umerebryx
commented
8 years ago I solved this, apparently in Keras 1.0.2 get_output() is deprecated. Change the following code in model.base.py: self._f_layer_outputs[name] = layer.get_output() to self._f_layer_outputs[name] = layer.output
worked for me.
While running one of the example scripts I am running into following issue:
./render-example.sh arch ../vgg16_weights.h5 Only using analogy loss Using Theano backend. Using gpu device 0: Tesla K80 (CNMeM is enabled with initial size: 90.0% of memory, CuDNN 3007) Using brute-force model Scale factor 0.25 "A" shape (1, 3, 116, 80) "B" shape (1, 3, 128, 89) Building loss... Precomputing static features... Traceback (most recent call last): File "/usr/local/bin/make_image_analogy.py", line 5, in
pkg_resources.run_script('neural-image-analogies==0.0.11', 'make_image_analogy.py')
File "/usr/lib/python2.7/dist-packages/pkg_resources.py", line 528, in run_script
self.require(requires)[0].run_script(script_name, ns)
File "/usr/lib/python2.7/dist-packages/pkg_resources.py", line 1401, in run_script
exec(script_code, namespace, namespace)
File "/usr/local/lib/python2.7/dist-packages/neural_image_analogies-0.0.11-py2.7.egg/EGG-INFO/scripts/make_image_analogy.py", line 27, in
File "build/bdist.linux-x86_64/egg/image_analogy/main.py", line 69, in main File "build/bdist.linux-x86_64/egg/image_analogy/models/base.py", line 23, in build File "build/bdist.linux-x86_64/egg/image_analogy/models/analogy.py", line 23, in build_loss File "build/bdist.linux-x86_64/egg/image_analogy/models/base.py", line 53, in precompute_static_features File "build/bdist.linux-x86_64/egg/image_analogy/models/base.py", line 61, in get_features File "build/bdist.linux-x86_64/egg/image_analogy/models/base.py", line 72, in get_layer_output AttributeError: 'Convolution2D' object has no attribute 'get_output'
Any idea what is wrong here. Any help would be really appreciated. Thanks