Import a TensorFlow model into TensorFlow.js
Skip to main content
Install
Learn
Introduction
New to TensorFlow?
Tutorials
Learn how to use TensorFlow with end-to-end examples
Guide
Learn framework concepts and components
Learn ML
Educational resources to master your path with TensorFlow
API
TensorFlow (v2.16.1)
Versions…
TensorFlow.js
TensorFlow Lite
TFX
Ecosystem
LIBRARIES
TensorFlow.js
Develop web ML applications in JavaScript
TensorFlow Lite
Deploy ML on mobile, microcontrollers and other edge devices
TFX
Build production ML pipelines
All libraries
Create advanced models and extend TensorFlow
RESOURCES
Models & datasets
Pre-trained models and datasets built by Google and the community
Tools
Tools to support and accelerate TensorFlow workflows
Responsible AI
Resources for every stage of the ML workflow
Recommendation systems
Build recommendation systems with open source tools
Community
Groups
User groups, interest groups and mailing lists
Contribute
Guide for contributing to code and documentation
Blog
Stay up to date with all things TensorFlow
Forum
Discussion platform for the TensorFlow community
Why TensorFlow
About
Case studies
/
English
Español
Español – América Latina
Français
Indonesia
Italiano
Polski
Português
Português – Brasil
Tiếng Việt
Türkçe
Русский
עברית
العربيّة
فارسی
हिंदी
বাংলা
ภาษาไทย
中文 – 简体
日本語
한국어
GitHub
Sign in
For JavaScript
Overview
Tutorials
Guide
Models
Demos
API
Install
Learn
More
Overview
Tutorials
Guide
Models
Demos
API
API
More
Ecosystem
More
Community
More
Why TensorFlow
More
GitHub
Get started
Set up a TensorFlow.js project
Upgrade to TensorFlow.js 3.0
Train models
Fit a curve to two-dimensional data
Recognize handwritten digits with CNNs
Predict baseball pitch types in Node.js
Train a model using a web worker
Transfer learning
What is transfer learning?
Build an image classifier
Build an audio recognizer
Import Python models
Use a pre-trained model
Import a Keras model
Import a TensorFlow SavedModel
Deployment & Optimization
Generating size-optimized browser bundles
Deploy a Chrome extension
Web ML applications
Predictive prefetching
React Native
Introduction
Tutorials
Guide
Learn ML
TensorFlow (v2.16.1)
Versions…
TensorFlow.js
TensorFlow Lite
TFX
LIBRARIES
TensorFlow.js
TensorFlow Lite
TFX
All libraries
RESOURCES
Models & datasets
Tools
Responsible AI
Recommendation systems
Groups
Contribute
Blog
Forum
About
Case studies
New to machine learning? Watch a video course to get practical working knowledge of ML using web technologiesView series
TensorFlow
Learn
For JavaScript
Tutorials
Import a TensorFlow model into TensorFlow.js
Stay organized with collections
Save and categorize content based on your preferences.
TensorFlow GraphDef-based models (typically created via the Python API) can be
saved in one of following formats:
TensorFlow
SavedModel
Frozen Model
Tensorflow Hub module
All of the above formats can be converted by the
TensorFlow.js converter
into a format that can be loaded directly into TensorFlow.js for inference.
(Note: TensorFlow has deprecated the session bundle format. Please migrate your
models to the SavedModel format.)
Requirements
The conversion procedure requires a Python environment; you may want to keep an
isolated one using pipenv or
virtualenv.
To install the converter, run the following command:
pip install tensorflowjs
Importing a TensorFlow model into TensorFlow.js is a two-step process. First,
convert an existing model to the TensorFlow.js web format, and then load it into
TensorFlow.js.
Step 1. Convert an existing TensorFlow model to the TensorFlow.js web format
Run the converter script provided by the pip package:
SavedModel example:
tensorflowjs_converter \
--input_format=tf_saved_model \
--output_node_names='MobilenetV1/Predictions/Reshape_1' \
--saved_model_tags=serve \
/mobilenet/saved_model \
/mobilenet/web_model
Frozen model example:
tensorflowjs_converter \
--input_format=tf_frozen_model \
--output_node_names='MobilenetV1/Predictions/Reshape_1' \
/mobilenet/frozen_model.pb \
/mobilenet/web_model
Tensorflow Hub module example:
tensorflowjs_converter \
--input_format=tf_hub \
'https://tfhub.dev/google/imagenet/mobilenet_v1_100_224/classification/1' \
/mobilenet/web_model
Positional Arguments
Description
input_path
Full path of the saved model directory, session bundle directory, frozen model file or TensorFlow Hub module handle or path.
output_path
Path for all output artifacts.
Options
Description
--input_format
The format of input model. Use tf_saved_model for SavedModel, tf_frozen_model for frozen model, tf_session_bundle for session bundle, tf_hub for TensorFlow Hub module and keras for Keras HDF5.
--output_node_names
The names of the output nodes, separated by commas.
--saved_model_tags
Only applicable to SavedModel conversion. Tags of the MetaGraphDef to load, in comma separated format. Defaults to serve.
--signature_name
Only applicable to TensorFlow Hub module conversion, signature to load. Defaults to default. See https://www.tensorflow.org/hub/common_signatures/
Use following command to get a detailed help message:
tensorflowjs_converter --help
Converter generated files
The conversion script above produces two types of files:
model.json: The dataflow graph and weight manifest
group1-shard\*of\*: A collection of binary weight files
For example, here is the output from converting MobileNet v2:
output_directory/model.json
output_directory/group1-shard1of5
...
output_directory/group1-shard5of5
Step 2: Loading and running in the browser
Install the tfjs-converter npm package:
yarn add @tensorflow/tfjs or npm install @tensorflow/tfjs
Instantiate the
FrozenModel class
and run inference.
import * as tf from '@tensorflow/tfjs';
import {loadGraphModel} from '@tensorflow/tfjs-converter';
const MODEL_URL = 'model_directory/model.json';
const model = await loadGraphModel(MODEL_URL);
const cat = document.getElementById('cat');
model.execute(tf.browser.fromPixels(cat));
Check out the
MobileNet demo.
The loadGraphModel API accepts an additional LoadOptions parameter, which
can be used to send credentials or custom headers along with the request. For
details, see the
loadGraphModel() documentation.
Supported operations
Currently TensorFlow.js supports a limited set of TensorFlow ops. If your model
uses an unsupported op, the tensorflowjs_converter script will fail and print
out a list of the unsupported ops in your model. Please file an
issue for each op to let us know
which ops you need support for.
Loading the weights only
If you prefer to load the weights only, you can use the following code snippet:
import * as tf from '@tensorflow/tfjs';
const weightManifestUrl = "https://example.org/model/weights_manifest.json";
const manifest = await fetch(weightManifestUrl);
this.weightManifest = await manifest.json();
const weightMap = await tf.io.loadWeights(
this.weightManifest, "https://example.org/model");
// Use `weightMap` ...
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-10-12 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2023-10-12 UTC."],[],[]]
Stay connected
Blog
Forum
GitHub
Twitter
YouTube
Support
Issue tracker
Release notes
Stack Overflow
Brand guidelines
Cite TensorFlow
Terms
Privacy
Manage cookies
Sign up for the TensorFlow newsletter
Subscribe
English
Español
Español – América Latina
Français
Indonesia
Italiano
Polski
Português
Português – Brasil
Tiếng Việt
Türkçe
Русский
עברית
العربيّة
فارسی
हिंदी
বাংলা
ภาษาไทย
中文 – 简体
日本語
한국어