TensorFlow Hub

TensorFlow Hub is an open repository and library for reusable machine learning. The tfhub.dev repository provides many pre-trained models: text embeddings, image classification models, TF.js/TFLite models and much more. The repository is open to community contributors.

The tensorflow_hub library lets you download and reuse them in your TensorFlow program with a minimum amount of code.

import tensorflow_hub as hub

model = hub.KerasLayer("https://tfhub.dev/google/nnlm-en-dim128/2")
embeddings = model(["The rain in Spain.", "falls",
                    "mainly", "In the plain!"])

print(embeddings.shape)  #(4,128)

Next Steps

• Find models on tfhub.dev
• Publish models on tfhub.dev
• TensorFlow Hub library
  • Install TensorFlow Hub
  • Library overview
• Follow tutorials