#pytorch Repositories
1,936 repositories total
๐ Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. ๐ซโ๏ธ
[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.
[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
[ICLR 2025 Oral] TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusion Interpolation
Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022
PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
Full-stack algorithm tutorial from NLP to LLM, online reading address: https://datawhalechina.github.io/base-llm/
utilities for decoding deep representations (like sentence embeddings) back to text
(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling
๐ฅ An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.
Formula Recognition & Office Editing | Handwriting & PDF to LaTeX/Markdown | Secure API Integrations.
JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.
A hackers AI voice assistant, built using Python and PyTorch.
๐ฅ CNN for Watermark Removal using Deep Image Prior with Pytorch ๐ฅ.
[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. โ ๐ค๐ค
SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.
[CVPR 2021 & IJCV 2024] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers