def check_backward_consistency_regression(self, x_data, gy_data):
# Regression test to two-dimensional unpooling layer.
ndim = len(self.dims)
if ndim != 2:
return
ksize = self.ksize
stride = self.stride
pad = self.pad
xp = cuda.get_array_module(x_data)
# Backward computation for N-dimensional unpooling layer.
x_nd = chainer.Variable(xp.array(x_data))
func_nd = functions.UnpoolingND(ndim, ksize, stride=stride,
pad=pad, cover_all=self.cover_all)
y_nd = func_nd(x_nd)
y_nd.grad = gy_data
y_nd.backward()
# Backward computation for two-dimensional unpooling layer.
x_2d = chainer.Variable(xp.array(x_data))
func_2d = functions.Unpooling2D(ksize, stride=stride, pad=pad,
cover_all=self.cover_all)
y_2d = func_2d(x_2d)
y_2d.grad = gy_data
y_2d.backward()
# Test that the two result gradients are close enough.
opt = self.check_backward_options
testing.assert_allclose(
x_nd.grad, x_2d.grad, atol=opt['atol'], rtol=opt['rtol'])
def check_backward(self, x_data, y_grad):
ndim = len(self.dims)
gradient_check.check_backward(
functions.UnpoolingND(ndim,
self.ksize,
self.stride,
self.pad,
cover_all=self.cover_all), x_data, y_grad,
**self.check_backward_options)