def _oper_gpu(cls, x, w, b, in_shape, out_shape, kernel, stride, padding,
dilation):
N = x.shape[0]
conv_desc = cu.ConvolutionDescriptor(padding, stride, dilation,
precision)
filter_desc = cu.FilterDescriptor(w.shape, precision)
y = GPUValue(shape=tuple([
N,
] + list(out_shape)))
with cu.cudnn_handler() as handle:
cu.cuConvolutionForward(handle, conv_desc, filter_desc, get_gpu(x),
get_gpu(w), y)
if b is not None:
cu.cu_add_bias(get_gpu(b), y)
# assert type(x) is not np.ndarray
ret = cls._create_node(y)
ret.attrs._conv_desc = conv_desc
ret.attrs._filter_desc = filter_desc
ret.attrs._x = x
ret.attrs._w = w
ret.attrs._b = b
ret.attrs._in_shape = in_shape
ret.attrs._out_shape = out_shape
ret.attrs._kernel = kernel
ret.attrs._stride = stride
ret.attrs._padding = padding
ret.attrs._dilation = dilation
return ret
def _oper_gpu(cls, x, w, b, in_shape, kernel, stride, padding):
conv_desc = cu.ConvolutionNDescriptor(padding, stride, precision)
filter_desc = cu.NdFilterDescriptor(w.shape, precision)
output_shape = [x.shape[0], w.shape[0]]
for i in range(len(x.shape[2:])):
output_shape.append(
(x.shape[i + 2] + padding[i] * 2 - kernel[i]) // stride[i] + 1)
y = GPUValue(shape=tuple(output_shape))
with cu.cudnn_handler() as handle:
cu.cuConvolutionForward(handle, conv_desc, filter_desc, get_gpu(x),
get_gpu(w), y)
if b is not None:
cu.cu_add_bias(get_gpu(b), y)
# assert type(x) is not np.ndarray
ret = cls._create_node(y)
ret.attrs._conv_desc = conv_desc
ret.attrs._filter_desc = filter_desc
ret.attrs._x = x
ret.attrs._w = w
ret.attrs._b = b
return ret
def _oper_gpu(cls, x, w, b, in_shape, out_shape, kernel, stride, padding,
dilation):
conv_desc = cu.ConvolutionDescriptor(padding, stride, dilation,
precision)
filter_desc = cu.FilterDescriptor(w.shape, precision)
N = x.shape[0]
z = GPUValue(shape=tuple([
N,
] + list(out_shape)))
with cu.cudnn_handler() as handle:
cu.cuConvolutionBackwardData(handle, conv_desc, filter_desc,
get_gpu(w), get_gpu(x), z)
if b is not None:
cu.cu_add_bias(get_gpu(b), z)
ret = cls._create_node(z)
ret.attrs._conv_desc = conv_desc
ret.attrs._filter_desc = filter_desc
ret.attrs._x = x
ret.attrs._w = w
ret.attrs._b = b
return ret