search

mingyuliutw / UNIT

Unsupervised Image-to-Image Translation
Other
1.99k stars 362 forks source link

Feature request: Rectangular images #19

Closed slundell closed 6 years ago

slundell commented 6 years ago

As far as I understand, in the current version only image sets consisting of images where width == height are properly supported. Current workaround would be to pre- and post-scale aspect ratios or add padding. Niether is ideal.

mingyuliutw commented 6 years ago

This is not true. Both of the generator and discriminator are fully-convolutional. It can work with no square shape.