Easily train and evaluate multiple flow matching generative models on various particle physics datasets
-
Updated
Jun 11, 2026 - Python
Easily train and evaluate multiple flow matching generative models on various particle physics datasets
Re-implementation of Eye Tracking for Everyone
This project is built around PyTorch-Lightning, offering a structured and friendly environment for anyone exploring sequential recommendation systems. This platform is designed to simplify the machine learning workflow, letting you focus more on the strategic aspects of model development and less on setup complexities.
Тут всё для тренировки модели и ее конвертации. Копия с gitlab
This project is the Kaggle notebook "Chicken Detection/Segmentation with MaskRCNN and Pytorch" code demo.
Enhacing classification accuracy for minority crop's classes via generating fake satellite image datasets with use of GANs
A UNet based document denoiser built with PyTorch
Automatically segment lung cancer in CTs
T5 fine tunning for sentiment analysis
Official implementation of accepted IEEE ICASSP paper "Adversarial Rivalry Learning for Music Classification".
Comparing text-only (RoBERTa), audio-only (wav2vec2/WavLM), and multimodal transfer learning approaches for Speech Emotion Recognition on RAVDESS, MELD, and IEMOCAP. PyTorch Lightning + HuggingFace + Gradio demo.
Minimal reference implementation for running Lightning and NeuralForecast on Intel GPU via native PyTorch XPU.
Segmentation of Lung CT via Python/Pytorch for Tumor identification
A package to aid in building models for RSNA Intracranial Hemorrhage Detection competition
PyTorch-Lightning wrapped in some shit code
Collection of GNN architectures for 3D shapes and graphs using NN Template
Handwriting Synthesis is implemented using PyTorch Lightning by following Alex Grave's paper on sequence generation
GAN models rewritten into PyTorch Lightning. With Pytests, Flake8, Mypy, Poetry, and other serious stuff included.
To associate your repository with the pytorch-lightning topic, visit your repo's landing page and select "manage topics."