@bipin The Autoencoder takes 8x8x3 volumes(ht,wd,ch) and compresses it down to 1x1x4 vector this is the reason. check out jono’s video - Lesson 2 A and the notebook ` section The Autoencoder(AE)
4 Likes
@bipin The Autoencoder takes 8x8x3 volumes(ht,wd,ch) and compresses it down to 1x1x4 vector this is the reason. check out jono’s video - Lesson 2 A and the notebook ` section The Autoencoder(AE)