zhangqianhui / conditional-gan Goto Github PK

Hi, I get the following error while running python main.py --operation 1 , using MNIST dataset.

Traceback (most recent call last):
File "main.py", line 30, in
tf.app.run()
File "/Users/Ido/tensorflow/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 27, in main
, model_path= FLAGS.model_path , visua_path=FLAGS.visua_path)
File "/Users/Ido/Conditional-Gans/model_mnist.py", line 37, in dcgan
data_array , data_y = load_mnist(data_name)
File "/Users/Ido/Conditional-Gans/utils.py", line 48, in load_mnist
y_vec[i, y[i]] = 1
IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices

Any ideas?
Thanks!

Please see the comment on line

There is no "10" in the next line of code. Instead this comment belongs to method "dis_net" and it should be just above the line conv1, w1 = conv2d(concat_data, output_dim=10, name='dis_conv1')
where 10 does indeed mean the number of labels.

On this line :

Otherwise, why does this create variables and then neglects to use them?

As far as I've understood, the architecture of the generator in this implementation mainly consists of two fully-connected layers and two "deconvolutional" ones.
However, in the DCGAN paper, the generator consists of four deconvolutional layers (more correctly would be saying "fractionally-strided convolutions").
Why such choice?

Many type errors.

since tf1.0 is ready and will be stable, I suggest to update the code with tf1.0

i have tried to run your code but it give this error. can you help to solve this problem?

TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64