def test_skip_linear_transform(self, BatchNormLayer):
input_shape = (20, 30, 40)
# random input tensor, beta, gamma
input = (np.random.randn(*input_shape).astype(theano.config.floatX) +
np.random.randn(1, 30, 1).astype(theano.config.floatX))
beta = np.random.randn(30).astype(theano.config.floatX)
gamma = np.random.randn(30).astype(theano.config.floatX)
# create layers without beta or gamma
layer1 = BatchNormLayer(input_shape, beta=None, gamma=gamma)
layer2 = BatchNormLayer(input_shape, beta=beta, gamma=None)
# check that one parameter is missing
assert len(layer1.get_params()) == 3
assert len(layer2.get_params()) == 3
# call get_output_for()
result1 = layer1.get_output_for(theano.tensor.constant(input),
deterministic=False).eval()
result2 = layer2.get_output_for(theano.tensor.constant(input),
deterministic=False).eval()
# compute expected results and expected updated parameters
mean = input.mean(axis=(0, 2))
std = np.sqrt(input.var(axis=(0, 2)) + layer1.epsilon)
exp_result = (input - mean[None, :, None]) / std[None, :, None]
exp_result1 = exp_result * gamma[None, :, None] # no beta
exp_result2 = exp_result + beta[None, :, None] # no gamma
# compare expected results to actual results
tol = {'atol': 1e-5, 'rtol': 1e-6}
assert np.allclose(result1, exp_result1, **tol)
assert np.allclose(result2, exp_result2, **tol)
def test_skip_linear_transform(self, BatchNormLayer):
input_shape = (20, 30, 40)
# random input tensor, beta, gamma
input = (np.random.randn(*input_shape).astype(theano.config.floatX) +
np.random.randn(1, 30, 1).astype(theano.config.floatX))
beta = np.random.randn(30).astype(theano.config.floatX)
gamma = np.random.randn(30).astype(theano.config.floatX)
# create layers without beta or gamma
layer1 = BatchNormLayer(input_shape, beta=None, gamma=gamma)
layer2 = BatchNormLayer(input_shape, beta=beta, gamma=None)
# check that one parameter is missing
assert len(layer1.get_params()) == 3
assert len(layer2.get_params()) == 3
# call get_output_for()
result1 = layer1.get_output_for(theano.tensor.constant(input),
deterministic=False).eval()
result2 = layer2.get_output_for(theano.tensor.constant(input),
deterministic=False).eval()
# compute expected results and expected updated parameters
mean = input.mean(axis=(0, 2))
std = np.sqrt(input.var(axis=(0, 2)) + layer1.epsilon)
exp_result = (input - mean[None, :, None]) / std[None, :, None]
exp_result1 = exp_result * gamma[None, :, None] # no beta
exp_result2 = exp_result + beta[None, :, None] # no gamma
# compare expected results to actual results
tol = {'atol': 1e-5, 'rtol': 1e-6}
assert np.allclose(result1, exp_result1, **tol)
assert np.allclose(result2, exp_result2, **tol)
def test_batch_norm_tag(self, BatchNormLayer):
input_shape = (20, 30, 40)
layer = BatchNormLayer(input_shape)
assert len(layer.get_params()) == 4
stat_params = layer.get_params(batch_norm_stat=True)
assert len(stat_params) == 2
param_names = [p.name for p in stat_params]
assert "mean" in param_names
assert "inv_std" in param_names
def test_batch_norm_tag(self, BatchNormLayer):
input_shape = (20, 30, 40)
layer = BatchNormLayer(input_shape)
assert len(layer.get_params()) == 4
stat_params = layer.get_params(batch_norm_stat=True)
assert len(stat_params) == 2
param_names = [p.name for p in stat_params]
assert "mean" in param_names
assert "inv_std" in param_names
