balgot / ib031-cifar10

Classifying CIFAR-10 dataset using simple classifiers
0 stars 0 forks source link

LEARNING: implement new model #28

Closed balgot closed 4 years ago

balgot commented 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

balgot commented 4 years ago

Probable categories merge might be computed from the average image using skimage.metrics.structural_similarity or rmse()