errors when running the code

[chouyiyu]

Hi !!
I was playing with your cyclegan code but I got the following error message:

File "./mnist_test.py", line 254, in
test_cyclegan()
File "./mnist_test.py", line 182, in test_cyclegan
cat_out = generator_cats.predict(mnist_in)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1713, in predict
verbose=verbose, steps=steps)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1269, in _predict_loop
batch_outs = f(ins_batch)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2273, in call
**self.session_kwargs)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: image must have at least one channel
[[Node: up_sampling2d_1/ResizeNearestNeighbor = ResizeNearestNeighbor[T=DT_FLOAT, align_corners=false, _device="/job:localhost/replica:0/task:0/gpu:0"](leaky_re_lu_23/sub, up_sampling2d_1/mul)]]
[[Node: conv2d_27/Sigmoid/_59 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_4095_conv2d_27/Sigmoid", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

Caused by op u'up_sampling2d_1/ResizeNearestNeighbor', defined at:
File "./mnist_test.py", line 254, in
test_cyclegan()
File "./mnist_test.py", line 111, in test_cyclegan
generator_cats = mnist_generator(mnist_shape)
File "/ISFILE3/USERS/chouy/Projects/DeepLearning/cycleGAN/example2/cyclegan/models.py", line 62, in mnist_generator
x = UpSampling2D(size=(2, 2))(x)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 602, in call
output = self.call(inputs, **kwargs)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/layers/convolutional.py", line 1361, in call
self.data_format)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1768, in resize_images
x = tf.image.resize_nearest_neighbor(x, new_shape)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_image_ops.py", line 927, in resize_nearest_neighbor
name=name)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/USERS/chouy/Applications/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): image must have at least one channel
[[Node: up_sampling2d_1/ResizeNearestNeighbor = ResizeNearestNeighbor[T=DT_FLOAT, align_corners=false, _device="/job:localhost/replica:0/task:0/gpu:0"](leaky_re_lu_23/sub, up_sampling2d_1/mul)]]
[[Node: conv2d_27/Sigmoid/_59 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_4095_conv2d_27/Sigmoid", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

---

Any suggestions ??
Thank you !!

Yiyu

[Alec Graves]

Not exactly sure what it is, but you should try an earlier version of tensorflow. It sounds like the upsample operation is expecting different arguments.
I am not sure exactly what version of tensorflow/keras I built this for. I intended it as more of a proof-of-concept.