ins = gpu_contiguous(ins)
out = GpuDnnSoftmax('bc01', 'accurate', 'channel')(ins)
out = as_cuda_ndarray_variable(out.dimshuffle(0, 1))
return [out]
class NoCuDNNRaise(Optimizer):
def apply(self, fgraph):
""" Raise a RuntimeError if cudnn can't be used"""
if not dnn_available():
# Make an assert error as we want Theano to fail, not
# just skip this optimization.
raise AssertionError(
"cuDNN optimization was enabled, but Theano was not able"
" to use it. We got this error: \n" + dnn_available.msg)
gpu_seqopt.register("NoCuDNNRaise", NoCuDNNRaise(), 0, 'cudnn')
@register_opt('cudnn')
@local_optimizer([SoftmaxGrad])
def local_softmax_dnn_grad(node):
if (isinstance(node.op, SoftmaxGrad)
and (isinstance(node.inputs[0].owner.op, HostFromGpu)
or isinstance(node.inputs[1].owner.op, HostFromGpu))):
if not dnn_available():
return
ins = []
for n in node.inputs:
if isinstance(n.owner.op, HostFromGpu):
n = n.owner.inputs[0]
ins.append(n.dimshuffle(0, 1, 'x', 'x'))
ins = gpu_contiguous(ins)
out = GpuDnnSoftmax('bc01', 'accurate', 'channel')(ins)
out = as_cuda_ndarray_variable(out.dimshuffle(0, 1))
return [out]
class NoCuDNNRaise(Optimizer):
def apply(self, fgraph):
""" Raise a RuntimeError if cudnn can't be used"""
if not dnn_available():
# Make an assert error as we want Theano to fail, not
# just skip this optimization.
raise AssertionError(
"cuDNN optimization was enabled, but Theano was not able"
" to use it. We got this error: \n" +
dnn_available.msg)
gpu_seqopt.register("NoCuDNNRaise", NoCuDNNRaise(), 0, 'cudnn')
@register_opt('cudnn')
@local_optimizer([SoftmaxGrad])
def local_softmax_dnn_grad(node):
if (
isinstance(node.op, SoftmaxGrad)
and (isinstance(node.inputs[0].owner.op, HostFromGpu)
or isinstance(node.inputs[1].owner.op, HostFromGpu))
):
if not dnn_available():
return
ins = []
for n in node.inputs:
if isinstance(n.owner.op, HostFromGpu):
n = n.owner.inputs[0]