kidach1

Results 4 comments of kidach1

@utkarshojha thank you for reply! > Yes we did try one version for 256x256 resolution, and it was working decently well. You can simply add more upsampling layers towards the...

@utkarshojha I tried following your suggestion but things don't seem to change. ### fake_imgs[0] (background stage) ![count_000012000_fake_samples0](https://user-images.githubusercontent.com/1152893/72411137-9b253c00-37ad-11ea-81c7-e91142d71476.png) ### fake_imgs[1] (parent stage) ![count_000012000_fake_samples1](https://user-images.githubusercontent.com/1152893/72411136-9b253c00-37ad-11ea-87fc-744217078c3d.png) ### fake_imgs[2] (child stage) ![count_000012000_fake_samples2](https://user-images.githubusercontent.com/1152893/72411138-9b253c00-37ad-11ea-879d-06956012739a.png) And this is...

@utkarshojha Thank you for reply despite your busy schedule! Unfortunately, change of CROP_IMG_SIZE doesn't seem to work (though the training progress is only 25 epochs yet, generated images in each...

Yes, my build was successful. output is this: ![DeepMimicCore - Microsoft Visual Studio 2019-07-06 07 58 21](https://user-images.githubusercontent.com/1152893/60747946-03f05800-9fc4-11e9-9a3d-beb4796b134e.png)