Open shukkkur opened 2 years ago
Hey, @shukkkur did you get any promising results further? This really looks scary tho :P
Thanks, Kritika
Hi @Kritz23! It's been awhile ago, so I don' really remember. My guess would be to use images with face looking directly at the camera, but I am probably wrong) So good luck!
So, I downloaded the pre-trained model (link in README).
0
insidemydata
folder and added their my photos (000001.jpg
,000002.jpg
...)2) Created landmarks using this line:
python process_data.py --input ../mydata --output ../output/
3) And the run thetest.py file
python test.py --data ../output/ --out ../output
So here are the results:
I mean, one of the advantages of this paper was creating a new identity and another face detection algorithm will probably detect these faces, however the other advantage was realistic results, but the faces I get are a bit intimidating.
Am I doing everything correctly? Also, how can I insert these new faces into original images? Any help, pointer or code is appreciated!