tensorflow/tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
ArchivedProvides a unified framework for sequence-to-sequence tasks across modalities (vision, language, speech, audio) through encoder-decoder transformer architectures and problem-specific abstractions. Features pre-built implementations of specialized models like Image Transformer, Universal Transformer, and ResNet, paired with curated datasets and hyperparameter configurations optimized for Cloud TPU and multi-GPU training. Built on TensorFlow with a modular design allowing custom datasets and models to be registered as pluggable components.
17,062 stars. No commits in the last 6 months.
Stars
17,062
Forks
3,728
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tensorflow/tensor2tensor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
tensorly/tensorly
TensorLy: Tensor Learning in Python.
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility
lava-nc/lava-dl
Deep Learning library for Lava