BaseModel problem #3
Description
Hello,I run your code as you describe.But when I run tests.py, I find that the terminal print the information 'too many indices for array,====== [ ERROR: Caffe was not found. Continuing... ] ======'.I am sure this is not caused by caffe path.So when I debug the code, I find it is caused by the code 'self.forward = theano.function([symbolic_input], outputs)'. and I wonder that why the nOutputs is set to 1,this cause 'print np.sum((fprop[fprop.keys()[0]][:,:,0,0] - outlist[-1])**2)' in test_similarity function of test.py arise that error. Then I turn the code 'outputs = [lay.get_output() for lay in self.all_layers[:nOutputs]] ' into outputs = layers.get_output(self.all_layers[-1]), but it still has problem,ImportError: ('The following error happened while compiling the node', <pylearn2.sandbox.cuda_convnet.filter_acts.FilterActs object at 0xba168d0>(GpuContiguous.0, GpuContiguous.0), '\n', '/home/scw4150/.theano/compiledir_Linux-3.2--generic-x86_64-with-Ubuntu-12.04-precise-x86_64-2.7.3-64/tmpzKRg5C/7e4013877baee663026e238eedaae7fa.so: undefined symbol: _ZN8NVMatrixC1EPK11CudaNdarrayiiPKc', '[<pylearn2.sandbox.cuda_convnet.filter_acts.FilterActs object at 0xba168d0>(<CudaNdarrayType(float32, 4D)>, <CudaNdarrayType(float32, 4D)>)]')