view_generative_model.py fail to generate animation about research

[zhaobaozi]

hi.i meet the same problem,have you solve it ?thanks

[yangyuekai]

Hello.I have the same question with you.Do you solve it?Thank you very much.It will be better if you could help me to solve it.

[Ling-wei]

Hi, I have solved this problem by using the following instructions:
$ ./server.py --time 15 --batch 7 $ ./view_generative_model.py --name transition --time 15 --batch 7
You can have a try.

[yangyuekai]

oh.I have tried it.But,there is a warning: ValueError:Cannot feed value of shape(35,512)for Tensor u'transition/dense_input_1:0',which has shape '(98,512)'.So,did you have changed code ? It is hepld me very much.Thanks!

[Ling-wei]

@yangyuekai
Hi, I didn't change the code from github. I guess your problem from this command( line 87 ) imgs = sess.run([G_out], feed_dict={O: outs.reshape((-1, z_dim)), K.learning_phase(): 1})[0]
The shape of G_out is (98,512) and the feed_dict which is the output of transition model should also be like this. You can check if something wrong when training the transition model because when I ran the command ./view_generative_model.py transition --time 15 --batch 7
the screen output T.shape: (7, 14, 512), maybe your model made some mistake and had a wrong output just like T.shape: (7, 5, 512)