edge-connect

edge-connect copied to clipboard

Hello ~ In the paper, the 1)G1, 2)G2 are trained separately and then 3)trained jointly. Finally 4)D1 is removed and G1,G2 are trained jointly with lower LR. There are four...

songzihang

 I'm trying it with one image, but process is long running. Is this normally? Thank you for your kind.

YoukiTakemoto

KeyError during the process of training

18

Hi, Knazeri. Thank you for your great work. I have a problem while I'm training the model with code `python train.py --model 1 --checkpoints ./checkpoints/celeba` it shows that : I...

Sherlockyyf

First of all, I would like to congratulate you on your achievements and thank you for exposing the code to provide quick learning for future generations. After the analysis, I...

Guanyunlph

Hello, I want to ask why when I was evaluating, why did the following happen?Is it because I am evaluating the image of the dataset to be 178x218 instead of...

wkkkkkx

Dear author, Thank you very much for your code, but I have some questions about model==2: The input of this model is the incomplete_image+edge_image, the edge_image is the complete_image's edge....

wangrong97

compared with CA version2:deepFill v2

1

Hi, Sorry to bother.But I'm really curious about which is better when compared with deepFill v2.Have you ever tested that?

tangeroo

How to add strokes like this?

decajcd

some question about MAX_ITERS parameter.

1

My computer configuration is not very good, but MAX_ITERS default is 2e6, Is this parameter too big?Not only does this take a lot of time to train, but it should...

695874419

thanks for you code. i found The resulting picture is not very clear.Do you know why? I used the model downloaded from your repo.The right eye is very blurred. ...

primejava