# Import Model Process

<figure><img src="https://3509361326-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9UXeOlFqlw8pl79U2HGU%2Fuploads%2FEXdwtXDUqiN2Gb5Dl9P2%2Fimage.png?alt=media&#x26;token=959c7338-d9e8-46d7-856e-7606e68ee86c" alt=""><figcaption><p>The Import Model Process</p></figcaption></figure>

### Overview

Once an upload of a model to Tensorleap had initiated, an import model process starts.

This process:

* Uploads the model into the Tensorleap server
* Parses through the model and extracts menaingful indicators for future use
* Converts the model into a Tensorleap Format that the Engine can easily utilize for analysis

### Common Run Issues:

{% hint style="danger" %}
An import Model process can fail due to:

* Invalid model (please ensure the model you upload is able to infer locally)
* Unsupported model architecture (please contact Tensorleap team)
* The use of a custom Layer in a .h5 file. To support custom h5 layers, you need to register a [custom layer](https://docs.tensorleap.ai/tensorleap-integration/writing-integration-code/custom-layers) to the [integration script](https://docs.tensorleap.ai/tensorleap-integration/writing-integration-code) before upload.
  {% endhint %}