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, detecting objects in images, 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 starting from pre-trained text embeddings.
Let a neural network redraw an image in the style of Picasso, van Gogh or like your own picture.
Detect objects in images using modules like FasterRCNN or SSD.
If you are familiar with TensorFlow, you can take a look at more advanced tutorials.
Classify and semantically compare sentences with the Universal Sentence Encoder.
Explore BERT fine-tuned on different tasks like MNLI, SQuAD, and PubMed, running on TPU.
Answer questions from the SQuAD dataset.
Generate artificial faces and interpolate between them using GANs.
Enhance the resolution of downsampled images.
Fill the masked part of given images.
Detect one of 400 actions in a video using the Inflated 3D ConvNet model.
Find videos that are the most related to a text query.