PyTorch extensions for fast R&D prototyping and Kaggle farming
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.
Image Test Time Augmentation with PyTorch!
[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
Test Time image Augmentation (TTA) wrapper for Keras model.
Test-Time Augmentation library for Pytorch
AI Manga Reader is a next-gen manga app powered by the MangaDex API, offering vast multi-language content and flexible reading modes. It uses AI-powered OCR to extract and translate text from manga pages, combined with AI-driven text-to-speech narration—letting you effortlessly read and listen to any chapter or page, anytime, anywhere.
ODA is a test-time-augmentation(TTA) tool for 2D object detectors. For use in Kaggle competitions.
telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3
Wheat detection using Faster RCNN
Efficient explaining AI algorithms for Keras models
Engage in a semantic segmentation challenge for land cover description using multimodal remote sensing earth observation data, delving into real-world scenarios with a dataset comprising 70,000+ aerial imagery patches and 50,000 Sentinel-2 satellite acquisitions.
A web-based code editor, compiler and debugger for the 16TTAC CPU
A curated collection of Test-Time Adaptation (TTA) papers, methods, and resources, updated monthly with the latest research.
Add a description, image, and links to the tta topic page so that developers can more easily learn about it.
To associate your repository with the tta topic, visit your repo's landing page and select "manage topics."