search

akanimax / T2F

T2F: text to face generation using Deep Learning
MIT License
545 stars 101 forks source link

Image generated not good, not even comparable. #14

Open jhamukesh998 opened 5 years ago

jhamukesh998 commented 5 years ago

@akanimax @AhmedHani I trained the model till 6th depths with epoch(640,320,160,80,40,20) and batch size of 16 in each depth but the output in final pth file wasn't up to the mark. Plus it generates 16 images of a single description. Can you help it out like what exactly are those 16 images and why not a single image for a single description. The image generated isn't good as well. What can I do to improve that ? Can you provide the trained model of augmentation,encoder,gen and dis if image generated is good like you have provided for celeb using msg. I tried for various depths and resolution but the output isn't clear.

Description: he is an old man with a wrinkled face , gray hair and no beard he has dark eyes and seems happy about something

Image: he is an old man with a wrinkled face , gray hair and no beard he has dark eyes and seems happy about something

sharmahr commented 5 years ago

How did you run the model?

adorsho commented 4 years ago

how did you run this with your own descriptions ? can you please provide me that code please ? it's badly needed for me

RohanBolusani commented 4 years ago

hey, not able to run the model please help?

shiv6891 commented 4 years ago

At my end, only 5th depth appears to be generating something meaningful...Nothing before/after this depth....Could someone explain this?