The course of true love never did run smooth about ugatit HOT 17 CLOSED

@hitechbeijing

Please turn down Iteration, Epoch and Batchsize

I'm using the default setting, epoch=100,iteration=10000,batch_size=1

p.s. 1 year is too long to me...

try epoch=10,iteration=1000,batch_size=1

from ugatit.

Can you please tell me how did you train it? I cant train it.

from ugatit.

Please turn down Iteration, Epoch and Batchsize

from ugatit.

I have not get the best result yet
and it will not take your lifetime, if use Intel Core i7 without a deep learning GPU, it will take up to 1 year.

from ugatit.

@hitechbeijing

Please turn down Iteration, Epoch and Batchsize

I'm using the default setting, epoch=100,iteration=10000,batch_size=1

p.s. 1 year is too long to me...

from ugatit.

What datasets are you using?

from ugatit.

What datasets are you using?

selife2anime

from ugatit.

Could you link that?

from ugatit.

@hitechbeijing hi, could you link the database u r using?

from ugatit.

I have tested the NVIDIA Tesla V100, it just 4 times faster than desktop CPU. and as faster as intel Xeon gold CPU.

from ugatit.

Cool but could you upload and link the dataset you're using

from ugatit.

Cool but could you upload and link the dataset you're using

see #6 ,and you can use tesla T4 or P4, no need v100, but you must have more than 30G free memory, and 8 core CPU.

from ugatit.

2080ti： each epoch takes 2 hours

from ugatit.

2080ti： each epoch takes 2 hours

increase batchsize?

from ugatit.

2080ti： each epoch takes 2 hours

increase batchsize?
light=True， epoch=100， iteration=10000， batch_size=1

from ugatit.

2080ti： each epoch takes 2 hours

increase batchsize?
light=True， epoch=100， iteration=10000， batch_size=1

am not turn on light. I think it is the reason for slow.

from ugatit.

1. We released 50 epoch and 100 epoch checkpoints so that people could test more widely.

2. Also, We published the selfie2anime datasets we used in the paper.

3. And, we fixed code in smoothing

4. In the test image, I recommend that your face be in the center.

from ugatit.