Closed MartinThoma closed 7 years ago
I've upgraded to Keras 1.2.2. Now I get:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "inception_v4.py", line 215, in create_inception_v4
x = Flatten()(x)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 572, in __call__
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 166, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/usr/local/lib/python2.7/dist-packages/keras/layers/core.py", line 483, in call
return K.batch_flatten(x)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1629, in batch_flatten
x = tf.reshape(x, tf.pack([-1, prod(shape(x)[1:])]))
AttributeError: 'module' object has no attribute 'pack'
pack
has been renamed to stack
in Tensorflow 1.0 (source1, source2)
After replacing pack
by stack
in /usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py
line 1629 it worked.
When I execute
I get
Environment
CUDA 8, CuDNN 5.1, Titan Black