pixel-rnn-tensorflow
pixel-rnn-tensorflow copied to clipboard
Sequential generation error
Current implementation successfully works as a autoencoder but it can't generate from the beginning, from a blank image. This error should be related to masking.

(Up: ground truth, Down: prediction)
Fix with 4c459c11394657c60b12ca0371aadded5e1f208b

Even the one-shot recovering of the original image can be learned quickly as shown in previous comment, the sequential sampling of an image is still not working like igul222/pixel_rnn.
Update.

Trained model with python main.py --data=mnist --model=pixel_cnn