# Fail with Transfer Learning with Unet Multiclass, Color Images, Semantic Segmentation

**URL:** <https://forums.developer.nvidia.com/t/fail-with-transfer-learning-with-unet-multiclass-color-images-semantic-segmentation/200498>\
**Category:** TAO Toolkit\
**Created:** [January 14, 2022, 5:03am UTC](https://forums.developer.nvidia.com/t/fail-with-transfer-learning-with-unet-multiclass-color-images-semantic-segmentation/200498 "2022-01-14T05:03:29Z")\
**Posts on this page:** 1\
**Showing post:** 5

<div class="post-metadata">

**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\
**Post date:** [January 14, 2022, 1:58pm UTC](https://forums.developer.nvidia.com/t/fail-with-transfer-learning-with-unet-multiclass-color-images-semantic-segmentation/200498/5 "2022-01-14T13:58:36Z")

</div>

Refer to [Problems encountered in training unet and inference unet - #26](https://forums.developer.nvidia.com/t/problems-encountered-in-training-unet-and-inference-unet/187317/26)  
and [Multiple classes not detected? - #11 by Morganh](https://forums.developer.nvidia.com/t/multiple-classes-not-detected/188234/11)  
Please note that the pixel integer value should be equal to the value of the label\_id provided in the spec.  
UNet expects the images and corresponding masks encoded as images. Each mask image is a single-channel image, where every pixel is assigned an integer value that represents the segmentation class.

Please inspect each pixel value of the mask image.

---

_[View the full topic](https://forums.developer.nvidia.com/t/fail-with-transfer-learning-with-unet-multiclass-color-images-semantic-segmentation/200498)._