samaonline / Hierarchical-Model-for-Long-term-Video-Prediction

Given the previous frames of the video as input, we want to get the long-term frame prediction.
Apache License 2.0
31 stars 7 forks source link

analogy network doesn't work #4

Open kikyou123 opened 7 years ago

kikyou123 commented 7 years ago

when i run your analogy_network.ipynb, the code output is all zero? i don't understand why? it seems it does't work.

samaonline commented 7 years ago

Thanks for posting. Would you mind showing more detailed result? Thanks!

kikyou123 commented 7 years ago

0_0

the first image is the input, the second image is the groundtruth, the last image is the generation

samaonline commented 7 years ago

This looks somewhat weird... What we tried in paper are gray scale images.

kikyou123 commented 7 years ago

but there is something wrong, you read image is rgb, how can you reshape it to [224, 224, 1]. would you provide .py that can be excused?