The LRP Toolbox provides simple and accessible stand-alone implementations of LRP for artificial neural networks supporting Matlab and Python. The Toolbox realizes LRP functionality for the Caffe Deep Learning Framework as an extension of Caffe source code published in 10/2015.
On Numpy 1.12, numpy.reshape does not accept shapes of type float.
Traceback (most recent call last):
File "lrp_demo.py", line 73, in <module>
digit = render.digit_to_rgb(x, scaling = 3)
File "/lrp_toolbox/python/render.py", line 158, in digit_to_rgb
image = enlarge_image(vec2im(X,shape), scaling) #enlarge
File "lrp_toolbox/python/render.py", line 45, in vec2im
return np.reshape(V, shape)
File "/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line 232, in reshape
return _wrapfunc(a, 'reshape', newshape, order=order)
File "/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line 67, in _wrapfunc
return _wrapit(obj, method, *args, **kwds)
File "/usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line 47, in _wrapit
result = getattr(asarray(obj), method)(*args, **kwds)
TypeError: 'numpy.float64' object cannot be interpreted as an index
On Numpy 1.12, numpy.reshape does not accept shapes of type float.
This edit fixes the issue.