def run_gradinput(self, inputs_shape, filters_shape, subsample=(1, 1, 1)):
inputs_val = numpy.random.random(inputs_shape).astype('float32')
filters_val = numpy.random.random(filters_shape).astype('float32')
inputs = shared(inputs_val)
filters = shared(filters_val)
bottom_height = (inputs_shape[1] - 1) * subsample[0] + filters_shape[1]
bottom_width = (inputs_shape[2] - 1) * subsample[1] + filters_shape[2]
bottom_depth = (inputs_shape[3] - 1) * subsample[2] + filters_shape[3]
bottom_shape = theano.shared(
numpy.array([bottom_height, bottom_width, bottom_depth]))
weight = gpu_contiguous(filters.dimshuffle(0, 4, 1, 2, 3))
top = gpu_contiguous(inputs.dimshuffle(0, 4, 1, 2, 3))
if (subsample == (1, 1, 1)):
conv_ref = Corr3dMM_gradInputs(subsample=subsample)(kern=weight,
topgrad=top)
conv_gemm = GpuCorr3dMM_gradInputs(subsample=subsample)(
kern=weight, topgrad=top)
else:
conv_ref = Corr3dMM_gradInputs(subsample=subsample)(
kern=weight, topgrad=top, shape=bottom_shape)
conv_gemm = GpuCorr3dMM_gradInputs(subsample=subsample)(
kern=weight, topgrad=top, shape=bottom_shape)
f_ref = theano.function([], conv_ref)
f = theano.function([], conv_gemm, mode=mode_with_gpu)
res_ref = f_ref()
res = f()
utt.assert_allclose(res_ref, res)
def run_gradinput(self, inputs_shape, filters_shape, subsample=(1, 1, 1)):
inputs_shape = [inputs_shape[i] for i in (0, 4, 1, 2, 3)]
filters_shape = [filters_shape[i] for i in (0, 4, 1, 2, 3)]
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)
bottom_height = (inputs_shape[2] - 1) * subsample[0] + filters_shape[2]
bottom_width = (inputs_shape[3] - 1) * subsample[1] + filters_shape[3]
bottom_depth = (inputs_shape[4] - 1) * subsample[2] + filters_shape[4]
bottom_shape = gpuarray_shared_constructor(
np.array([bottom_height, bottom_width, bottom_depth]))
if (subsample == (1, 1, 1)):
conv_ref = Corr3dMM_gradInputs(subsample=subsample)(
kern=ref_cast(filters), topgrad=ref_cast(inputs))
conv_gemm = GpuCorr3dMM_gradInputs(subsample=subsample)(
kern=filters, topgrad=inputs)
else:
conv_ref = Corr3dMM_gradInputs(subsample=subsample)(
kern=ref_cast(filters),
topgrad=ref_cast(inputs),
shape=bottom_shape)
conv_gemm = GpuCorr3dMM_gradInputs(subsample=subsample)(
kern=filters, topgrad=inputs, shape=bottom_shape)
f_ref = theano.function([], conv_ref, mode=mode_without_gpu)
f = theano.function([], conv_gemm, mode=mode_with_gpu)
res_ref = f_ref()
res = f()
utt.assert_allclose(res_ref, res)
def local_abstractconv3d_gradinputs_gemm(node):
if theano.config.cxx == "" or not theano.config.blas.ldflags:
return
if not isinstance(node.op, AbstractConv3d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if not isinstance(kern.type, TensorType) or \
not isinstance(topgrad.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1, ::-1]
rval = Corr3dMM_gradInputs(border_mode=node.op.border_mode,
subsample=node.op.subsample,
filter_dilation=node.op.filter_dilation)(
kern, topgrad, shape)
copy_stack_trace(node.outputs[0], rval)
return [rval]
def local_abstractconv3d_gradinputs_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, AbstractConv3d_gradInputs):
return None
kern, topgrad, shape = node.inputs
if not isinstance(kern.type, TensorType) or \
not isinstance(topgrad.type, TensorType):
return None
# need to flip the kernel if necessary
if node.op.filter_flip:
kern = kern[:, :, ::-1, ::-1, ::-1]
rval = Corr3dMM_gradInputs(border_mode=node.op.border_mode,
subsample=node.op.subsample,
filter_dilation=node.op.filter_dilation,
num_groups=node.op.num_groups)(kern, topgrad,
shape)
copy_stack_trace(node.outputs[0], rval)
return [rval]