The program has run successfully, how to train my own new data model?

[cookanger]

Because the face is very European and American, I want to create Asian face

[cookanger]

https://blog.csdn.net/u010034154/article/details/107136605

[QNeverSayNever]

I can’t download the pre-trained model here. How do I download it?

[cookanger]

I can’t download the pre-trained model here. How do I download it?

Finally, you will need an internet connection the first time you run the code as it will automatically download the relevant pretrained model from Google Drive (if it has already been downloaded, it will use the local copy). In the event that the public Google Drive is out of capacity, add the files to your own Google Drive instead; get the share URL and replace the ID in the https://drive.google.com/uc?=ID links in align_face.py and PULSE.py with the new file ids from the share URL given by your own Drive file.

That's what I did:
log in to Google Drive in browser, then visit the download link in the code, and get a file

[cookanger]

I can’t download the pre-trained model here. How do I download it?

the pre-trained model I downloaded is in "cache" directory of the repository ( https://gitee.com/cookanger/pulse )

[QNeverSayNever]

I can’t download the pre-trained model here. How do I download it?

the pre-trained model I downloaded is in "cache" directory of the repository ( https://gitee.com/cookanger/pulse )

the download was successful, thank you very much

[jameswangcnbj]

my project is cuda out of memory,my cuda is 1GB ，your card setting ?how much GB at least i got the machine? ths

[0xinit]

@cookanger How did you train the model on your own dataset?

[ss24cs]

I got same question, how training own face dataset and get my own weight or model? The training demo is?

[mandeepk3335]

Please tell me how to use this code.i am unable to Use this