tensorflow/hub
A library for transfer learning by reusing parts of TensorFlow models.
Provides a Python API to download and load SavedModels from Kaggle Models (formerly tfhub.dev) with minimal code, supporting both TensorFlow 2 and legacy TF1 formats. Handles model caching, version management, and compatible signature discovery for seamless integration into TensorFlow workflows. Enables fine-tuning pre-trained embeddings and feature extractors across computer vision and NLP domains.
3,527 stars. No commits in the last 6 months.
Stars
3,527
Forks
1,649
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/tensorflow/hub"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
MinishLab/model2vec
Fast State-of-the-Art Static Embeddings
Embedding/Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
AnswerDotAI/ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
Santosh-Gupta/SpeedTorch
Library for faster pinned CPU <-> GPU transfer in Pytorch
twang2218/vocab-coverage
语言模型中文认知能力分析