rlkelly
commented
8 years ago Input and Output images must both be 2-dimensional, 3-dimensional, etc.
If you go into image-analogies/main.py you'll see on line 65 the method for getting dimensions from from image_analogy import img_utils, vgg16 and this will help to troubleshoot the problem.
6o6o
I get this error when I run the app with images I insert, I check with numpy/cv2 and they have the same shape, so I was wondering where this error is coming from?
Using Theano backend. /usr/local/lib/python2.7/site-packages/theano/tensor/signal/downsample.py:6: UserWarning: downsample module has been moved to the theano.tensor.signal.pool module. "downsample module has been moved to the theano.tensor.signal.pool module.") Theano CPU mode detected. Forcing a-scale-mode to "match" Using PatchMatch model Scale factor 0.25 "A" shape (1, 4, 132, 186) "B" shape (1, 3, 132, 186) Building loss... Precomputing static features... Traceback (most recent call last): File "/usr/local/bin/make_image_analogy.py", line 27, in
image_analogy.main.main(args, model_class)
File "/usr/local/lib/python2.7/site-packages/image_analogy/main.py", line 69, in main
model.build(a_image, ap_image, b_image, (1, img_num_channels, img_height, img_width))
File "/usr/local/lib/python2.7/site-packages/image_analogy/models/nnf.py", line 17, in build
loss = self.build_loss(a_image, ap_image, b_image)
File "/usr/local/lib/python2.7/site-packages/image_analogy/models/nnf.py", line 55, in build_loss
all_a_features, all_ap_image_features, all_b_features = self.precompute_static_features(a_image, ap_image, b_image)
File "/usr/local/lib/python2.7/site-packages/image_analogy/models/base.py", line 53, in precompute_static_features
all_a_features = self.get_features(a_image, a_layers)
File "/usr/local/lib/python2.7/site-packages/image_analogy/models/base.py", line 62, in get_features
feature_outputs = f([x])
File "/usr/local/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 384, in call
return self.function(inputs)
File "/usr/local/lib/python2.7/site-packages/theano/compile/function_module.py", line 871, in call
storage_map=getattr(self.fn, 'storage_map', None))
File "/usr/local/lib/python2.7/site-packages/theano/gof/link.py", line 314, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/usr/local/lib/python2.7/site-packages/theano/compile/function_module.py", line 859, in call
outputs = self.fn()
ValueError: The hardcoded shape for the image stack size (3) isn't the run time shape (4).
Apply node that caused the error: ConvOp{('imshp', (3, 134, 188)),('kshp', (3, 3)),('nkern', 64),('bsize', None),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', None),('unroll_kern', None),('unroll_patch', True),('imshp_logical', (3, 134, 188)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}(IncSubtensor{InplaceSet;::, ::, int64:int64:, int64:int64:}.0, <TensorType(float32, 4D)>)
Toposort index: 26
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(1, 4, 134, 188), (64, 3, 3, 3)]
Inputs strides: [(403072, 100768, 752, 4), (108, 36, 12, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Elemwise{Composite{(i0 \ (Abs((i1 + i2)) + i1 + i2))}}[(0, 1)](TensorConstant{%281, 1, 1, 1%29 of 0.5}, ConvOp{%28'imshp', %283, 134, 188%29%29,%28'kshp', %283, 3%29%29,%28'nkern', 64%29,%28'bsize', None%29,%28'dx', 1%29,%28'dy', 1%29,%28'out_mode',),('unroll_batch', None),('unroll_kern', None),('unroll_patch', True),('imshp_logical', (3, 134, 188)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}.0, Reshape{4}.0)]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer): File "/usr/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 496, in get_output X = self.get_input(train) File "/usr/local/lib/python2.7/site-packages/keras/layers/core.py", line 175, in get_input previous_output = self.previous.get_output(train=train) File "/usr/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 312, in get_output X = self.get_input(train) File "/usr/local/lib/python2.7/site-packages/keras/layers/core.py", line 175, in get_input previous_output = self.previous.get_output(train=train) File "/usr/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 763, in get_output X = self.get_input(train) File "/usr/local/lib/python2.7/site-packages/keras/layers/core.py", line 175, in get_input previous_output = self.previous.get_output(train=train) File "/usr/local/lib/python2.7/site-packages/keras/layers/convolutional.py", line 317, in get_output filter_shape=self.W_shape) File "/usr/local/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 624, in conv2d filter_shape=filter_shape)
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.