zhengziqiang

@liujiaxing you can remove the pretrained_model_path and it works for me.

I have reorganized the codes, and you can generate one single image or multiple images at once.

@ak9250 I have uploaded the two files with the codes, you could download these with the added testing codes.

In our paper, we feed the model with the RGB image and geometric guidance (landmark, skeleton or even key point annotation). And for the weird results you mentioned, we have...

@ak9250 For the first case you mentioned, you should feed the model with real RGB image and geometric guidance.

You can also try other combinations by changing he path of input image or reference image. In theory, you could generate 1000*1000 images using 1000 images.

Ok, I will upload the code to extract the geometric guidance as possible as soon. Any problem for the evaluation?

@ak9250 I will also upload the code to merge all the synthesized images to a larger image, which is similar to the shown image in our paper. As you can...

To make it easier to show the reshaped results, I will upload the merge_results.py this evening.

Yeah, I just used the dlib to obtain the facial landmark.