-
I can get good results when I use the images in celaba-hq.But when I tested with my own pictures, I got a bad result, and I've used the image editing tool to cut the characters,so can you guide me how…
-
Hi, great work, Thanks for providing the code online. Would it be possible to also provide the parameters for the conditional ImageNet generator?
-
Dear developers,
Thanks for your contribution for building this package. But I have met some problems, could you please help me?
I want to build a pipeline which can read images from a directory, …
-
I noticed that the loss function is set to wp_gan by default. however, in the official implementation, the loss is set to r1 by default. Is that correct? If so why did you choose that?
-
I got this error while doing the testing. Please help me out here.
Traceback (most recent call last):
File "test.py", line 79, in
vars_list))
File "test.py", line 78, in
assign_ops …
Haoru updated
5 years ago
-
Hi nperraud,
Thanks for your code, I'm running the make_HQ_images.py without any problem, but the result is not a single subject 1024by1024 image but a 3by3 replication of the subject(and the image i…
-
@shepnerd ,hello. Thanks for your great work and also looking forward to paper ' Semantic Regeneration Network' .
Since gmcnn has a huge amount of parameters, i wonder how much time you spend on trai…
cmyyy updated
5 years ago
-
Hi,
thank you for this code !
I have an error in the make_celeba_hQ.py
Traceback (most recent call last):
File "/cvmfs/soft.computecanada.ca/easybuild/software/2017/Core/python/3.5.4/lib/pyt…
-
In your datasets, how many epochs did you need to train to get these reasonable results ?
Thanks.
-
Hello,@JiahuiYu.
I'm curious about the performance of deepfill2 on celeba-HQ, when the mask is regular, so could you share the pretrained model?Or would you mind sending me the inpaintng results when…
cmyyy updated
5 years ago