Did not get good result from the model you provide.

run-youngjoo / SC-FEGAN

SC-FEGAN : Face Editing Generative Adversarial Network with User's Sketch and Color (ICCV2019)

Other

3.35k stars 530 forks source link

Did not get good result from the model you provide. #39

Open swagzhang opened 5 years ago

swagzhang commented 5 years ago

Hi, I tried this demo with model u provide, but the result is not good. However, the result u showed below are quite good. I wonder it is my personal problem or the trained model is not as same as what you use to generate these samples?

abtExp commented 5 years ago

The examples shown in the paper just like every other paper are the best generations from the model and are obtained by several finetunings so you can't expect the model to generalize in all cases. You can further train the model to get better results. But again the training code isn't provided so bad luck there. I've been working on recreating the code in keras but due to lack of time I've been stuck, so fingers crossed if I can get the code complete.

redaghanem commented 4 years ago

@lz2470 hi, you run and test this code

can you help me, I get this error when trying to run !python demo.py

i use google colab

qt.qpa.xcb: could not connect to display qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "" even though it was found. This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

Available platform plugins are: eglfs, linuxfb, minimal, minimalegl, offscreen, vnc, wayland-egl, wayland, wayland-xcomposite-egl, wayland-xcomposite-glx, webgl, xcb.