Lists (1)
Stars
Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
A course in reinforcement learning in the wild
G-code generator for 3D printers (Bambu, Prusa, Voron, VzBot, RatRig, Creality, etc.)
Step by step explanation of 2D convolution implemented as matrix multiplication using toeplitz matrices
rl from zero pretrain, can it be done? yes.
Hierarchical Reasoning Model Official Release
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A feature-rich command-line audio/video downloader
Learning causal or non-causal graphical models using information theory
All Stanford Cheatsheets: Artificial Intelligence, Transformers, LLMs, Deep Learning, Machine Learning, Probabilities, Statistics, Algebra and Calculus.
Classification of ASD (autism spectrum disorder) vs TD (typically developing) children based on their scanpaths of image viewing [ICME2019 GrandChallenge "Saliency4ASD" submission]
Neural network training using iterated projections.
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
Gin provides a lightweight configuration framework for Python
The simplest, fastest repository for training/finetuning small-sized VLMs.
Siamese and triplet networks with online pair/triplet mining in PyTorch
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
Pytorch implementation of our paper accepted by NeurIPS 2020 -- Rotated Binary Neural Network
Implemented here a Binary Neural Network (BNN) achieving nearly state-of-art results but recorded a significant reduction in memory usage and total time taken during training the network.
😎 Awesome photogrammetry projects
A modular framework for neural networks with Euclidean symmetry
A TTS model capable of generating ultra-realistic dialogue in one pass.
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Python Image Sequence: Load video and sequential images in many formats with a simple, consistent interface.