def check_backward_consistency_regression(self, x_data, gy_data,
use_cudnn='always'):
# Regression test to two-dimensional average pooling layer.
if len(self.dims) != 2:
return
ksize = self.ksize
stride = self.stride
pad = self.pad
xp = cuda.get_array_module(x_data)
# Backward computation for N-dimensional average pooling layer.
x_nd = chainer.Variable(xp.array(x_data))
with chainer.using_config('use_cudnn', use_cudnn):
func_nd = functions.AveragePoolingND(self.ndim, ksize,
stride=stride, pad=pad)
y_nd = func_nd.apply((x_nd,))[0]
y_nd.grad = gy_data
y_nd.backward()
# Backward computation for two-dimensional average pooling layer.
x_2d = chainer.Variable(xp.array(x_data))
with chainer.using_config('use_cudnn', use_cudnn):
func_2d = functions.AveragePooling2D(ksize, stride=stride, pad=pad,
cover_all=False)
y_2d = func_2d.apply((x_2d,))[0]
y_2d.grad = gy_data
y_2d.backward()
# Test that the two result gradients are close enough.
testing.assert_allclose(x_nd.grad, x_2d.grad)
def check_backward(self, x_data, y_grad, use_cudnn=True):
gradient_check.check_backward(
functions.AveragePoolingND(self.ndim,
self.ksize,
self.stride,
self.pad,
use_cudnn=use_cudnn), x_data, y_grad,
**self.check_backward_options)
def check_backward(self, x_data, y_grad, use_cudnn='always'):
with chainer.using_config('use_cudnn', use_cudnn):
gradient_check.check_backward(functions.AveragePoolingND(
self.ndim, self.ksize, self.stride, self.pad),
x_data,
y_grad,
dtype=numpy.float64,
**self.check_backward_options)
def test_cover_all_not_supported(self):
with self.assertRaises(ValueError):
functions.AveragePoolingND(3, 3, cover_all=True)
