# Can I generate my own brand new segmentation model by training without loading the pre trained model?

**URL:** <https://discourse.slicer.org/t/can-i-generate-my-own-brand-new-segmentation-model-by-training-without-loading-the-pre-trained-model/33368>\
**Category:** Support\
**Tags:** monailabel\
**Created:** [December 12, 2023, 7:04pm UTC](https://discourse.slicer.org/t/can-i-generate-my-own-brand-new-segmentation-model-by-training-without-loading-the-pre-trained-model/33368 "2023-12-12T19:04:44Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![xiang\_yao](https://sea2.discourse-cdn.com/flex002/user_avatar/discourse.slicer.org/xiang_yao/32/68673_2.png) [@xiang\_yao](https://discourse.slicer.org/u/xiang_yao)\
**Post date:** [December 12, 2023, 7:04pm UTC](https://discourse.slicer.org/t/can-i-generate-my-own-brand-new-segmentation-model-by-training-without-loading-the-pre-trained-model/33368/1 "2023-12-12T19:04:44Z")

</div>

I would like to use MonAILabel to create a new model for segmenting the bone gray matter of vertebrae L1, L2, and L3. May I ask if I have modified the self labels in segmention.py{  
“Background”: 0,  
“SegmentionL1”: 1,  
“SegmentionL2”: 2,  
“SegmentionL3”: 3,  
}And if strtobool  
(self. conf. get (“use\_pretrained\_model”, “false”):,  
How to train without loading pre trained models and generate your own brand new segmentation model? In fact, after trying it out, I found that it did not work