angelolab / Nimbus

Other
12 stars 1 forks source link

Dimensions are swapped on output #81

Closed ngreenwald closed 2 months ago

ngreenwald commented 4 months ago

Please refer to our FAQ and look at our known issues before opening a bug report.

Describe the bug "I noticed that there's a bug in the output nimbus image shape - it appears to swap x and y dimensions from the input. For example, the input image and segmentation mask for a run I had was (2924, 3285), and the resulting output nimbus image was (3295, 2924). The underlying classification looks correct, it's just the dimensions of the image that are wrong. I was using your 1_Nimbus_Predict template, and the critical line of code was cell_table = nimbus.predict_fovs()"

Expected behavior Input and output images have same shape

To Reproduce Screenshot 2024-06-11 at 1 14 02 PM

Got this from @peterjchou

JLrumberger commented 2 months ago

Should be fixed in our latest version of Nimbus-Inference