Skip to content
Catégories de projets

Apprentissage automatique · GitHub

Explorez les outils pour entraîner, évaluer et exécuter des modèles, et comparez leur popularité.

Projets GitHub utiles

12,822 projets

denoisers

will-rice

44étoiles

Simple PyTorch Denoisers for Waveform Audio

  • WaveUNet: Based on the original paper, optimized for high-fidelity audio restoration
  • UNet1D: Custom architecture inspired by diffusion models, designed for efficiency and real-time processing

TextGAN-PyTorch

williamSYSU

904étoiles
TextGAN-PyTorch preview

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.

  • Visualization Use utils/visualization.py to visualize the log file, including model loss and metrics scores. Custom your log files in log_file_list, no more than len(color_list). The log filename should exclude .txt.
  • Automatiaclly select GPU In config.py, the program would automatically select a GPU device with the least GPU-Util in nvidia-smi. This feature is enabled by default. If you want to manually select a GPU device, please uncomment the --device args in run_[run_model].py and specify a GPU device with command.

ECE298A-TPU

WilliamZhang20

57étoiles
ECE298A-TPU preview

A custom AI chip to be taped out soon!

  • Systolic Array: A 2×2 grid of MAC units propagates data left-to-right and top-to-bottom, emulating a systolic matrix multiplication engine.
  • Signed 8-bit Inputs, 16-bit Outputs: Handles signed integers (-128 to 127) and accumulates products in 16-bit precision.

SiT

willisma

1,228étoiles
SiT preview

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

detect-waste

wimlds-trojmiasto

225étoiles
detect-waste preview

AI to Combat Environmental Pollution - detecting plastic waste in the environment to combat environmental pollution and promote circular economy (Deep Learning, PyTorch)

vitamin-cuda

WingEdge777

236étoiles

🍎 One kernel a day keeps high latency away. A hands-on CUDA learning path featuring a rich collection of kernels, from the basics to peak performance, seamlessly integrated as PyTorch C++ extensions.

ster

wisent-ai

346étoiles
ster preview

Ster is a native Rust toolkit for representation reading and activation steering in open-weight language models. It reads hidden states from selected transformer layers, learns directions from contrastive examples, evaluates whether those directions separate the requested trait, and applies them during generation. It also trains the weights themselves: LoRA adapters under a supervised, a preference, a reward-modelling or a policy-gradient objective, and the tools to merge, score and inspect what comes out. And it reads decisions: typed questions about a state answered from one forward pass, with a probability for every option and no text generated.