some questions about datasets about voxel-dcgan HOT 11 CLOSED

Sorry for late. We can solve it by setting nvx to 256 in config.py

Solved it . thanks

from voxel-dcgan.

Three output data are in out folder, but I don't have input data. Sorry. We have to write code for saving input data.

from voxel-dcgan.

Three output data are in out folder, but I don't have input data. Sorry. We have to write code for saving input data.

thanks for your reply, your project's input and output file's type are also *.binvox, is it right? And I also
meet this problem as follows:
Traceback (most recent call last):
File "train.py", line 18, in
model.optimize(z, x)
File "/home/voxel-dcgan/model.py", line 105, in optimize
self.sess.run(self.optD, feed_dict=fd)
File "/home/anaconda3/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/anaconda3/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1093, in _run
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
File "/home/anaconda3/envs/tensorflow/lib/python2.7/site-packages/numpy/core/numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.

from voxel-dcgan.

Yes. Output file type is binvox. To reproduce the error on my environment, cloud you tell me tensorflow version? Maybe, tensorflow==1.15 works.

from voxel-dcgan.

Yes. Output file type is binvox. To reproduce the error on my environment, cloud you tell me tensorflow version? Maybe, tensorflow==1.15 works.

the version I used is tensorflow1.14,python2.7.Could you please tell me your enviroments? include the version of tensorflow , numpy ,and so on?
look forward to your reply

from voxel-dcgan.

I tested tensorflow 1.15 with python 2.7.
This is output of pip list:

Package              Version    
-------------------- -----------
absl-py              0.9.0      
astor                0.8.1      
backports.weakref    1.0.post1  
enum34               1.1.6      
funcsigs             1.0.2      
functools32          3.2.3.post2
futures              3.3.0      
gast                 0.2.2      
google-pasta         0.1.8      
grpcio               1.26.0     
h5py                 2.10.0     
Keras-Applications   1.0.8      
Keras-Preprocessing  1.1.0      
Markdown             3.1.1      
mock                 3.0.5      
numpy                1.16.5     
opt-einsum           2.3.2      
pip                  19.3.1     
protobuf             3.11.2     
setuptools           42.0.2     
six                  1.13.0     
tensorboard          1.15.0     
tensorflow           1.15.0     
tensorflow-estimator 1.15.1     
termcolor            1.1.0      
Werkzeug             0.16.0     
wheel                0.33.6     
wrapt                1.11.2

from voxel-dcgan.

ok,thanks very much, it's the problem of enviroment, do you konw this errors? it as follows:
ValueError: Cannot feed value of shape (1, 32, 32, 32, 1) for Tensor u'x0:0', which has shape '(64, 32, 32, 32, 1)'

from voxel-dcgan.

We need to change batch_size to 1 in config.py
https://github.com/maxorange/voxel-dcgan/blob/master/config.py

from voxel-dcgan.

We need to change batch_size to 1 in config.py
https://github.com/maxorange/voxel-dcgan/blob/master/config.py
I've tried, But it not work. The error is :
ValueError: Cannot feed value of shape (1, 256, 256, 256, 1) for Tensor u'x0:0', which has shape '(1, 32, 32, 32, 1)'

from voxel-dcgan.

do you have solved it?

from voxel-dcgan.

Sorry for late. We can solve it by setting nvx to 256 in config.py

from voxel-dcgan.