# Pre-made models for TensorFlow.js

Pre-made models are models that are already trained for a specific purpose.
There are a variety of already trained, open source models you can use
immediately with TensorFlow.js to accomplish many machine learning tasks. This
topic provides guidance on how to find and select pre-made models for your
use case.

## Benefits of using pre-made models

TensorFlow.js has a broad spectrum of pre-made models that can be used in any
project out of the box and provide you with the following significant benefits:

- **Save Time and Resources**: Avoid the time-consuming processes of gathering, preparing, and labeling data, then training, evaluating, and improving the model. Be able to prototype your ideas rapidly.
- **Leverage existing research and documentation**: The state-of-the-art research used in developing pre-made models enables you to quickly deploy them while understanding how they perform in different real-world scenarios.
- **Enable transfer learning**: Pre-made models allow you to use information learned by a model for a task on another, similar use-case. This transfer learning process will enable you to train existing models rapidly on custom data.

## Find a model

Finding an existing TensorFlow.js model for your use case depends on what you
are trying to accomplish. For example, does your app need to run on the
client-side or server-side? How important are factors such as privacy, speed
and accuracy? etc.

Here are a few recommended ways to discover models for
use with TensorFlow.js:

**By example:** The fastest way to find and start using models with
TensorFlow.js is to browse the [TensorFlow.js demos](https://www.tensorflow.org/js/demos) section to find
demos that perform a task similar to your use case. This catalog
provides fun example use cases with links to the code that will help you get
started.

**By data input type:** Aside from looking at examples similar to your use case,
another way to discover models for your own use is to consider the type of data
you want to process, such as audio, text, or images. Machine
learning models are frequently designed for use with one of these types of data,
so looking for models that handle the data type you want to use can help you
narrow down what models to consider. You can start browsing TensorFlow.js models
based on general use cases in the
[TensorFlow.js models](https://www.tensorflow.org/js/models) section, or browse a larger set
of models on
[TensorFlow Hub](https://tfhub.dev/s?deployment-format=tfjs). On TensorFlow Hub, you can use
the **Problem domain** filter to view model data types and narrow your list.

> [!IMPORTANT]
> **Important:** TensorFlow Hub lists both regular TensorFlow models and TensorFlow.js format models. These model formats are not interchangeable. TensorFlow models can be converted into TensorFlow.js models, but that process is not reversible.

The following list links to TensorFlow.js models on
[TensorFlow Hub](https://tfhub.dev/s?deployment-format=tfjs) for common use cases:

- [Image classification](https://tfhub.dev/s?deployment-format=tfjs&module-type=image-classification) models
- [Object detection](https://tfhub.dev/s?deployment-format=tfjs&module-type=image-object-detection) models
- [Text](https://tfhub.dev/s?deployment-format=tfjs&module-type=text) models
- [Audio](https://tfhub.dev/s?deployment-format=tfjs&module-type=audio) models

### Choose between similar models

If your application follows a common use case such as image classification or
object detection, you may find multiple TensorFlow.js models that fit your
need. Once you have some models that are applicable to your use case, you
want to identify the model that will provide the best solution.
To do this, consider the following aspects of each model:

1. Inference speed
2. File size
3. Runtime RAM usage
4. Model features/capabilities

When deciding between a number of models, you
can narrow your options based first on your most limiting constraint such as
size of model, size of data, inference speed, or accuracy, etc.

If you are not sure what your most limiting constraint is, assume it is the size
of the model and pick the smallest model available. Picking a small model gives
you the most flexibility in terms of where you can successfully
deploy and run the model. Smaller models also typically produce faster
inferences, and speedier predictions generally create better end-user
experiences. **However**, smaller models typically have lower accuracy rates,
so you may need
to pick larger models if prediction accuracy is your primary concern.

## Sources for models

Pre-made models in TensorFlow.js are typically available in two forms. Official
models come wrapped in JavaScript classes making them simple to deploy in your
app. Others are in a raw form that may require additional code to pre/post
process input and output data.

Use the [TensorFlow.js models](https://www.tensorflow.org/js/models) as your first destination for finding and
selecting models for use with TensorFlow.js. These are the official
models provided by the TensorFlow.js team which already
have the JavaScript wrappers that make it simple to integrate into your code.
The
[TensorFlow Hub](https://tfhub.dev/s?deployment-format=tfjs)
site provides additional models. Note that models in the Hub
may be in a raw format that requires additional work on your part to integrate.

### TensorFlow models

It is possible to [convert](https://www.tensorflow.org/js/guide/conversion)
regular TensorFlow models to TensorFlow.js format. For more information about
converting models, see the [Model conversion](https://www.tensorflow.org/js/guide/conversion)
topic. You can find TensorFlow models on
[TensorFlow Hub](https://tfhub.dev/)
and in the [TensorFlow Model Garden](https://github.com/tensorflow/models).

## Further reading

- Now that you know where to find models ready for use, see the [React native](https://www.tensorflow.org/js/tutorials/applications/react_native) tutorial to learn how you can use such a model in a web app.