view_generative_model.py fail to generate animation

[longjie]

Hi,

I have successfully trained the transition model.
Now I'm going to generate the gif of the predicted image.
I followed instructions:

$ ./server.py --time 60 --batch 64
$ ./view_generative_model.py transition --name transition

I got an error:

loading weights...
Traceback (most recent call last):
  File "./view_generative_model.py", line 71, in <module>
    x = X.reshape((sh[0], args.time, 80, 160, 3))
ValueError: cannot reshape array of size 147456000 into shape (64,1,80,160,3)

I thought I may need to make the input size matched, I add time and batch options as:

$ ./view_generative_model.py transition --name transition --batch 64 --time 60

I got another error:

loading weights...
Sampling...
  0%|                                                   | 0/128 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "./view_generative_model.py", line 83, in <module>
    code = sess.run([E_out[0]], feed_dict={I: x, K.learning_phase(): 1})[0]
  File "/home/tajima/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 766, in run
    run_metadata_ptr)
  File "/home/tajima/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 943, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (3840, 80, 160, 3) for Tensor u'transition/input_1:0', which has shape '(960, 80, 160, 3)'

How can I make it work?

[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)