Hello, when I try to run the codes to create the GAN model, I receive an error saying that I am unable to create a Session. Appreciate any help :)

InternalError Traceback (most recent call last)
in ()
3 disc_condition_input = Input(shape=(10,))
4
----> 5 discriminator, disc_out = get_discriminator(img_input, disc_condition_input)
6 discriminator.compile(optimizer=Adam(0.0002, 0.5), loss='binary_crossentropy', metrics=['accuracy'])
7

in get_discriminator(input_layer, condition_layer)
1 def get_discriminator(input_layer, condition_layer):
2 hid = Conv2D(128, kernel_size=3, strides=1, padding='same')(input_layer)
----> 3 hid = BatchNormalization(momentum=0.9)(hid)
4 hid = LeakyReLU(alpha=0.1)(hid)
5

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/engine/base_layer.py in call(self, inputs, **kwargs)
458 # Actually call the layer,
459 # collecting output(s), mask(s), and shape(s).
--> 460 output = self.call(inputs, **kwargs)
461 output_mask = self.compute_mask(inputs, previous_mask)
462

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/layers/normalization.py in call(self, inputs, training)
181 normed_training, mean, variance = K.normalize_batch_in_training(
182 inputs, self.gamma, self.beta, reduction_axes,
--> 183 epsilon=self.epsilon)
184
185 if K.backend() != 'cntk':

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in normalize_batch_in_training(x, gamma, beta, reduction_axes, epsilon)
1833 """
1834 if ndim(x) == 4 and list(reduction_axes) in [[0, 1, 2], [0, 2, 3]]:
-> 1835 if not _has_nchw_support() and list(reduction_axes) == [0, 2, 3]:
1836 return _broadcast_normalize_batch_in_training(x, gamma, beta,
1837 reduction_axes,

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in _has_nchw_support()
287 """
288 explicitly_on_cpu = _is_current_explicit_device('CPU')
--> 289 gpus_available = len(_get_available_gpus()) > 0
290 return (not explicitly_on_cpu and gpus_available)
291

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in _get_available_gpus()
273 global _LOCAL_DEVICES
274 if _LOCAL_DEVICES is None:
--> 275 _LOCAL_DEVICES = get_session().list_devices()
276 return [x.name for x in _LOCAL_DEVICES if x.device_type == 'GPU']
277

~/.virtualenvs/jlenv/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in get_session()
181 config = tf.ConfigProto(intra_op_parallelism_threads=num_thread,
182 allow_soft_placement=True)
--> 183 _SESSION = tf.Session(config=config)
184 session = _SESSION
185 if not _MANUAL_VAR_INIT:

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in init(self, target, graph, config)
1561
1562 """
-> 1563 super(Session, self).init(target, graph, config=config)
1564 # NOTE(mrry): Create these on first __enter__ to avoid a reference cycle.
1565 self._default_graph_context_manager = None

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in init(self, target, graph, config)
631 if self._created_with_new_api:
632 # pylint: disable=protected-access
--> 633 self._session = tf_session.TF_NewSession(self._graph._c_graph, opts)
634 # pylint: enable=protected-access
635 else:

InternalError: Failed to create session.

I just ran this code on my gpu but did not get the similar images. actually the generated images are like random noise. And I also tried it on other dataset, but the accuracy of discriminator is always close to 0. I guess it is because of mode collapse, but you have used experience replay. I'm really confused now.

Hello, may I know why is the loss function binary_crossentropy instead of categorical_crossentropy?

When changing the output image size to 128x128, what should be changed in the code ...?

Could you share def generate_random_labels()?

In cifar10cgan.ipynb, the function "generate_random_labels" is missing.

Thank you for your helpful ipynb!