def test_forward_cpu_input_size_invariant(model, data):
atom_data, adj_data = data[0], data[1]
is_real_node = numpy.ones(atom_data.shape, dtype=numpy.float32)
y_actual = cuda.to_cpu(model(atom_data, adj_data, is_real_node).data)
atom_data_ex = extend_node(atom_data, out_size=8)
adj_data_ex = extend_adj(adj_data, out_size=8)
is_real_node_ex = extend_node(is_real_node, out_size=8)
y_actual_ex = cuda.to_cpu(model(
atom_data_ex, adj_data_ex, is_real_node_ex).data)
assert numpy.allclose(y_actual, y_actual_ex, rtol=1e-5, atol=1e-6)
def test_forward_cpu_input_size_invariant(model, data):
atom_data, adj_data = data[0], data[1]
is_real_node = numpy.ones(atom_data.shape, dtype=numpy.float32)
y_actual = cuda.to_cpu(model(atom_data, adj_data, is_real_node).data)
atom_data_ex = extend_node(atom_data, out_size=8)
adj_data_ex = extend_adj(adj_data, out_size=8)
is_real_node_ex = extend_node(is_real_node, out_size=8)
y_actual_ex = cuda.to_cpu(
model(atom_data_ex, adj_data_ex, is_real_node_ex).data)
assert numpy.allclose(y_actual, y_actual_ex, rtol=1e-5, atol=1e-6)
def test_extend_node_2d(x):
x_extended = extend_node(x, out_size=6)
x_expected = numpy.array([[0, 1, 2, 0, 0, 0],
[3, 4, 5, 0, 0, 0]], dtype=x.dtype)
print('x type', x_extended.dtype)
assert x_extended.shape == (batchsize, 6)
assert x_extended.dtype == x.dtype
assert numpy.array_equal(x_extended, x_expected)
def test_extend_node_2d(x):
x_extended = extend_node(x, out_size=6)
x_expected = numpy.array([[0, 1, 2, 0, 0, 0], [3, 4, 5, 0, 0, 0]],
dtype=x.dtype)
print('x type', x_extended.dtype)
assert x_extended.shape == (batchsize, 6)
assert x_extended.dtype == x.dtype
assert numpy.array_equal(x_extended, x_expected)
def test_extend_node_3d(x, axis):
x_extended = extend_node(x, out_size=6, axis=axis)
x_expected = numpy.array([[[0, 1, 2, 3, 4, 0], [5, 6, 7, 8, 9, 0],
[10, 11, 12, 13, 14, 0]],
[[15, 16, 17, 18, 19,
0], [20, 21, 22, 23, 24, 0],
[25, 26, 27, 28, 29, 0]]])
assert x_extended.shape == (batchsize, num_node, 6)
assert x_extended.dtype == x.dtype
assert numpy.array_equal(x_extended, x_expected)
def test_extend_node_3d(x, axis):
x_extended = extend_node(x, out_size=6, axis=axis)
x_expected = numpy.array([
[[0, 1, 2, 3, 4, 0],
[5, 6, 7, 8, 9, 0],
[10, 11, 12, 13, 14, 0]],
[[15, 16, 17, 18, 19, 0],
[20, 21, 22, 23, 24, 0],
[25, 26, 27, 28, 29, 0]]])
assert x_extended.shape == (batchsize, num_node, 6)
assert x_extended.dtype == x.dtype
assert numpy.array_equal(x_extended, x_expected)
def test_forward_cpu_input_size_invariant(model, data):
# This RSGCN uses dropout, so we need to forward with test mode
# to remove stochastic calculation.
atom_data, adj_data = data[0], data[1]
with chainer.using_config('train', False):
y_actual = cuda.to_cpu(model(atom_data, adj_data).data)
# Set bigger size than original `atom_size`.
atom_data_ex = extend_node(atom_data, out_size=8)
adj_data_ex = extend_adj(adj_data, out_size=8)
# print('size', atom_data.shape, adj_data.shape,
# atom_data_ex.shape, adj_data_ex.shape)
with chainer.using_config('train', False):
y_actual_ex = cuda.to_cpu(model(atom_data_ex, adj_data_ex).data)
assert numpy.allclose(y_actual, y_actual_ex, rtol=1.e-4, atol=1.e-5)
def test_forward_cpu_input_size_invariant(model, data):
# This RSGCN uses dropout, so we need to forward with test mode
# to remove stochastic calculation.
atom_data, adj_data = data[0], data[1]
with chainer.using_config('train', False):
y_actual = cuda.to_cpu(model(atom_data, adj_data).data)
# Set bigger size than original `atom_size`.
atom_data_ex = extend_node(atom_data, out_size=8)
adj_data_ex = extend_adj(adj_data, out_size=8)
# print('size', atom_data.shape, adj_data.shape,
# atom_data_ex.shape, adj_data_ex.shape)
with chainer.using_config('train', False):
y_actual_ex = cuda.to_cpu(model(
atom_data_ex, adj_data_ex).data)
assert numpy.allclose(y_actual, y_actual_ex, rtol=1.e-4, atol=1.e-5)
def test_extend_node_assert_raises():
with pytest.raises(ValueError):
extend_node(x_2d, out_size=1)
def test_extend_node_assert_raises():
with pytest.raises(ValueError):
extend_node(x_2d, out_size=1)
