def local_abstractconv_gemm(node):
# If theano.config.blas.ldflags is empty, Theano will use
# a NumPy C implementation of [sd]gemm_.
if theano.config.cxx == "" or node.inputs[0].dtype == "float16":
return
if not isinstance(node.op, AbstractConv2d):
return None
img, kern = node.inputs
if not isinstance(img.type, TensorType) or not isinstance(
kern.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
flip = (slice(None), ) * (kern.ndim - 2) + (slice(None, None,
-1), ) * 2
kern = kern[flip]
rval = CorrMM(
border_mode=node.op.border_mode,
subsample=node.op.subsample,
filter_dilation=node.op.filter_dilation,
num_groups=node.op.num_groups,
unshared=node.op.unshared,
)(img, kern)
copy_stack_trace(node.outputs[0], rval)
return [rval]
def run_conv_valid(self, inputs_shape, filters_shape,
border_mode='valid',
filter_dilation=(1, 1),
subsample=(1, 1),
verify_grad=False):
inputs_shape = [inputs_shape[i] for i in (0, 3, 1, 2)]
filters_shape = [filters_shape[i] for i in (0, 3, 1, 2)]
inputs_val = np.random.random(inputs_shape).astype(config.floatX)
filters_val = np.random.random(filters_shape).astype(config.floatX)
inputs = gpuarray_shared_constructor(inputs_val)
filters = gpuarray_shared_constructor(filters_val)
conv_ref = CorrMM(border_mode=border_mode,
filter_dilation=filter_dilation,
subsample=subsample)(ref_cast(inputs),
ref_cast(filters))
f_ref = theano.function([], conv_ref, mode=mode_without_gpu)
conv = GpuCorrMM(border_mode=border_mode,
filter_dilation=filter_dilation,
subsample=subsample)(inputs, filters)
f = theano.function([], conv, mode=mode_with_gpu)
res_ref = f_ref()
res = f()
utt.assert_allclose(res_ref, res)
if verify_grad:
utt.verify_grad(GpuCorrMM(border_mode=border_mode,
filter_dilation=filter_dilation,
subsample=subsample),
[inputs_val, filters_val])
def local_abstractconv_gemm(node):
if not isinstance(node.op, AbstractConv2d):
return None
img, kern = node.inputs
if not isinstance(img.type, TensorType) or \
not isinstance(kern.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1]
rval = CorrMM(border_mode=node.op.border_mode,
subsample=node.op.subsample)(img, kern)
return [rval]
def local_abstractconv_gemm(node):
if theano.config.cxx == "" or not theano.config.blas.ldflags:
return
if not isinstance(node.op, AbstractConv2d):
return None
img, kern = node.inputs
if not isinstance(img.type, TensorType) or \
not isinstance(kern.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1]
rval = CorrMM(border_mode=node.op.border_mode,
subsample=node.op.subsample)(img, kern)
copy_stack_trace(node.outputs[0], rval)
return [rval]
def local_abstractconv_gemm(node):
# If theano.config.blas.ldflags is empty, Theano will use
# a NumPy C implementation of [sd]gemm_.
if theano.config.cxx == "" or node.inputs[0].dtype == 'float16':
return
if not isinstance(node.op, AbstractConv2d):
return None
img, kern = node.inputs
if not isinstance(img.type, TensorType) or \
not isinstance(kern.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1]
rval = CorrMM(border_mode=node.op.border_mode,
subsample=node.op.subsample,
filter_dilation=node.op.filter_dilation)(img, kern)
copy_stack_trace(node.outputs[0], rval)
return [rval]
