# Import Model Process

### 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](/tensorleap-integration/writing-integration-code/custom-layers.md) to the [integration script](/tensorleap-integration/writing-integration-code.md) before upload.
  {% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tensorleap.ai/user-interface/project/menu-bar/runs-and-processes/process-types/import-model-process.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.