def test_prod_without_zeros_custom_acc_dtype(self):
# Test ability to provide your own acc_dtype for a ProdWithoutZeros().
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
idx = 0
for input_dtype in imap(str, theano.scalar.all_types):
x = tensor.matrix(dtype=input_dtype)
for acc_dtype in imap(str, theano.scalar.all_types):
axis = axes[idx % len(axes)]
# If acc_dtype would force a downcast, we expect a TypeError
# We always allow int/uint inputs with float/complex outputs.
upcasted_dtype = scalar.upcast(input_dtype, acc_dtype)
if acc_dtype == upcasted_dtype or (
input_dtype in tensor.discrete_dtypes and acc_dtype in tensor.continuous_dtypes
):
prod_woz_var = ProdWithoutZeros(axis=axis, acc_dtype=acc_dtype)(x)
assert prod_woz_var.owner.op.acc_dtype == acc_dtype
if acc_dtype.startswith("complex") and input_dtype != acc_dtype:
continue
f = theano.function([x], prod_woz_var)
data = numpy.random.rand(2, 3) * 3
data = data.astype(input_dtype)
f(data)
else:
self.assertRaises(TypeError, ProdWithoutZeros(axis=axis, acc_dtype=acc_dtype), x)
idx += 1
def simplify_mul(tree):
"""
Simplify a multiplication tree.
:param tree: A multiplication tree (as output by `parse_mul_tree`).
:return: A multiplication tree computing the same output as `tree` but
without useless multiplications by 1 nor -1 (identified by leaves of the
form [False, None] or [True, None] respectively). Useless multiplications
(with less than two inputs) are also removed from the tree.
"""
neg, inputs = tree
if isinstance(inputs, list):
# Recurse through inputs.
s_inputs = []
for s_i in imap(simplify_mul, inputs):
if s_i[1] is None:
# Multiplication by +/-1.
neg ^= s_i[0]
else:
s_inputs.append(s_i)
if not s_inputs:
# The multiplication is empty.
rval = [neg, None]
elif len(s_inputs) == 1:
# The multiplication has a single input.
s_inputs[0][0] ^= neg
rval = s_inputs[0]
else:
rval = [neg, s_inputs]
else:
rval = tree
# print 'simplify_mul: %s -> %s' % (tree, rval)
return rval
def test_prod_without_zeros_default_acc_dtype(self):
# Test the default dtype of a ProdWithoutZeros().
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
for idx, dtype in enumerate(imap(str, theano.scalar.all_types)):
axis = axes[idx % len(axes)]
x = tensor.matrix(dtype=dtype)
p = ProdWithoutZeros(axis=axis)(x)
assert p.owner.op.acc_dtype == dict(
bool="int64",
int8="int64",
int16="int64",
int32="int64",
uint8="uint64",
uint16="uint64",
uint32="uint64",
float16="float32",
float32="float64",
complex64="complex128",
).get(dtype, dtype)
if "complex" in dtype:
continue
f = theano.function([x], p)
data = numpy.random.rand(2, 3) * 3
data = data.astype(dtype)
f(data)
def simplify_mul(tree):
"""
Simplify a multiplication tree.
:param tree: A multiplication tree (as output by `parse_mul_tree`).
:return: A multiplication tree computing the same output as `tree` but
without useless multiplications by 1 nor -1 (identified by leaves of the
form [False, None] or [True, None] respectively). Useless multiplications
(with less than two inputs) are also removed from the tree.
"""
neg, inputs = tree
if isinstance(inputs, list):
# Recurse through inputs.
s_inputs = []
for s_i in imap(simplify_mul, inputs):
if s_i[1] is None:
# Multiplication by +/-1.
neg ^= s_i[0]
else:
s_inputs.append(s_i)
if not s_inputs:
# The multiplication is empty.
rval = [neg, None]
elif len(s_inputs) == 1:
# The multiplication has a single input.
s_inputs[0][0] ^= neg
rval = s_inputs[0]
else:
rval = [neg, s_inputs]
else:
rval = tree
# print 'simplify_mul: %s -> %s' % (tree, rval)
return rval
def test_prod_without_zeros_custom_dtype(self):
# Test ability to provide your own output dtype for a ProdWithoutZeros().
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
idx = 0
for input_dtype in imap(str, theano.scalar.all_types):
x = tensor.matrix(dtype=input_dtype)
for output_dtype in imap(str, theano.scalar.all_types):
axis = axes[idx % len(axes)]
prod_woz_var = ProdWithoutZeros(axis=axis, dtype=output_dtype)(x)
assert prod_woz_var.dtype == output_dtype
idx += 1
if "complex" in output_dtype or "complex" in input_dtype:
continue
f = theano.function([x], prod_woz_var)
data = numpy.random.rand(2, 3) * 3
data = data.astype(input_dtype)
f(data)
def test_mean_custom_dtype(self):
"""
Test the ability to provide your own output dtype for a mean.
"""
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
idx = 0
for input_dtype in imap(str, theano.scalar.all_types):
x = tensor.matrix(dtype=input_dtype)
for sum_dtype in imap(str, theano.scalar.all_types):
axis = axes[idx % len(axes)]
# If the inner sum cannot be created, it will raise a
# TypeError.
try:
mean_var = x.mean(dtype=sum_dtype, axis=axis)
except TypeError:
pass
else:
# Executed if no TypeError was raised
if sum_dtype in tensor.discrete_dtypes and axis != []:
assert mean_var.dtype == "float64", (mean_var.dtype, sum_dtype)
else:
assert mean_var.dtype == sum_dtype, (mean_var.dtype, sum_dtype)
if ("complex" in input_dtype or "complex" in sum_dtype) and input_dtype != sum_dtype:
continue
f = theano.function([x], mean_var)
data = numpy.random.rand(3, 4) * 10
data = data.astype(input_dtype)
f(data)
# Check that we can take the gradient, when implemented
if "complex" in mean_var.dtype:
continue
try:
tensor.grad(mean_var.sum(), x, disconnected_inputs="ignore")
except NotImplementedError:
# TrueDiv does not seem to have a gradient when
# the numerator is complex.
if mean_var.dtype in tensor.complex_dtypes:
pass
else:
raise
idx += 1
def test_prod_without_zeros_default_dtype(self):
"""
Test the default dtype of a ProdWithoutZeros().
"""
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
for idx, dtype in enumerate(imap(str, theano.scalar.all_types)):
axis = axes[idx % len(axes)]
x = ProdWithoutZeros(axis=axis)(tensor.matrix(dtype=dtype))
assert x.dtype == dict(
int8="int64", int16="int64", int32="int64", uint8="uint64", uint16="uint64", uint32="uint64"
).get(dtype, dtype)
def test_mean_default_dtype(self):
# Test the default dtype of a mean().
# We try multiple axis combinations even though axis should not matter.
axes = [None, 0, 1, [], [0], [1], [0, 1]]
for idx, dtype in enumerate(imap(str, theano.scalar.all_types)):
axis = axes[idx % len(axes)]
x = tensor.matrix(dtype=dtype)
m = x.mean(axis=axis)
if dtype in tensor.discrete_dtypes:
assert m.dtype == "float64"
else:
assert m.dtype == dtype, (m, m.dtype, dtype)
f = theano.function([x], m)
data = numpy.random.rand(3, 4) * 10
data = data.astype(dtype)
f(data)
def test_is_1pexp(self):
backup = config.warn.identify_1pexp_bug
config.warn.identify_1pexp_bug = False
try:
x = tensor.vector('x')
exp = tensor.exp
assert is_1pexp(1 + exp(x)) == (False, x)
assert is_1pexp(exp(x) + 1) == (False, x)
for neg, exp_arg in imap(is_1pexp, [(1 + exp(-x)), (exp(-x) + 1)]):
assert not neg and theano.gof.graph.is_same_graph(exp_arg, -x)
assert is_1pexp(1 - exp(x)) is None
assert is_1pexp(2 + exp(x)) is None
assert is_1pexp(exp(x) + 2) is None
assert is_1pexp(exp(x) - 1) is None
assert is_1pexp(-1 + exp(x)) is None
assert is_1pexp(1 + 2 * exp(x)) is None
finally:
config.warn.identify_1pexp_bug = backup
def test_is_1pexp(self):
backup = config.warn.identify_1pexp_bug
config.warn.identify_1pexp_bug = False
try:
x = tensor.vector('x')
exp = tensor.exp
assert is_1pexp(1 + exp(x)) == (False, x)
assert is_1pexp(exp(x) + 1) == (False, x)
for neg, exp_arg in imap(is_1pexp, [(1 + exp(-x)), (exp(-x) + 1)]):
assert not neg and theano.gof.graph.is_same_graph(exp_arg, -x)
assert is_1pexp(1 - exp(x)) is None
assert is_1pexp(2 + exp(x)) is None
assert is_1pexp(exp(x) + 2) is None
assert is_1pexp(exp(x) - 1) is None
assert is_1pexp(-1 + exp(x)) is None
assert is_1pexp(1 + 2 * exp(x)) is None
finally:
config.warn.identify_1pexp_bug = backup
def test_is_1pexp(self):
backup = config.warn.identify_1pexp_bug
config.warn.identify_1pexp_bug = False
try:
x = tensor.vector('x')
exp = tensor.exp
assert is_1pexp(1 + exp(x), False) == (False, x)
assert is_1pexp(exp(x) + 1, False) == (False, x)
for neg, exp_arg in imap(
lambda x: is_1pexp(x, only_process_constants=False),
[(1 + exp(-x)), (exp(-x) + 1)]):
assert not neg and theano.gof.graph.is_same_graph(exp_arg, -x)
assert is_1pexp(1 - exp(x), False) is None
assert is_1pexp(2 + exp(x), False) is None
assert is_1pexp(exp(x) + 2, False) is None
assert is_1pexp(exp(x) - 1, False) is None
assert is_1pexp(-1 + exp(x), False) is None
assert is_1pexp(1 + 2 * exp(x), False) is None
finally:
config.warn.identify_1pexp_bug = backup
def test_is_1pexp(self):
backup = config.warn.identify_1pexp_bug
config.warn.identify_1pexp_bug = False
try:
x = tensor.vector('x')
exp = tensor.exp
assert is_1pexp(1 + exp(x), False) == (False, x)
assert is_1pexp(exp(x) + 1, False) == (False, x)
for neg, exp_arg in imap(lambda x:
is_1pexp(x, only_process_constants=False),
[(1 + exp(-x)), (exp(-x) + 1)]):
assert not neg and theano.gof.graph.is_same_graph(exp_arg, -x)
assert is_1pexp(1 - exp(x), False) is None
assert is_1pexp(2 + exp(x), False) is None
assert is_1pexp(exp(x) + 2, False) is None
assert is_1pexp(exp(x) - 1, False) is None
assert is_1pexp(-1 + exp(x), False) is None
assert is_1pexp(1 + 2 * exp(x), False) is None
finally:
config.warn.identify_1pexp_bug = backup
