Execution on CPU - Githubissues

ESanchezLozano / GANnotation

GANnotation (PyTorch): Landmark-guided face to face synthesis using GANs (And a triple consistency loss!)

Other

194 stars 30 forks source link

Execution on CPU #15

Open sparshgarg23 opened 2 years ago

sparshgarg23 commented 2 years ago

I am running the code on CPU by setting enable cuda to false,on execution i was presented initalizing weights normal.and then it started counting,is this behaviour normal while running code on CPU.Should i try running it on colab? sample 2

sparshgarg23 commented 2 years ago

Hi,the execution ended and a video file was created but the landmarks were not annotated on that video. A test_1 cropped file was created.In accordance are there total 66 landmarks created for the face? Let me know if there was something went wrong here. Note I didn't disable the visualization by setting Visdom --False,I just executed python demo_gannotation.py

ESanchezLozano commented 2 years ago

Hi,

Sorry for the late reply, just noticed this issue. The landmarks in the generated video are exactly those parsed as input. You need to send a set of landmarks following from some video to convert the target image :)