Closed balgot closed 4 years ago
Create new model which will merge some categories to one (let's say <dog, cats> <ships, planes> ...) based on some metrics, achieve high accuracy on those categories and then will run sub-model to differentiate between merged categories
Probable categories merge might be computed from the average image using skimage.metrics.structural_similarity or rmse()
skimage.metrics.structural_similarity
Create new model which will merge some categories to one (let's say <dog, cats> <ships, planes> ...) based on some metrics, achieve high accuracy on those categories and then will run sub-model to differentiate between merged categories