Skip to content

P
pytensor
提交 7885e618 authored 作者: Ian Goodfellow's avatar Ian Goodfellow
浏览文件
操作

a lot of pep8

上级 c7d06ac9
全部展开 隐藏空白字符变更
内嵌 并排
正在显示 包含 69 行增加 和 45 行删除
theano/tensor/nnet/sigm.py
浏览文件 @ 7885e618
......@@ -42,7 +42,7 @@ class ScalarSigmoid(scalar.UnaryScalarOp):
assert rval.type.dtype.find('float') != -1
return [ rval ]
return [rval]
def c_code(self, node, name, inp, out, sub):
x, = inp
......@@ -69,7 +69,7 @@ sigmoid = elemwise.Elemwise(scalar_sigmoid, name='sigmoid')
sigmoid_inplace = elemwise.Elemwise(
ScalarSigmoid(scalar.transfer_type(0)),
inplace_pattern={0:0},
inplace_pattern={0: 0},
name='sigmoid_inplace',
)
......@@ -84,12 +84,15 @@ class ScalarSoftplus(scalar.UnaryScalarOp):
if x > 30.0:
return x
return numpy.log1p(numpy.exp(x))
def impl(self, x):
return ScalarSoftplus.static_impl(x)
def grad(self, inp, grads):
x, = inp
gz, = grads
return [gz * scalar_sigmoid(x)]
def c_code(self, node, name, inp, out, sub):
x, = inp
z, = out
......@@ -103,27 +106,29 @@ class ScalarSoftplus(scalar.UnaryScalarOp):
return """%(z)s = %(x)s < -745.0 ? 0.0 : %(x)s > 16.0 ? %(x)s : log1p(exp(%(x)s));""" % locals()
else:
raise NotImplementedError('only floatingpoint is implemented')
def c_code_cache_version(self):
v = super(ScalarSoftplus, self).c_code_cache_version()
if v:
return (2,) + v
else:
return v
scalar_softplus = ScalarSoftplus(scalar.upgrade_to_float, name='scalar_softplus')
scalar_softplus = ScalarSoftplus(scalar.upgrade_to_float, name= 'scalar_softplus')
softplus = elemwise.Elemwise(scalar_softplus, name='softplus')
pprint.assign(softplus, printing.FunctionPrinter('softplus'))
def _skip_mul_1(r):
if r.owner and r.owner.op == tensor.mul:
not_is_1 = [i for i in r.owner.inputs if not _is_1(i) ]
if len(not_is_1)==1:
not_is_1 = [i for i in r.owner.inputs if not _is_1(i)]
if len(not_is_1) == 1:
return not_is_1[0]
logsigm_to_softplus = gof.PatternSub(
(tensor.log, (sigmoid, 'x')),
(tensor.neg, (softplus, (tensor.neg, 'x'))),
allow_multiple_clients = True,
allow_multiple_clients=True,
skip_identities_fn=_skip_mul_1)
......@@ -139,21 +144,22 @@ def _is_1(expr):
log1msigm_to_softplus = gof.PatternSub(
(tensor.log,
(tensor.sub,
dict(pattern='y', constraint = _is_1),
dict(pattern='y', constraint=_is_1),
(sigmoid, 'x'))),
(tensor.neg, (softplus, 'x')),
allow_multiple_clients = True,
allow_multiple_clients=True,
skip_identities_fn=_skip_mul_1)
log1pexp_to_softplus = gof.PatternSub(
(tensor.log1p,
(tensor.exp, 'x')),
(softplus, 'x'),
allow_multiple_clients = True)
allow_multiple_clients=True)
opt.register_stabilize(logsigm_to_softplus, name='logsigm_to_softplus')
opt.register_stabilize(log1msigm_to_softplus, name='log1msigm_to_softplus')
opt.register_stabilize(log1pexp_to_softplus, name='log1pexp_to_softplus')
opt.register_stabilize(logsigm_to_softplus, name = 'logsigm_to_softplus')
opt.register_stabilize(log1msigm_to_softplus, name = 'log1msigm_to_softplus')
opt.register_stabilize(log1pexp_to_softplus, name = 'log1pexp_to_softplus')
def is_1pexp(t):
"""
......@@ -247,7 +253,7 @@ def partition_num_or_denom(r, f):
else:
neg_t, f_t = f_t
f_terms.append(f_t)
neg ^= neg_t #bit flip if neg_t is true
neg ^= neg_t # bit flip if neg_t is true
return f_terms, rest, neg
......@@ -299,7 +305,8 @@ def local_exp_over_1_plus_exp(node):
#find all the exp() terms in the numerator
num, denom = node.inputs
num_exp_x, num_rest, num_neg = partition_num_or_denom(num, is_exp)
denom_1pexp, denom_rest, denom_neg = partition_num_or_denom(denom, is_1pexp)
denom_1pexp, denom_rest,
denom_neg = partition_num_or_denom(denom, is_1pexp)
sigmoids = []
for t in denom_1pexp:
......@@ -311,7 +318,7 @@ def local_exp_over_1_plus_exp(node):
# case: 1/(1+exp(x))
sigmoids.append(sigmoid(-t))
if not sigmoids: # we didn't find any. abort
if not sigmoids: # we didn't find any. abort
return
# put the new numerator together
new_num = sigmoids + [tensor.exp(t) for t in num_exp_x] + num_rest
......@@ -330,6 +337,7 @@ def local_exp_over_1_plus_exp(node):
else:
return [new_num / tensor.mul(*denom_rest)]
def parse_mul_tree(root):
"""
Parse a tree of multiplications starting at the given root.
......@@ -512,7 +520,7 @@ def perform_sigm_times_exp(tree, exp_x=None, exp_minus_x=None, sigm_x=None,
sigm_minus_x = []
if full_tree is None:
full_tree = tree
if False: # Debug code.
if False: # Debug code.
print '<perform_sigm_times_exp>'
print ' full_tree = %s' % full_tree
print ' tree = %s' % tree
......@@ -621,10 +629,13 @@ def local_inv_1_plus_exp(node):
if nonconsts[0].owner and nonconsts[0].owner.op == tensor.exp:
if scalars and numpy.allclose(numpy.sum(scalars), 1):
return opt._fill_chain(
sigmoid(tensor.neg(nonconsts[0].owner.inputs[0])),
sigmoid(
tensor.neg(nonconsts[0].owner.inputs[0])),
scalar_inputs)
# Registration is below, and conditional.
@gof.local_optimizer([tensor.sub])
def local_1msigmoid(node):
"""
......@@ -633,7 +644,7 @@ def local_1msigmoid(node):
if node.op == tensor.sub:
sub_l, sub_r = node.inputs
if len(sub_r.clients) > 1:
return # graph is using both sigm and 1-sigm
return # graph is using both sigm and 1-sigm
if sub_r.owner and sub_r.owner.op == sigmoid:
try:
val_l = opt.get_constant_value(sub_l)
......@@ -686,13 +697,14 @@ if 0:
assert t0.owner.op == div
t0top, t0bot = t0.owner.inputs
t1top, t1bot = t1.owner.inputs
rval.append(div(mul(*(t0top+t1top)), mul(*(t0bot+t1bot))))
rval.append(div(mul(*(
t0top + t1top)), mul(*(t0bot + t1bot))))
if len(rval) > 100:
# This loop can be exponentially long.
# aborting
return []
elif len(node.outputs)>1:
elif len(node.outputs) > 1:
return []
else:
return [node.outputs[0]]
theano/tensor/randomstreams.py
浏览文件 @ 7885e618
......@@ -136,7 +136,7 @@ class RandomStreams(Component, raw_random.RandomStreamsBase):
"""
def __init__(self, seed=None, no_warn = False):
def __init__(self, seed=None, no_warn=False):
""":type seed: None or int
:param seed: a default seed to initialize the RandomState
......@@ -146,7 +146,7 @@ class RandomStreams(Component, raw_random.RandomStreamsBase):
"""
if not no_warn:
deprecation_warning()
super(RandomStreams, self).__init__(no_warn = True)
super(RandomStreams, self).__init__(no_warn=True)
self.random_state_variables = []
self.default_instance_seed = seed
......
theano/tensor/tests/test_basic.py
浏览文件 @ 7885e618
This source diff could not be displayed because it is too large. You can view the blob instead.
theano/tensor/tests/test_elemwise.py
浏览文件 @ 7885e618
......@@ -47,7 +47,8 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
#test that DimShuffle.infer_shape work correctly
x = TensorType('float64', ib)('x')
e = DimShuffle(ib, shuffle)(x)
f = copy(linker).accept(FunctionGraph([x], [e.shape])).make_function()
f = copy(linker).accept(FunctionGraph([x], [e.
shape])).make_function()
assert all(f(numpy.ones(xsh))) == all(zsh)
# Test when we drop a axis that is not broadcastable
......@@ -125,7 +126,8 @@ class test_Broadcast(unittest.TestCase):
x = TensorType('float64', [(entry == 1) for entry in xsh])('x')
y = TensorType('float64', [(entry == 1) for entry in ysh])('y')
e = Elemwise(scalar.add)(x, y)
f = copy(linker).accept(FunctionGraph([x, y], [e.shape])).make_function()
f = copy(linker).accept(FunctionGraph([x,
y], [e.shape])).make_function()
assert tuple(f(xv, yv)) == tuple(zv.shape)
def with_linker_inplace(self, linker):
......@@ -154,7 +156,8 @@ class test_Broadcast(unittest.TestCase):
x = TensorType('float64', [(entry == 1) for entry in xsh])('x')
y = TensorType('float64', [(entry == 1) for entry in ysh])('y')
e = Elemwise(scalar.Add(scalar.transfer_type(0)), {0: 0})(x, y)
f = copy(linker).accept(FunctionGraph([x, y], [e.shape])).make_function()
f = copy(linker).accept(FunctionGraph([x,
y], [e.shape])).make_function()
xv = numpy.asarray(numpy.random.rand(*xsh))
yv = numpy.asarray(numpy.random.rand(*ysh))
zv = xv + yv
......@@ -349,7 +352,8 @@ class test_CAReduce(unittest_tools.InferShapeTester):
e = tensor_op(x, axis=tosum)
if tosum is None:
tosum = range(len(xsh))
f = copy(linker).accept(FunctionGraph([x], [e.shape])).make_function()
f = copy(linker).accept(FunctionGraph([x],
[e.shape])).make_function()
if not(scalar_op in [scalar.maximum, scalar.minimum] and
((xsh == () or numpy.prod(xsh) == 0))):
assert all(f(xv) == zv.shape)
......@@ -459,7 +463,8 @@ class test_Prod(unittest.TestCase):
# including zeros, as the case with zeros is important
# (and special cases: 1 zero in the row, more than 1 zero in the row)
x_val = numpy.asarray([[1,2,3],[4,5,6],[7,8,9]], dtype='float32')
x_val = numpy.asarray([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
dtype='float32')
x = theano.tensor.dmatrix()
# now with verify_grad
unittest_tools.verify_grad(Prod(axis=1), [x_val], mode=self.mode)
......@@ -471,26 +476,28 @@ class test_Prod(unittest.TestCase):
unittest_tools.verify_grad(fn, [x_val], mode=self.mode)
def test_verify_grad_with_zeros(self):
# including zeros, as the case with zeros is important
# (and special cases: 1 zero in the row, more than 1 zero in the row)
x_val = numpy.asarray([[1.,2.,3.],[0.,5.,6.],[0.,0.,9.]], dtype='float32')
x_val = numpy.asarray([[1., 2., 3.], [0., 5., 6.], [0., 0., 9.]],
dtype='float32')
x = theano.tensor.dmatrix()
# sanity check
x2 = theano.tensor.dmatrix()
p = Prod(axis=1)(x)
p2 = Prod(axis=1)(x2)
fn = theano.function([x,x2],[p-p2], mode=self.mode)
fn = theano.function([x, x2], [p - p2], mode=self.mode)
#print "hand computed diff for each row"
x2_val = numpy.asarray([[1., 2., 3.003], [0.003,5.,6], [0.,0.,9.01]])
x2_val = numpy.asarray([[1., 2., 3.003], [0.003, 5., 6], [
0., 0., 9.01]])
#print fn(x_val, x2_val)
fn2 = theano.function([x],[theano.tensor.grad(p.sum(),x)], mode=self.mode)
fn2 = theano.function([x], [theano.tensor.grad(p.sum(), x)],
mode=self.mode)
#print "real grad"
#print fn2(x_val)
fn3 = theano.function([x],[p], mode=self.mode)
assert numpy.allclose(fn3(x_val), [6.,0.,0.])
fn3 = theano.function([x], [p], mode=self.mode)
assert numpy.allclose(fn3(x_val), [6., 0., 0.])
# now with verify_grad
unittest_tools.verify_grad(Prod(axis=1), [x_val], mode=self.mode)
......@@ -511,10 +518,10 @@ class test_Prod(unittest.TestCase):
def test_prod_without_zeros(self):
x = theano.tensor.dmatrix()
x_val = numpy.array([[1,2,3],[0,5,6],[0,0,9]], dtype='float32')
x_val = numpy.array([[1, 2, 3], [0, 5, 6], [0, 0, 9]], dtype='float32')
pwz = ProdWithoutZeros(axis=1)(x)
fn = theano.function([x], pwz, mode=self.mode)
assert numpy.allclose(fn(x_val), [6,30,9])
assert numpy.allclose(fn(x_val), [6, 30, 9])
pwz_a0 = ProdWithoutZeros(axis=0)(x)
fn_a0 = theano.function([x], pwz_a0, mode=self.mode)
......@@ -522,25 +529,30 @@ class test_Prod(unittest.TestCase):
def test_other_grad_tests(self):
x = theano.tensor.dmatrix()
x_val1 = numpy.array([[1,2,3],[0,5,6],[0,0,9]], dtype='float32')
x_val2 = numpy.array([[1,2,0],[0,5,6],[7,8,9],[9,10,0]], dtype='float32')
x_val1 = numpy.array([[1, 2, 3], [0, 5, 6], [0, 0, 9]],
dtype='float32')
x_val2 = numpy.array([[1, 2, 0], [0, 5, 6], [7, 8, 9], [9, 10, 0]],
dtype='float32')
rng = rng = numpy.random.RandomState(43)
p = Prod(axis=1)
grad_p = theano.tensor.grad(p(x).sum(), x)
grad_fn = theano.function([x], grad_p, mode=self.mode)
assert numpy.allclose(grad_fn(x_val1), [[6.,3.,2.],[30.,0.,0.],[0.,0.,0.]])
assert numpy.allclose(grad_fn(x_val2), [[0., 0., 2.], [30., 0., 0.], [72., 63., 56.], [0., 0., 90.]])
assert numpy.allclose(grad_fn(x_val1), [[6., 3., 2.], [30., 0.,
0.], [0., 0., 0.]])
assert numpy.allclose(grad_fn(x_val2), [[0., 0., 2.], [30.,
0., 0.], [72., 63., 56.], [0., 0., 90.]])
p_axis0 = Prod(axis=0)
grad_p_axis0 = theano.tensor.grad(p_axis0(x).sum(), x)
grad_fn_axis0 = theano.function([x], grad_p_axis0, mode=self.mode)
assert numpy.allclose(grad_fn_axis0(x_val2), [[0., 400., 0.],[63., 160., 0.], [0., 100., 0.], [0., 80., 0.]])
assert numpy.allclose(grad_fn_axis0(x_val2), [[0., 400.,
0.], [63., 160., 0.], [0., 100., 0.], [0., 80., 0.]])
tensor.verify_grad(p, [x_val1], rng=rng, mode=self.mode)
def test_mul_without_zeros_zeros(self):
a = numpy.zeros((3,3))
a = numpy.zeros((3, 3))
x = theano.tensor.dmatrix()
......@@ -655,6 +667,7 @@ class T_sum_dtype(unittest.TestCase):
idx += 1
class T_mean_dtype(unittest.TestCase):
def test_mean_default_dtype(self):
"""
......@@ -710,6 +723,7 @@ class T_mean_dtype(unittest.TestCase):
idx += 1
class T_prod_dtype(unittest.TestCase):
def test_prod_default_dtype(self):
"""
......@@ -761,6 +775,7 @@ class T_prod_dtype(unittest.TestCase):
idx += 1
class T_prod_without_zeros_dtype(unittest.TestCase):
def test_prod_without_zeros_default_dtype(self):
"""
......@@ -844,11 +859,8 @@ if __name__ == '__main__':
"""
if __name__ == '__main__':
t = TestElemwise('setUp')
t.setUp()
t.test_infer_shape()
theano/tensor/tests/test_opt.py
浏览文件 @ 7885e618
This source diff could not be displayed because it is too large. You can view the blob instead.
theano/tests/test_rop.py
浏览文件 @ 7885e618
差异被折叠。
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论