search

Ha0Tang / C2GAN

[ACM MM 2019 Oral] Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
http://disi.unitn.it/~hao.tang/project/C2GAN.html
Other
69 stars 5 forks source link

Testing of images and train for high resolution images #5

Open sandhyalaxmiK opened 4 years ago

sandhyalaxmiK commented 4 years ago

Thanks for sharing the code. The concept is good.

I want to get pose transfer of source image. For this i want to use MVC dataset (https://github.com/MVC-Datasets/MVC) contains 4 poses of images(streight view,left side view, right side view, back view). I preprocessed these images that, 1.Non-human images have to be deleted using face-detection 2.I created key-points for these images using open-pose

I want to train these images such that image A:streight view, image B: left view I have a following questions which can solve my problem to train:

  1. Suppose I trained for those two types images (streight, left view), to get a lefft view of test_image, how can I give its keypoints?? (I don't have left view of test_image. I want generate it)

  2. How to train for high resolution images??

Thanks in Advance. Regards, Sandhya

Ha0Tang commented 4 years ago

Thank you for your interest in our work.

  1. Maybe you can use any left view keypoints in your training data, or you can simply draw it.
  2. You need to change the data load so that you can load your data. Moreover, you need to change some parameters of the network so that you can train the model.