Open alexshepard opened 4 months ago
I made a comparison between three different preprocessing strategies:
here is how the "no crop, just squeeze" approach transforms an image
here is how the "central crop, then squeeze" approach transforms an image
note this is how we do things in production now
here is how the "resize with crop, no squeezing" approach transforms an image
here's a look at performance metrics across our normal categories for each approach.
based on this, I'm recommending we switch to using tf.image.resize_with_crop_or_pad
to preprocess our images. I'll make a pull request for this in the inatVisionAPI repo.
I made a PR for this here https://github.com/inaturalist/inatVisionAPI/pull/17 and requested that Patrick take a look
this came up as followup todos during the bounding box experiments.
across the clades, evaluate the following different approaches:
also, visualize the different approaches in a slide or presentation or notebook so that people know what we're talking about.