TensorFlow Hub is a comprehensive repository of pre-trained models ready for fine-tuning and deployable anywhere. The tensorflow_hub library lets you download and reuse the latest trained models with a minimal amount of code. The following tutorials should help you getting started with using and applying models from Hub to your needs. Interactive tutorials let you modify them and execute them with your changes. Click the Run in Google Colab button at the top of an interactive tutorial to tinker with it.
If you are unfamiliar with machine learning and TensorFlow, you can start by getting an overview of how to classify images and text or by stylizing your own pictures like famous artists:
Build a Keras model on top of a pre-trained image classifier to distinguish flowers.
Classify movie reviews as either positive or negative.
Let a neural network redraw an image in the style of Picasso, van Gogh or like your own picture.
If you are familiar with TensorFlow, you can take a look at more advanced tutorials.
Explore the CORD-19 embedding by analyzing semantically similar words and classifying scientific articles.
Answer questions from the SQuAD dataset.
Find news headlines that are semantically close to a given query.
Classify and semantically compare sentences with the Universal Sentence Encoder.
Semantically compare sentences of different languages using the Multilingual Universal Sentence Encoder.
Detect objects in images using modules like FasterRCNN or SSD.
Generate artificial faces and interpolate between them.
Match key points of two images using DELF.
Detect one of 400 actions in a video using the Inflated 3D ConvNet model.
Predict what happened in a video between the first and the last frame.