX Model Exporter for PaddlePaddle☆731Updated this week
- ⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio …☆2,998Updated this week
- OpenMMLab Model Deployment Framework☆2,777Updated last month
- An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.☆2,788Updated last year