Pretrained models for TensorFlow.js
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
Xu Xing 4d09134407
Split canvas2d renderer from camera.js (#1138)
19 hours ago
.tslint Add linting rules for tfjs-models. (#333) 3 years ago
.vscode Move pose-detection code needed in hand detection to a common folder (#830) 2 years ago
blazeface Standardize Bodypix rollup config (#1104) 4 weeks ago
body-pix Standardize Bodypix rollup config (#1104) 4 weeks ago
body-segmentation Standardize rollup configs with a central config generator (#1102) 1 month ago
coco-ssd Standardize rollup configs with a central config generator (#1102) 1 month ago
deeplab Standardize rollup configs with a central config generator (#1102) 1 month ago
depth-estimation Standardize rollup configs with a central config generator (#1102) 1 month ago
face-detection Standardize rollup configs with a central config generator (#1102) 1 month ago
face-landmarks-detection Standardize rollup configs with a central config generator (#1102) 1 month ago
hand-pose-detection Standardize rollup configs with a central config generator (#1102) 1 month ago
handpose Standardize rollup configs with a central config generator (#1102) 1 month ago
knn-classifier Standardize rollup configs with a central config generator (#1102) 1 month ago
mobilenet Standardize rollup configs with a central config generator (#1102) 1 month ago
model-playground Standardize rollup configs with a central config generator (#1102) 1 month ago
pose-detection Split canvas2d renderer from camera.js (#1138) 19 hours ago
posenet Standardize rollup configs with a central config generator (#1102) 1 month ago
qna Standardize rollup configs with a central config generator (#1102) 1 month ago
scripts [handpose] Add model. (#414) 3 years ago
shared [pose-detection] Add WebGPU backend (#1044) 5 months ago
speech-commands Standardize rollup configs with a central config generator (#1102) 1 month ago
tasks Standardize rollup configs with a central config generator (#1102) 1 month ago
tools Standardize rollup configs with a central config generator (#1102) 1 month ago
toxicity Standardize rollup configs with a central config generator (#1102) 1 month ago
universal-sentence-encoder up stream the changes from g3 (#1128) 4 weeks ago
.gitignore [facemesh] Add model. (#413) 3 years ago
CONTRIBUTING.md Add license and contributing 5 years ago
LICENSE Add license and contributing 5 years ago
README.md Add depth estimation to readme (#1037) 8 months ago
cloudbuild.yml Standardize rollup configs with a central config generator (#1102) 1 month ago
package.json Standardize rollup configs with a central config generator (#1102) 1 month ago
presubmit.ts Add publish-npm, make-version, tag-version scripts to models. (#369) 3 years ago
run_python_tests.sh [SpeechCommands] Clean up training/browser-fft directory (#513) 3 years ago
test_util.ts Move pose-detection code needed in hand detection to a common folder (#830) 2 years ago
tsconfig.json Standardize rollup configs with a central config generator (#1102) 1 month ago
tsconfig.test.json Create test tsconfig. (#522) 3 years ago
tslint.json Add linting rules for tfjs-models. (#333) 3 years ago
update_yarn_lock.sh fix security vulnerabilities (#620) 2 years ago
workspace.code-workspace Add base class and types. (#607) 2 years ago
yarn.lock Standardize rollup configs with a central config generator (#1102) 1 month ago

README.md

Pre-trained TensorFlow.js models

This repository hosts a set of pre-trained models that have been ported to TensorFlow.js.

The models are hosted on NPM and unpkg so they can be used in any project out of the box. They can be used directly or used in a transfer learning setting with TensorFlow.js.

To find out about APIs for models, look at the README in each of the respective directories. In general, we try to hide tensors so the API can be used by non-machine learning experts.

For those interested in contributing a model, please file a GitHub issue on tfjs to gauge interest. We are trying to add models that complement the existing set of models and can be used as building blocks in other apps.

Models

Type Model Demo Details Install
Images
MobileNet
live Classify images with labels from the ImageNet database. npm i @tensorflow-models/mobilenet
source
Hand
live Real-time hand pose detection in the browser using TensorFlow.js. npm i @tensorflow-models/hand-pose-detection
source
Pose
live An API for real-time human pose detection in the browser. npm i @tensorflow-models/pose-detection
source
Coco SSD
Object detection model that aims to localize and identify multiple objects in a single image. Based on the TensorFlow object detection API. npm i @tensorflow-models/coco-ssd
source
DeepLab v3
Semantic segmentation npm i @tensorflow-models/deeplab
source
Face Landmark Detection
live Real-time 3D facial landmarks detection to infer the approximate surface geometry of a human face npm i @tensorflow-models/face-landmarks-detection
source
Audio
Speech Commands
live Classify 1 second audio snippets from the speech commands dataset. npm i @tensorflow-models/speech-commands
source
Text
Universal Sentence Encoder
Encode text into a 512-dimensional embedding to be used as inputs to natural language processing tasks such as sentiment classification and textual similarity. npm i @tensorflow-models/universal-sentence-encoder
source
Text Toxicity
live Score the perceived impact a comment might have on a conversation, from "Very toxic" to "Very healthy". npm i @tensorflow-models/toxicity
source
Depth Estimation
Portrait Depth
live Estimate per-pixel depth (the distance to the camera center) for a single portrait image, which can be further used for creative applications such as 3D photo and relighting. npm i @tensorflow-models/depth-estimation
source
General Utilities
KNN Classifier
This package provides a utility for creating a classifier using the K-Nearest Neighbors algorithm. Can be used for transfer learning. npm i @tensorflow-models/knn-classifier
source

Development

You can run the unit tests for any of the models by running the following inside a directory:

yarn test

New models should have a test NPM script (see this package.json and run_tests.ts helper for reference).

To run all of the tests, you can run the following command from the root of this repo:

yarn presubmit