search

menyifang / ADGAN

The Implementation of paper "Controllable Person Image Synthesis with Attribute-Decomposed GAN" CVPR 2020 (Oral); Pose and Appearance Attributes Transfer;
476 stars 90 forks source link

Not able to reproduce the result #9

Closed nitthilan closed 4 years ago

nitthilan commented 4 years ago

I am not able to reproduce the results using the pre-trained models. fashionWOMENJackets_Coatsid0000417103_1front jpg___fashionWOMENJackets_Coatsid0000417103_2side jpg_vis

The above is the output I am getting. Can you predict why I am getting this issue?

nitthilan commented 4 years ago

The problem is already addressed

nitthilan commented 4 years ago

It is addressed in this issue: https://github.com/menyifang/ADGAN/issues/6

It was due to the number of GPUS. Use 2 GPUs using the pre-trained model.