Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Declarative and readable tensor operations in Julia

Clean, reproducible, boilerplate-free deep learning project template.

C++17 implementation of einops for libtorch - clear and reliable tensor manipulations with einstein-like notation

A collection of components for transformers 🧩

R port of the einops library

TensorCrafter is an efficient, from-scratch reimplementation of einops.rearrange with full support for complex patterns, split axes, ellipses, and error handling. Built to be robust, iterative, and optimized without over-engineering.

One tensor operation is all you need

Demonstration for NVIDIA's Nemotron-Parse-v1.1 model, designed for advanced document parsing and OCR. Upload images of documents (e.g., papers, forms) to extract structured content: text, tables (LaTeX), figures, and titles. Outputs annotated images with colored bounding boxes and processed markdown/LaTeX text for easy integration.

Layer normalization with einops semantics.

Modern Eager TensorFlow implementation of Attention Is All You Need

Powerful Library helps peform operations on torch by creating a pattern

Demonstration for the Lightricks LTX-2 Distilled model, enhanced with specialized LoRA adapters for cinematic camera movements (dolly left/right/in/out, jib up/down, static). Generates animated videos from text prompts or input images, with optional prompt enhancement using Gemma-3-12b.

📄 Enhance document processing with NVIDIA's Nemotron-Parse-OCR, extracting structured content and providing clear visual annotations for easier integration.

대조 학습을 추천 시스템에 적용하여 개인화 추천의 다양성을 향상하는 프로젝트입니다.

Code implementation of computer vision models for practice based on pytorch and einops.