dlstreamer
ncnn
| dlstreamer | ncnn | |
|---|---|---|
| 2 | 12 | |
| 500 | 19,275 | |
| 2.4% | 1.2% | |
| 4.3 | 9.4 | |
| 12 days ago | 5 days ago | |
| C++ | C++ | |
| MIT License | 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.
dlstreamer
-
What is the best model and approach to identify a car model? Is a YOLO a good choice for that or is it better to user YOLO or RCNN or darknet for object detection and then use somethin like resnet152 to predict the exact model?
If you want object detection, classification (car models in your case) as well as tracking them, before getting your feet wet on model selection viz., Yolo, RCNN etc, check out Intel DLStreamer which uses GStreamer as the back end.... It uses Intel OpenVINO for inferencing and custom plugins for detection/classification and tracking also.... Intel has a big model zoo of pre-trained models, which can do the task of identifying the car models..... https://github.com/dlstreamer/dlstreamer
-
How would you approach hosting real time detection model in server/cloud?
https://github.com/dlstreamer/dlstreamer based on gstreamer
ncnn
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
ncnn uses Vulkan for GPU acceleration, I've seen it used in a few projects to get AMD hardware support.
https://github.com/Tencent/ncnn
-
[D] Best way to package Pytorch models as a standalone application
They're using NCNN to package the model. Have a look. https://github.com/Tencent/NCNN
-
Realtime object detection android app
Hi. Here is my prefered android app for realtime objet detection: https://github.com/nihui/ncnn-android-nanodet ; https://github.com/Tencent/ncnn contains a lot of android demo app for a lot of models.
- ncnn: High-performance neural network inference framework optimized for mobile
-
Esp32 tensorflow lite
ncnn home page: https://github.com/Tencent/ncnn
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
ncnn
-
Draw Things, Stable Diffusion in your pocket, 100% offline and free
Yes, Android devices tend to have bigger RAMs, making running 1024x1024 possible (this is not possible at all on iPhones, which could peak around 5GiB memory with my current implementation, some serious engineering required to bring that down on iPhone devices). The problem is I am not sure about speed. I would likely switch to NCNN (https://github.com/Tencent/ncnn) as the backend which have a decent Vulkan computing kernel support. It is definitely a possibility and there is a path to do that.
- What’s New in TensorFlow 2.10?
-
[Technical Article] OCR Upgrade
As the leading open-source inference framework in China and in the world, what we like are its almost zero cost cross-platform capability, high inference speed, and minimal deployment volume. (Project address: https://github.com/Tencent/ncnn)
-
Is there a functioning neural netowork or backbone written in pure C language only?
If you’re not planning on training the neural net on an embedded device and just do inference, this might interest you: https://github.com/Tencent/ncnn
What are some alternatives?
vokoscreenNG - vokoscreenNG is a powerful screencast creator in many languages to record the screen, an area or a window (Linux only). Recording of audio from multiple sources is supported. With the built-in camera support, you can make your video more personal. Other tools such as systray, magnifying glass, countdown, timer, Showclick and Halo support will help
XNNPACK - High-efficiency floating-point neural network inference operators for mobile, server, and Web
AACS - Android Auto Server encapsulates communication with modern car infotainment system
rife-ncnn-vulkan - RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library
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.
deepdetect - Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
nulloy - Music player with a waveform progress bar
netron - Visualizer for neural network, deep learning and machine learning models
openvino - OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
darknet - Convolutional Neural Networks
RPi_64-bit_Zero-2-image - Raspberry Pi Zero 2 W 64-bit OS image with OpenCV, TensorFlow Lite and ncnn Framework.
torch-mlir - The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.