Hi
following the Guided Backpropagation recipe/example I had error for:
if theano.sandbox.cuda.cuda_enabled because, I guess, I use newer theano / lasagne versions with CuDNN etc. I have no cuda under theano.sandbox. two solutions:
- skip the if and use the else option:
maybe_to_gpu = lambda x: x
- use gpu with gpuarray.dnn
maybe_to_gpu = theano.gpuarray.dnn.as_gpuarray_variable x = maybe_to_gpu(x,None)
and then a few lines below (as above, add None as second input argument):
outp = maybe_to_gpu(self.nonlinearity(inp),None)
Thanks for the examples
Hi
following the Guided Backpropagation recipe/example I had error for:
if theano.sandbox.cuda.cuda_enabledbecause, I guess, I use newer theano / lasagne versions with CuDNN etc. I have no cuda under theano.sandbox. two solutions:maybe_to_gpu = lambda x: xmaybe_to_gpu = theano.gpuarray.dnn.as_gpuarray_variable x = maybe_to_gpu(x,None)and then a few lines below (as above, add None as second input argument):
outp = maybe_to_gpu(self.nonlinearity(inp),None)Thanks for the examples