PyTorch extensions for fast R&D prototyping and Kaggle farming

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.

Image Test Time Augmentation with PyTorch!

Test Time image Augmentation (TTA) wrapper for Keras model.

A test times augmentation toolkit based on paddle2.0.

Test-Time Augmentation library for Pytorch

telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3

[ICCV 2025] Official Repository for "Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models"

Efficient explaining AI algorithms for Keras models

A tool with nice GUI to visualize the codon usage frequencies in whole genomes

LIGHTest DNS API

Test Time Augmentation for Deep Learning Inference

Test time augmentation with Tensorflow keras models for segmentation tasks. This package also enables creation of keras layers for GPU acceleration

8th place solution for the U-Tokyo Deep Learning Course CIFAR-10 Competition (Top 0.6%). High-performance CNN pipeline featuring WideResNet-28-10, SAM, and advanced augmentation scheduling.

Just another ResNet implementation trained on CIFAR-100 dataset achieving 73% test accuracy

1st place solution for the CentraleSupélec Deep Learning Kaggle challenge "3-MD-4040 2026 ZooCAM Challenge". Plankton image classification (1.2M samples, 86 classes) using CNNs trained from scratch and a weighted logits ensemble of ResNet50, EfficientNet-B3 and ConvNeXt-Tiny with label smoothing, weighted sampling and TTA.