Pradeep Rajasekhar

Thanks a lot @andreped . This is super detailed. I wasn't aware of the challenge with mitosis detection and how you use normalize instead of augment.. In regard to catching...

Thanks so much for posting all this with extensive information. Whats the lightsheet angle for this dataset and one you posted in the other issue https://github.com/clEsperanto/pyclesperanto_prototype/issues/276?

Hi @oleksiievetsno I think I've figured the issue. When using the orthogonal interpolation (default), the angles you were trying lead to negative values in the calculations which in turn caused...

Thanks @haesleinhuepf . Will do. Have a great weekend too!!

Thanks @oleksiievetsno. You are right.. So, I was playing around with the data and tried the deskew_x function. Essentially, I rotated your data by 90 degrees and then applied the...

Still investigating.. Atleast with the code, it could be due to an issue with the scan direction. I have mostly processed datasets where scan direction is - top -> bottom...

Sorry, I think I posted the wrong image above. This is the code. I've rotated it so scan direction is from top to bottom: ``` img_t0 = img[0,:,:] deskewing_angle_in_degrees =49...

Thanks for the message. The shift in Z planes should have been fixed in the branch: pip install git+https://github.com/clEsperanto/pyclesperanto_prototype.git@orthogonal_interpolation I haven't pushed it to the main one yet. Will fix...

Hi Do you mean 2.6 or 2.82? If its 2.82, the scaling factor is based on making your data isotropic pixel size in x is 0.1773018 and z is 0.5...

Hi * Scan direction of your data is Bottom to Top, so shear angle is negative. * Scaling is applied using z scaling factor (voxel_size_z/voxel_size_x) ``` img_t0 = img[0,:,:] voxel_size_x_in_microns...