Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes. Register now
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 (MobileNet).

Object detection

Localize and identify multiple objects in a single image (Coco SSD).

Body segmentation

Segment person(s) and body parts in real-time (BodyPix).

Pose estimation

Estimate human poses in real-time (PoseNet).

Text toxicity detection

Score the perceived impact a comment may have on a conversation, from "Very toxic" to "Very healthy" (Toxicity).

Sentence encoding

Encode text into embeddings for NLP tasks such as sentiment classification and textual similarity (Universal Sentence Encoder).

Speech command recognition

Classify 1-second audio snippets from the speech commands dataset (speech-commands).

KNN Classifier

Utility to create a classifier using the K-Nearest-Neighbors algorithm. Can be used for transfer learning.