InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now. Learn more →
Top 23 C++ neural-network Projects
- Project mention: Ask HN: Why do maintainers spend time reviewing my code? | news.ycombinator.com | 2025-11-24
Recently, I was working on various open source projects. Mostly I was working on issues labelled as "good first issues". Before I start working on a issue I usually take a look at the previous attempts made by other people. Usually I can find a couple of PRs or comments if the issue is older than one year. Looking at the work history usually it becomes obvious why previous attempts were not successful: someone completely misunderstood the task and went the wrong direction, someone can barely code, someone is just pinging the contributors instead of doing the actual work[1]. What was surprising to me was that the maintainers almost always found time to answer every question, review ridiculously bad and incorrect PRs and spend days communicating with the contributor (including me) to give feedback about the work, while they themselves could absolutely resolve the issue in less than an hour. To be honest I don't understand why someone with 10+ years of experience would spend time reviewing my "good first issue" PRs like they don't have anything else to do. I am trying to be useful and to learn but I don’t want to bother anyone or waste anyone’s time and that's why I am wondering why would maintainers spend their time reviewing my code? What is their motivation?
[1] https://github.com/tensorflow/tensorflow/issues/22926#issuecomment-2888463504
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
PaddlePaddle
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
PaddlePaddle (so good they named it twice) predates Ray and supports both data parallel and model-parallel training. It is still being developed.
https://github.com/PaddlePaddle/Paddle
They have pedigry.
-
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
-
-
-
TensorFlow Serving GitHub
-
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
DALI
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
-
-
mace
MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
-
-
distributed-llama
Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
Project mention: Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5 | news.ycombinator.com | 2025-09-06 -
Simd
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON for ARM. (by ermig1979)
-
-
-
MocapNET
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic
-
-
nnstreamer
:twisted_rightwards_arrows: Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.
-
-
- Project mention: 5 APIs for Developers to Integrate In-App Content Creation Functionality | dev.to | 2025-12-22
2. OpenAI API: Text and Language
-
SegmentationCpp
A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.
-
vs-mlrt
Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020).
C++ neural-network discussion
C++ neural-network related posts
-
Grasping Computer Vision Fundamentals Using Python
-
Run Llama 3.3 70B Q40 on $1516 GPU 3.3 tok/s
-
GPT 4.5 level for 1% of the price
-
Distributed-Llama: Connect home devices into a cluster for LLM inference
-
What's new in C++26 (part 1)
-
Training AI Models on CPU on AWS EC2
-
Distributed-Llama: Tensor Parallelism for Home AI Clusters
- A note from our sponsor - InfluxDB www.influxdata.com | 24 Dec 2025
Index
What are some of the best open-source neural-network projects in C++? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | tensorflow | 192,863 |
| 2 | PaddlePaddle | 23,507 |
| 3 | ncnn | 22,450 |
| 4 | CNTK | 17,601 |
| 5 | oneflow | 9,377 |
| 6 | serving | 6,337 |
| 7 | tiny-cnn | 5,986 |
| 8 | DALI | 5,578 |
| 9 | flashlight | 5,429 |
| 10 | mace | 5,030 |
| 11 | tiny-cuda-nn | 4,358 |
| 12 | distributed-llama | 2,772 |
| 13 | Simd | 2,223 |
| 14 | fann | 1,704 |
| 15 | armnn | 1,290 |
| 16 | MocapNET | 917 |
| 17 | vectordb | 869 |
| 18 | nnstreamer | 768 |
| 19 | ONE | 540 |
| 20 | INSTA | 505 |
| 21 | liboai | 478 |
| 22 | SegmentationCpp | 463 |
| 23 | vs-mlrt | 400 |
Sponsored
InfluxDB – Built for High-Performance Time Series Workloads
InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
www.influxdata.com