TensorFlow 2.0 Beta is available Learn more
Models

Explore pre-trained TensorFlow.js models that can be used in any project out of the box.

Image classification

Classify images with labels from the ImageNet database.

Object detection

Object detection model that aims to localize and identify multiple objects in a single image.

Body segmentation

Real-time person and body part segmentation in the browser using TensorFlow.js.

Pose estimation

A machine learning model which allows for real-time human pose estimation in the browser.

Text toxicity detection

Score the perceived impact a comment might have on a conversation, from "Very toxic" to "Very healthy".

Sentence encoding

Encode text into an embedding to be used as inputs to natural language processing tasks such as sentiment classification and textual similarity.

Speech command recognition

Classify 1 second audio snippets from the speech commands dataset.

KNN Classifier

This package provides a utility for creating a classifier using the K-Nearest Neighbors algorithm. Can be used for transfer learning.