You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I tried creating an adversarial network, when I got the following error. (I'm using python 3.5.3)
Traceback (most recent call last):
File "gan.py", line 69, in
history = model.fit(x=train_x, y=gan_targets(train_x.shape[0]), epochs=10, batch_size=batch_size)
File "/home/atul/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1581, in fit
batch_size=batch_size)
File "/home/atul/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1399, in _standardize_user_data
for output_shape, loss_fn in zip(self._feed_output_shapes, self._feed_loss_fns):
AttributeError: 'AdversarialModel' object has no attribute '_feed_output_shapes'
The text was updated successfully, but these errors were encountered:
Happened with me when I installed it using pip. Install it by cloing the repo, and it'll work. The file adversarial_model.py is different in the pip version and doesn't have _feed_output_shapes
I am getting the same error.
the environment is below.
Keras 2.1.2
keras-adversarial 0.0.3
Keras-Applications 1.0.4
Keras-Preprocessing 1.0.2
tensorflow 1.8.0
I tried creating an adversarial network, when I got the following error. (I'm using python 3.5.3)
Traceback (most recent call last):
File "gan.py", line 69, in
history = model.fit(x=train_x, y=gan_targets(train_x.shape[0]), epochs=10, batch_size=batch_size)
File "/home/atul/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1581, in fit
batch_size=batch_size)
File "/home/atul/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1399, in _standardize_user_data
for output_shape, loss_fn in zip(self._feed_output_shapes, self._feed_loss_fns):
AttributeError: 'AdversarialModel' object has no attribute '_feed_output_shapes'
The text was updated successfully, but these errors were encountered: