def create_convolution_descriptor(pad, stride, dtype, mode=cudnn.CUDNN_CROSS_CORRELATION):
desc = Descriptor(cudnn.createConvolutionDescriptor(), cudnn.destroyConvolutionDescriptor)
ndim = len(pad)
if ndim != len(stride):
raise ValueError("pad and stride must be of same length")
if ndim == 2:
cudnn.setConvolution2dDescriptor(desc.value, pad[0], pad[1], stride[0], stride[1], 1, 1, mode)
else:
c_pad = _to_ctypes_array(pad)
c_stride = _to_ctypes_array(stride)
c_upscale = _to_ctypes_array((1,) * ndim)
if _cudnn_version >= 3000:
data_type = get_data_type(dtype)
# TODO(takagi) Temporarily use computing precision of FP32 for
# storing precision of FP16.
if dtype == numpy.float16:
data_type = cudnn.CUDNN_DATA_FLOAT
cudnn.setConvolutionNdDescriptor_v3(
desc.value, ndim, c_pad.data, c_stride.data, c_upscale.data, mode, data_type
)
else:
cudnn.setConvolutionNdDescriptor_v2(desc.value, ndim, c_pad.data, c_stride.data, c_upscale.data, mode)
return desc
def create_convolution_descriptor(pad,
stride,
dtype,
mode=cudnn.CUDNN_CROSS_CORRELATION):
desc = Descriptor(cudnn.createConvolutionDescriptor(),
cudnn.destroyConvolutionDescriptor)
ndim = len(pad)
if ndim != len(stride):
raise ValueError('pad and stride must be of same length')
if ndim == 2:
cudnn.setConvolution2dDescriptor(desc.value, pad[0], pad[1], stride[0],
stride[1], 1, 1, mode)
else:
c_pad = _to_ctypes_array(pad)
c_stride = _to_ctypes_array(stride)
c_upscale = _to_ctypes_array((1, ) * ndim)
if _cudnn_version >= 3000:
data_type = get_data_type(dtype)
# TODO(takagi) Temporarily use computing precision of FP32 for
# storing precision of FP16.
if dtype == numpy.float16:
data_type = cudnn.CUDNN_DATA_FLOAT
cudnn.setConvolutionNdDescriptor_v3(desc.value, ndim, c_pad.data,
c_stride.data, c_upscale.data,
mode, data_type)
else:
cudnn.setConvolutionNdDescriptor_v2(desc.value, ndim, c_pad.data,
c_stride.data, c_upscale.data,
mode)
return desc
def create_convolution_descriptor(pad, stride, mode=cudnn.CUDNN_CROSS_CORRELATION):
desc = Descriptor(cudnn.createConvolutionDescriptor(), cudnn.destroyConvolutionDescriptor)
ndim = len(pad)
if ndim != len(stride):
raise ValueError("pad and stride must be of same length")
if ndim == 2:
cudnn.setConvolution2dDescriptor(desc.value, pad[0], pad[1], stride[0], stride[1], 1, 1, mode)
else:
c_pad = _to_ctypes_array(pad)
c_stride = _to_ctypes_array(stride)
c_upscale = _to_ctypes_array((1,) * ndim)
cudnn.setConvolutionNdDescriptor_v2(desc.value, ndim, c_pad.data, c_stride.data, c_upscale.data, mode)
return desc
def create_convolution_descriptor(pad, stride,
mode=cudnn.CUDNN_CROSS_CORRELATION):
desc = Descriptor(cudnn.createConvolutionDescriptor(),
cudnn.destroyConvolutionDescriptor)
ndim = len(pad)
if ndim != len(stride):
raise ValueError('pad and stride must be of same length')
if ndim == 2:
cudnn.setConvolution2dDescriptor(
desc.value, pad[0], pad[1], stride[0], stride[1], 1, 1, mode)
else:
upscale = (1,) * ndim
cudnn.setConvolutionNdDescriptor(
desc.value, ndim, _to_ctypes_array(pad), _to_ctypes_array(stride),
_to_ctypes_array(upscale), mode)
return desc
