Closed vinduon closed 3 years ago
- Firstly, I will train my own psp encode using pSp repo with my sub-data only (not full FFHQ, only Asian woman).
- Then, use that pre-trained psp encode in SAM. Train SAM again with my sub-data (also only Asian woman).
I believe that this may help in your case.
- Firstly, I will train my own psp encode using pSp repo with my sub-data only (not full FFHQ, only Asian woman).
- Then, use that pre-trained psp encode in SAM. Train SAM again with my sub-data (also only Asian woman).
I believe that this may help in your case.
Oh thank you for your reply. I will report to you after experiment. Many thanks, sir!
- Firstly, I will train my own psp encode using pSp repo with my sub-data only (not full FFHQ, only Asian woman).
- Then, use that pre-trained psp encode in SAM. Train SAM again with my sub-data (also only Asian woman).
I believe that this may help in your case.
Oh thank you for your reply. I will report to you after experiment. Many thanks, sir!
Do it work?
Hi sir,
I have a question about inference procedure. The model seems to be very good at age transformation. However, in terms of gender, there are some problems in my case.
I filter and get all Asian woman from FFHQ dataset (I call this sub-data). Then, I use all your pre-trained models (psp encode, sam age, ...) to inference on my sub-data. The age transformation seems to be very good. However, the gender of original image seems not to be preserved. For example:
The origin is female but it transforms into male. This issue affects much on target_ages = 30,40,50. So my idea to fix this is:
Could you give me your perspectives and feedback for this idea to preserve gender? Thank you, sir.