Low Intersection over Union (mIOU) metric on Unet Classifier.

[TimG]

Hello

I have replicated the code on this training example

https://developers.arcgis.com/python/sample-notebooks/land-cover-classification-using-sparse-trainin...

And are interested in the F1 and mIOU metrics. The example shows F1 metrics which for me came out similar (but not exactly) to the example. They are all in the around 90 mark, all good.  My question is when, I run the mIOU score, the scores are 30 or less. Which would seem really low compared to F1.  Why are the mIOU scores so low?

Many thanks

I am running arcgis 1.8.2 and fastai 1.0.60

[Anonymous User]

Hey,

May I know the size of data you are using. Also, if you can share the results, data, and model you trained (if possible) it will help me further investigate the issue.