π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
- wifi
- esp32
- monitoring
- rf
132,241 visible repositories in the index
1–24 of 47 · Most stars
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
🎞 mpv.net is a media player for Windows with a modern GUI.
RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.
Deformable Convolutional Networks
RepVGG: Making VGG-style ConvNets Great Again
The repository host gives no description.
Easy benchmarking of all publicly accessible implementations of convnets
subpixel: A subpixel convnet for super resolution with Tensorflow
CVNets: A library for training computer vision networks
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
Interactive convnet features visualization for Keras
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
Deformable ConvNets V2 (DCNv2) in PyTorch
MatConvNet: CNNs for MATLAB
[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)
A Tensorflow implementation of Spatial Transformer Networks.
Memory consumption and FLOP count estimates for convnets
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.