FastDeploy
deepdetect
FastDeploy | deepdetect | |
---|---|---|
5 | 4 | |
2,715 | 2,495 | |
1.9% | 0.2% | |
7.5 | 6.7 | |
14 days ago | 8 days ago | |
C++ | C++ | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FastDeploy
- Testing YOLO on Orange Pi 5
-
Github-Paddle.js: Run AI models on browsers for computer version.
Refer to this link(https://github.com/PaddlePaddle/FastDeploy/blob/develop/examples/application/js/WebDemo_en.md) for examples and tutorials.
-
[P] FastDeploy: Make DL deployment easier and faster!
🔥 2022.10.31:Release FastDeploy release v0.5.0
Repo: https://github.com/PaddlePaddle/FastDeploy
deepdetect
-
Exploring Open-Source Alternatives to Landing AI for Robust MLOps
For those seeking a lightweight solution for setting up deep learning REST APIs across platforms without the complexity of Kubernetes, Deepdetect is worth considering.
-
[D] Deep Learning Framework for C++.
But you need to have good reasons to do it. Ours is that we have a multi-backend framework, and that we don't want any step in between dev & run. C++ allows for this since the same code can run on training server and edge device as needed. It also allows for building full AI applicatioms with great performances (e g. real time) We dev & use https://github.com/jolibrain/deepdetect for these purposes and it serves us very well, but it's not the faint of heart !
-
[P] Real-time AR for jewelry virtual try on that looks real, done with joliGAN, based on a few 2D videos and no 3D model
- Real-time is achieved through our full C++ Open Source backend DeepDetect, https://github.com/jolibrain/deepdetect. We use CUDA along with OpenCV and TensorRT to chain multiple models (ring detection and generator mostly), and we make sure the data remain within CUDA memory at all time. This allows us to reach ~60 FPS on 1080Ti and 20% more on average on an RTX3090.
-
[P] Benchmarking OpenBLAS on an Apple MacBook M1
Interesting, thanks. Recently benchmarked inference with Vulkan/MoltenVK/NCNN, M1 GPU is roughly 30% faster than M1 CPU, https://github.com/jolibrain/deepdetect/pull/1105 for single batch inference (NCNN does not really support batch size > 1).
What are some alternatives?
mmdeploy - OpenMMLab Model Deployment Framework
ncnn - ncnn is a high-performance neural network inference framework optimized for the mobile platform
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 performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
netron - Visualizer for neural network, deep learning and machine learning models
tensorRT_Pro - C++ library based on tensorrt integration
tensorflow-wheels - Tensorflow Wheels
jetson-inference - Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
YoloV7-ncnn-Jetson-Nano - YoloV7 for a Jetson Nano using ncnn.
maps-core - The lightweight and modern Map SDK for Android and iOS
mdspan - Reference implementation of mdspan targeting C++23
useful-transformers - Efficient Inference of Transformer models
mmaction2 - OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark