Issue on RGBD dataset

[daodaofr]

I run the mnist example without any problem.
But when I try to reimplement the example on the RGBD datset in your paper, I can't genarate the right objects. I exactly followed your parameters in your supplementary materials, but I can't get it right.
Could your please update an example for the RGBD dataset, or simply provide the .train.ptt file for me to verify my errors? That will help me a lot.
Thank you.

[mahfuj1093]

Same problem.

[mingyuliutw]

The training script belongs to Mitsubishi Electric Research Labs.
I did the experiment long time back. I think what you need to do is to

1. Resize the image to 64x64,
2. Normalize the depth range.
   • Find the max and min depth value (You have to remove outliers first)
   • Scale depth value so that max and min fall in the range of 1 to 0 if using sigmoid and 1 to -1 if using tanH.

[shivaniThakur93]

We are getting accuracy as equal to 1 after around 50 iterations. The generator model converges and does not update the images. Could you please provide insights as what might be wrong?

Could you specify what versions to use for the code to work correctly?