# Sample Analysis Process

<figure><img src="https://3509361326-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9UXeOlFqlw8pl79U2HGU%2Fuploads%2FQ2UQB9UNyeMZrOhcEnKo%2Fimage.png?alt=media&#x26;token=95e0cd9c-fb22-439a-ae01-06d942272ed8" alt=""><figcaption><p>Filtering for all sample analysis processes in the platform</p></figcaption></figure>

### Overview

The sample analysis process is triggered manually from the population exploration dashlet

This process computes a per-layer gradcam-like heatmap.

### Common Run Issues:

{% hint style="danger" %}
Sample analysis can fail due to the possible reasons:

* OOM in sample analysis, please adjust the limits in the [settings](https://docs.tensorleap.ai/user-interface/settings) page.
* If heatmaps are invalid: make sure [add\_prediction](https://docs.tensorleap.ai/tensorleap-integration/python-api/code_loader/leap_binder/add_prediction) and [input\_encoder](https://docs.tensorleap.ai/tensorleap-integration/python-api/code_loader/decorators/tensorleap_input_encoder) both declare the correct channel dimension.
  {% endhint %}