def join(small_image,
big_image,
n_filter_small,
n_filter_big,
big_img_size_in,
ordering=''):
# upsample small image
upsampled_small = tensor.repeat(small_image, 2, axis=2)
upsampled_small = tensor.repeat(upsampled_small, 2, axis=3)
img_size_small = (n_filter_small, big_img_size_in[0], big_img_size_in[1])
img_size_big = (n_filter_big, big_img_size_in[0], big_img_size_in[1])
bn_small = BatchNormalization(img_size_small,
name='bn_small%s' % (ordering, ))
bn_small.initialize()
bn_big = BatchNormalization(img_size_big, name='bn_big%s' % (ordering, ))
bn_big.initialize()
depth_concat = tensor.concatenate(
[bn_small.apply(upsampled_small),
bn_big.apply(big_image)], axis=1)
return depth_concat
def test_batch_normalization_broadcastable_sanity():
bn = BatchNormalization((5, 3, 2), broadcastable=(False, True, False))
with bn:
cg = ComputationGraph([bn.apply(tensor.tensor4('abc'))])
vars = VariableFilter(roles=[BATCH_NORM_MINIBATCH_ESTIMATE])(cg)
assert all(v.broadcastable[1:] == bn.population_mean.broadcastable
for v in vars)
def test_batch_normalization_broadcastable_sanity():
bn = BatchNormalization((5, 3, 2), broadcastable=(False, True, False))
with bn:
cg = ComputationGraph([bn.apply(tensor.tensor4('abc'))])
vars = VariableFilter(roles=[BATCH_NORM_MINIBATCH_ESTIMATE])(cg)
assert all(v.broadcastable[1:] == bn.population_mean.broadcastable
for v in vars)
def test_batch_normalization_simple():
x = tensor.matrix()
eps = 1e-4
bn = BatchNormalization(input_dim=4, epsilon=eps)
bn.initialize()
with batch_normalization(bn):
y = bn.apply(x)
rng = numpy.random.RandomState((2016, 1, 18))
x_ = rng.uniform(size=(5, 4)).astype(theano.config.floatX)
y_ = y.eval({x: x_})
y_expected = (x_ - x_.mean(axis=0)) / numpy.sqrt(x_.var(axis=0) + eps)
assert_allclose(y_, y_expected, rtol=1e-4)
def test_batch_normalization_simple():
x = tensor.matrix()
eps = 1e-4
bn = BatchNormalization(input_dim=4, epsilon=eps)
bn.initialize()
with batch_normalization(bn):
y = bn.apply(x)
rng = numpy.random.RandomState((2016, 1, 18))
x_ = rng.uniform(size=(5, 4)).astype(theano.config.floatX)
y_ = y.eval({x: x_})
y_expected = (x_ - x_.mean(axis=0)) / numpy.sqrt(x_.var(axis=0) + eps)
assert_allclose(y_, y_expected, rtol=1e-4)
