Skip to content

P
pytensor
提交 e9328fdd authored 作者: Pascal Lamblin's avatar Pascal Lamblin
浏览文件
操作

Merge pull request #2706 from abergeron/merge_test_fixes

Merge test fixes
上级 b2d3d192 575e4594
全部展开 隐藏空白字符变更
内嵌 并排
正在显示 包含 95 行增加 和 305 行删除
theano/sandbox/cuda/tests/test_basic_ops.py
浏览文件 @ e9328fdd
......@@ -945,18 +945,18 @@ class TestAlloc(theano.tensor.tests.test_basic.TestAlloc):
dtype = "float32"
mode = mode_with_gpu
shared = staticmethod(cuda.shared_constructor)
allocs = [B.GpuAlloc, B.GpuAlloc, tensor.Alloc]
allocs = [B.GpuAlloc(), B.GpuAlloc(), tensor.Alloc()]
class T_Join_and_Split(theano.tensor.tests.test_basic.T_Join_and_Split):
def setUp(self):
utt.seed_rng()
self.mode = mode_with_gpu.excluding('constant_folding')
self.join_op = cuda.GpuJoin
self.join_op = cuda.GpuJoin()
# No gpu split.
self.split_op = tensor.Split
self.split_op_class = tensor.Split
# No Make vector on the gpu, Join used instead
self.make_vector_op = cuda.GpuJoin
self.make_vector_op = cuda.GpuJoin()
self.floatX = "float32"
# In FAST_COMPILE mode, we force the FAST_RUN mode for optimization.
self.hide_error = theano.config.mode not in ['DebugMode', 'DEBUG_MODE']
......
theano/sandbox/gpuarray/tests/test_basic_ops.py
浏览文件 @ e9328fdd
......@@ -7,9 +7,10 @@ import theano
import theano.tensor as T
from theano.tensor import TensorType
from theano.tensor.basic import alloc
from theano.tensor.tests.test_basic import (
rand, safe_make_node, T_reshape, T_Join_and_Split
)
# Don't import test classes otherwise they get tested as part of the file
from theano.tensor.tests import test_basic
from theano.tensor.tests.test_basic import rand, safe_make_node
from theano.tests.unittest_tools import SkipTest
from numpy.testing.noseclasses import KnownFailureTest
......@@ -304,7 +305,7 @@ class TestAlloc(theano.tensor.tests.test_basic.TestAlloc):
dtype = "float32"
mode = mode_with_gpu
shared = staticmethod(gpuarray_shared_constructor)
allocs = [GpuAlloc, GpuAlloc, T.Alloc]
allocs = [GpuAlloc(), GpuAlloc(), T.Alloc()]
def test_shape():
......@@ -340,33 +341,32 @@ def test_gpu_contiguous():
assert f(a_val, 2).flags.c_contiguous
class G_reshape(T_reshape):
class G_reshape(test_basic.T_reshape):
def shortDescription(self):
return None
def __init__(self, name):
T_reshape.__init__(self, name,
shared=gpuarray_shared_constructor,
op=GpuReshape,
mode=mode_with_gpu,
# avoid errors with limited devices
# dtype='float32',
ignore_topo=(HostFromGpu, GpuFromHost,
theano.compile.DeepCopyOp,
theano.sandbox.gpuarray.elemwise.GpuElemwise,
theano.tensor.opt.Shape_i,
theano.tensor.opt.MakeVector))
test_basic.T_reshape.__init__(
self, name,
shared=gpuarray_shared_constructor,
op=GpuReshape,
mode=mode_with_gpu,
ignore_topo=(HostFromGpu, GpuFromHost,
theano.compile.DeepCopyOp,
theano.sandbox.gpuarray.elemwise.GpuElemwise,
theano.tensor.opt.Shape_i,
theano.tensor.opt.MakeVector))
assert self.op == GpuReshape
class G_Join_and_Split(T_Join_and_Split):
class G_Join_and_Split(test_basic.T_Join_and_Split):
def setUp(self):
super(G_Join_and_Split, self).setUp()
self.mode = mode_with_gpu.excluding('constant_folding')
self.join_op = GpuJoin
self.split_op = GpuSplit
self.join_op = GpuJoin()
self.split_op_class = GpuSplit
# Use join instead of MakeVector since there is no MakeVector on GPU
self.make_vector_op = GpuJoin
self.make_vector_op = GpuJoin()
# this is to avoid errors with limited devices
self.floatX = 'float32'
self.hide_error = theano.config.mode not in ['DebugMode', 'DEBUG_MODE']
......
theano/sandbox/gpuarray/tests/test_conv_cuda_ndarray.py
浏览文件 @ e9328fdd
......@@ -400,208 +400,12 @@ def get_valid_shapes():
return shapes
def test_valid_0_2():
seed_rng()
shapes = get_valid_shapes()
version = [0, 2]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[3] > device_prop['maxThreadsDim0']:
continue
if ishape[1] > 1:
continue
if ((numpy.prod(ishape[2:]) + numpy.prod(kshape[2:])) * 4 >
(16 * 1024 - 150)):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid_1_3_11_12():
seed_rng()
shapes = get_valid_shapes()
version = [1, 3, 11, 12]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[3] > device_prop['maxThreadsDim0']:
continue
if ((numpy.prod(ishape[2:]) + numpy.prod(kshape[2:])) * 4 >
(16 * 1024 - 150)):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid_4():
seed_rng()
shapes = get_valid_shapes()
version = [4]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[3] > device_prop['maxThreadsDim0']:
continue
if ishape[1] > 1:
continue
if ((kshape[2] * ishape[3] * 4 + numpy.prod(kshape[2:]) * 4) >
(16 * 1024 - 150)):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid_5():
seed_rng()
shapes = get_valid_shapes()
version = [5]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
# print len(shapes)
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[3] > device_prop['maxThreadsDim0']:
continue
if ((kshape[2] * ishape[3] * 4 + numpy.prod(kshape[2:]) * 4) >
(16 * 1024 - 150)):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
# print len(shapes2)
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid_7_8_13():
seed_rng()
shapes = get_valid_shapes()
# This is to test the "new" lower shared memory usage.
shapes.append(((10, 30, 60, 60), (20, 30, 40, 40),
(1, 1), (1, 1), (1, 1)))
version = [7, 8, 13]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
# print len(shapes)
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[2] * oshape[3] > device_prop['maxThreadsDim0']:
continue
if max(numpy.prod(ishape[2:]) * 4 + 2 * kshape[3] * 4,
oshape[2] * oshape[3] * 4 * 2) > (16 * 1024 - 150):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
# print len(shapes2)
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid_9_10():
seed_rng()
shapes = get_valid_shapes()
version = [9, 10]
verbose = 0
random = True
print_ = False
ones = False
if ones:
random = False
shapes2 = []
# print len(shapes)
for id, (ishape, kshape, subshape, istride, kstride) in enumerate(shapes):
oshape = [ishape[0]] + [kshape[0]] + list(numpy.asarray(ishape[2:]) -
numpy.asarray(kshape[2:]) +
numpy.asarray([1, 1]))
if oshape[3] > device_prop['maxThreadsDim0']:
continue
if (kshape[3] * 4 + ishape[3]) > (16 * 1024 - 150):
continue
if subshape == (1, 1):
shapes2.append((ishape, kshape, subshape, istride, kstride))
shapes = shapes2
# print len(shapes2)
exec_conv(version, shapes, verbose, random, 'valid',
print_=print_, ones=ones, rtol=1.1e-5)
def test_valid():
seed_rng()
shapes = get_valid_shapes()
# shapes=shapes[400:426]
# I put -1 in case we forget to add version in the test to.
# I put -2 to test the reference version.
version = [-2, -1, 6]
version = [-1]
verbose = 0
# version=[1]
random = True
print_ = False
......@@ -666,10 +470,8 @@ def test_full():
, ((2, 4, 1050, 13), (3, 4, 10, 11), (1, 1), (1, 1), (1, 1))
]
# shapes=shapes[:277]
version = [-2, -1, 0, 1, 2, 3, 4, 5]
version = [-1]
verbose = 0
# version=[4]
random = True
exec_conv(version, shapes, verbose, random, 'full')
......@@ -689,9 +491,8 @@ def test_subsample():
shapes += get_shapes2(scales_img=(2, 2), subsample=(2, 1))
shapes += get_shapes2(scales_img=(2, 2), subsample=(2, 2))
# We put only the version that implement the subsample to make the test faster.
version_valid = [-2, -1, 1, 3, 11, 12]
version_full = [-2, -1]
version_valid = [-1]
version_full = [-1]
verbose = 0
random = True
print_ = False
......
theano/sandbox/gpuarray/tests/test_neighbours.py
浏览文件 @ e9328fdd
......@@ -12,6 +12,3 @@ class T_GpuImages2Neibs(test_neighbours.T_Images2Neibs):
mode = mode_with_gpu
op = GpuImages2Neibs
dtypes = ['int64', 'float32', 'float64']
if __name__ == '__main__':
unittest.main()
theano/sandbox/gpuarray/tests/test_subtensor.py
浏览文件 @ e9328fdd
......@@ -3,8 +3,7 @@ import numpy
import theano
from theano import tensor
from theano.compile import DeepCopyOp
from theano.tensor.tests.test_subtensor import T_subtensor
from theano.tensor.tests import test_subtensor
from ..basic_ops import HostFromGpu, GpuFromHost
from ..subtensor import (GpuIncSubtensor, GpuSubtensor,
......@@ -15,21 +14,22 @@ from .test_basic_ops import mode_with_gpu
class G_subtensor(T_subtensor):
class G_subtensor(test_subtensor.T_subtensor):
def shortDescription(self):
return None
def __init__(self, name):
T_subtensor.__init__(self, name,
shared=gpuarray_shared_constructor,
sub=GpuSubtensor,
inc_sub=GpuIncSubtensor,
adv_incsub1=GpuAdvancedIncSubtensor1,
mode=mode_with_gpu,
# avoid errors with limited devices
dtype='float32',
ignore_topo=(HostFromGpu, GpuFromHost,
DeepCopyOp))
test_subtensor.T_subtensor.__init__(
self, name,
shared=gpuarray_shared_constructor,
sub=GpuSubtensor,
inc_sub=GpuIncSubtensor,
adv_incsub1=GpuAdvancedIncSubtensor1,
mode=mode_with_gpu,
# avoid errors with limited devices
dtype='float32',
ignore_topo=(HostFromGpu, GpuFromHost,
DeepCopyOp))
# GPU opt can't run in fast_compile only.
self.fast_compile = False
assert self.sub == GpuSubtensor
......
theano/tensor/basic.py
浏览文件 @ e9328fdd
......@@ -3539,7 +3539,7 @@ class Join(Op):
split_gz = [split_gz]
# Split.make_node isn't always able to infer the right
# broadcast. As the grad need to keep the information,
# readd it if needed.
# read it if needed.
split_gz = [patternbroadcast(g, t.broadcastable)
for t, g in zip(tensors, split_gz)]
rval = rval + split_gz
......
theano/tensor/opt.py
浏览文件 @ e9328fdd
......@@ -2549,8 +2549,7 @@ compile.optdb.register('local_inplace_setsubtensor',
def local_inplace_incsubtensor1(node):
""" also work for GpuAdvancedIncSubtensor1 """
if isinstance(node.op, AdvancedIncSubtensor1) and not node.op.inplace:
new_op = node.op.__class__(
inplace=True, set_instead_of_inc=node.op.set_instead_of_inc)
new_op = node.op.clone_inplace()
new_node = new_op(*node.inputs)
return [new_node]
return False
......@@ -5258,7 +5257,8 @@ for i in xrange(1,len(p64)): print i, 64[i]-p64[i-1]
# ###############
# # Loop fusion #
# ###############
def local_elemwise_fusion_op(OP, max_input_fct=lambda node: 1024):
def local_elemwise_fusion_op(OP, max_input_fct=lambda node: 1024,
maker=None):
"""
We parametrize it to make it work for Elemwise and GpuElemwise op.
......@@ -5277,6 +5277,9 @@ def local_elemwise_fusion_op(OP, max_input_fct=lambda node: 1024):
enough that if we hit it, I'm not sure it
will affect performance.
"""
if maker is None:
def maker(node, scalar_op):
return OP(scalar_op)
def local_fuse(node):
"""
As part of specialization, we fuse two consecutive elemwise Ops of the
......@@ -5458,7 +5461,7 @@ your code will run correctly, but may be slower.""")
# create the new node.
# Do not call make_node to have test_value
n = OP(C)(*inputs).owner
n = maker(node, C)(*inputs).owner
assert len(n.outputs) == 1
assert node.outputs[0].dtype == n.outputs[0].dtype
......
theano/tensor/subtensor.py
浏览文件 @ e9328fdd
......@@ -1600,23 +1600,13 @@ def _sum_grad_over_bcasted_dims(x, gx):
class AdvancedSubtensor1(Op):
"""Implement x[ilist] where ilist is a vector of integers."""
# sparse_grad doesn't go in here since it only affects the output
# of the grad() method.
__props__ = ()
def __init__(self, sparse_grad=False):
self.sparse_grad = sparse_grad
def __hash__(self):
return hash(type(self))
def __eq__(self, other):
# Don't check the sparse_grad attribute as
# This don't change the output of this op
# So we want the merge optimier to merge two op
# that differ from there sparse_grad attribute.
return type(self) == type(other)
def __str__(self):
return self.__class__.__name__
def make_node(self, x, ilist):
x_ = theano.tensor.as_tensor_variable(x)
ilist_ = theano.tensor.as_tensor_variable(ilist)
......@@ -1794,19 +1784,18 @@ advanced_subtensor1 = AdvancedSubtensor1()
class AdvancedIncSubtensor1(Op):
"""Increments a subtensor using advanced slicing (list of index)"""
__props__ = ('inplace', 'set_instead_of_inc')
def __init__(self, inplace=False, set_instead_of_inc=False):
self.inplace = inplace
self.set_instead_of_inc = set_instead_of_inc
if inplace:
self.destroy_map = {0: [0]}
def __hash__(self):
return hash((type(self), self.inplace, self.set_instead_of_inc))
def __eq__(self, other):
return (type(self) == type(other)
and self.inplace == other.inplace
and self.set_instead_of_inc == other.set_instead_of_inc)
def clone_inplace(self):
return self.__class__(
inplace=True,
set_instead_of_inc=self.set_instead_of_inc)
def __str__(self):
if self.inplace:
......
theano/tensor/tests/test_blas.py
浏览文件 @ e9328fdd
......@@ -1472,14 +1472,14 @@ class BaseGemv(object):
x_v = x_v.astype("float32")
y_v = y_v.astype("float32")
alpha = T.dscalar('a')
a = T.fmatrix('w')
x = T.fvector('v')
y = T.fvector('t')
alpha = T.dscalar('alpha')
a = self.shared(a_v)
x = self.shared(x_v)
y = self.shared(y_v)
rval = T.dot(a, x) * alpha + y
f = theano.function([a, x, y, alpha], rval, mode=self.mode)
f = theano.function([alpha], rval, mode=self.mode)
# this function is currently optimized so that the gemv is
# done inplace on a temporarily allocated-buffer, which is
# then scaled by alpha and to t with a fused elemwise.
......@@ -1491,7 +1491,7 @@ class BaseGemv(object):
assert node.outputs[0].dtype == 'float32'
assert n_gemvs == 1, n_gemvs
self.assertFunctionContains1(f, self.gemv_inplace)
f(a_v, x_v, y_v, alpha_v)
f(alpha_v)
class TestSgemv(TestCase, BaseGemv, unittest_tools.TestOptimizationMixin):
......
theano/tensor/tests/test_elemwise.py
浏览文件 @ e9328fdd
......@@ -27,6 +27,7 @@ def FunctionGraph(i, o):
class test_DimShuffle(unittest_tools.InferShapeTester):
op = DimShuffle
type = TensorType
def with_linker(self, linker):
for xsh, shuffle, zsh in [((2, 3), (1, 'x', 0), (3, 1, 2)),
......@@ -40,12 +41,12 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
((1, 1, 1), (), ()),
((1,), ('x', 'x'), (1, 1))]:
ib = [(entry == 1) for entry in xsh]
x = TensorType('float64', ib)('x')
x = self.type('float64', ib)('x')
e = self.op(ib, shuffle)(x)
f = copy(linker).accept(FunctionGraph([x], [e])).make_function()
assert f(numpy.ones(xsh)).shape == zsh
# test that DimShuffle.infer_shape work correctly
x = TensorType('float64', ib)('x')
x = self.type('float64', ib)('x')
e = self.op(ib, shuffle)(x)
f = copy(linker).accept(FunctionGraph([x],
[e.shape])).make_function()
......@@ -53,12 +54,12 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
# Test when we drop a axis that is not broadcastable
ib = [False, True, False]
x = TensorType('float64', ib)('x')
x = self.type('float64', ib)('x')
self.assertRaises(ValueError, self.op, ib, shuffle)
# Test when we drop a axis that don't have shape 1
ib = [True, True, False]
x = TensorType('float64', ib)('x')
x = self.type('float64', ib)('x')
e = self.op(ib, (1, 2))(x)
f = copy(linker).accept(FunctionGraph([x], [e.shape])).make_function()
self.assertRaises(TypeError, f, numpy.ones((2, 1, 4)))
......@@ -66,7 +67,7 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
# Test that we can't take a dimensions multiple time
xsh, shuffle, zsh = ((1, 1, 4), (0, 1, 2, 0), (1, 4))
ib = [False, True, False]
x = TensorType('float64', ib)('x')
x = self.type('float64', ib)('x')
self.assertRaises(ValueError, DimShuffle, ib, shuffle)
def test_perform(self):
......@@ -89,7 +90,7 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
((1, 1, 1), ()),
((1,), ('x', 'x'))]:
ib = [(entry == 1) for entry in xsh]
adtens = TensorType('float64', ib)('x')
adtens = self.type('float64', ib)('x')
adtens_val = numpy.ones(xsh)
self._compile_and_check([adtens],
[self.op(ib, shuffle)(adtens)],
......@@ -97,7 +98,7 @@ class test_DimShuffle(unittest_tools.InferShapeTester):
warn=False)
def test_too_big_rank(self):
x = tensor.dscalar()
x = self.type('float64', broadcastable=())()
y = x.dimshuffle(('x',) * (numpy.MAXDIMS + 1))
self.assertRaises(ValueError, y.eval, {x: 0})
......@@ -328,6 +329,7 @@ class test_CAReduce(unittest_tools.InferShapeTester):
((), None),
((), ())
]
type = TensorType
def with_linker(self, linker, scalar_op=scalar.add, dtype="floatX",
pre_scalar_op=None,
......@@ -335,7 +337,7 @@ class test_CAReduce(unittest_tools.InferShapeTester):
for xsh, tosum in self.cases:
if dtype == "floatX":
dtype = theano.config.floatX
x = TensorType(dtype, [(entry == 1) for entry in xsh])('x')
x = self.type(dtype, [(entry == 1) for entry in xsh])('x')
d = {}
if pre_scalar_op is not None:
d = {"pre_scalar_op": pre_scalar_op}
......@@ -438,7 +440,7 @@ class test_CAReduce(unittest_tools.InferShapeTester):
if test_nan:
try:
self.assertTrue(
theano.tensor.TensorType.values_eq(f(xv), zv),
self.type.values_eq(f(xv), zv),
(f(xv), zv))
except NotImplementedError:
# GpuCAReduce don't implement all cases when size is 0
......@@ -453,7 +455,7 @@ class test_CAReduce(unittest_tools.InferShapeTester):
# GpuCAReduce don't implement all cases when size is 0
assert xv.size == 0
x = TensorType(dtype, [(entry == 1) for entry in xsh])('x')
x = self.type(dtype, [(entry == 1) for entry in xsh])('x')
if tensor_op is None:
e = self.op(scalar_op, axis=tosum)(x)
else:
......@@ -538,7 +540,7 @@ class test_CAReduce(unittest_tools.InferShapeTester):
if dtype is None:
dtype = theano.config.floatX
for xsh, tosum in self.cases:
x = TensorType(dtype, [(entry == 1) for entry in xsh])('x')
x = self.type(dtype, [(entry == 1) for entry in xsh])('x')
if pre_scalar_op is not None:
x = pre_scalar_op(x)
if tosum is None:
......
theano/tensor/tests/test_subtensor.py
浏览文件 @ e9328fdd
......@@ -49,6 +49,7 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
adv_incsub1=tensor.AdvancedIncSubtensor1,
mode=None,
dtype=theano.config.floatX,
type=tensor.TensorType,
ignore_topo=DeepCopyOp):
self.shared = shared
self.sub = sub
......@@ -59,6 +60,7 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
mode = theano.compile.mode.get_default_mode()
self.mode = mode
self.dtype = dtype
self.type = type
self.ignore_topo = ignore_topo
self.fast_compile = theano.config.mode == 'FAST_COMPILE'
self.ops = (sub, inc_sub, adv_sub1, adv_incsub1)
......@@ -88,8 +90,10 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
Subtensor.debug = False
utt.seed_rng()
def eval_output_and_check(self, t, list=False):
f = inplace_func([], t, mode=self.mode)
def eval_output_and_check(self, t, list=False, mode=None):
if mode is None:
mode = self.mode
f = inplace_func([], t, mode=mode)
topo = f.maker.fgraph.toposort()
topo_ = [node for node in topo if not isinstance(node.op,
self.ignore_topo)]
......@@ -167,12 +171,8 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
n = self.shared(numpy.ones((), dtype=self.dtype))
t = self.sub([])(n)
self.assertTrue(isinstance(t.owner.op, Subtensor))
mode = self.mode
self.mode = mode.excluding("local_useless_subtensor")
try:
self.eval_output_and_check(t)
finally:
self.mode = mode
self.eval_output_and_check(
t, mode=self.mode.excluding("local_useless_subtensor"))
def test1_err_invalid(self):
n = self.shared(numpy.ones(1, dtype=self.dtype))
......@@ -885,16 +885,14 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
Test increment and set with broadcast
"""
X = tensor.matrix(dtype=self.dtype)
X = self.shared(numpy.ones((9, 9)).astype(self.dtype))
y = set_subtensor(X[1::, 1::], 0)
f = self.function([X], [y],
f = self.function([], [y],
op=self.inc_sub,
N=1)
out = f()
x_ = numpy.ones((9, 9))
out = f(x_.astype('float32'))
res = x_.copy()
res = numpy.ones((9, 9))
res[1::, 1::] = 0
assert numpy.allclose(out, res)
......@@ -925,9 +923,9 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
# Symbolic variable to be incremented.
# We create a new one every time in order not to
# have duplicated variables in the function's inputs
data_var = tensor.tensor(
broadcastable=[False] * data_n_dims,
dtype=self.dtype)
data_var = self.type(
broadcastable=[False] * data_n_dims,
dtype=self.dtype)()
# Symbolic variable with rows to be incremented.
idx_var = theano.tensor.vector(dtype='int64')
n_to_inc = rng.randint(data_shape[0])
......@@ -935,9 +933,9 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
idx_num = rng.randint(0, data_shape[0], n_to_inc)
idx_num = idx_num.astype('int64')
# Symbolic variable with increment value.
inc_var = tensor.tensor(
broadcastable=[False] * inc_n_dims,
dtype=self.dtype)
inc_var = self.type(
broadcastable=[False] * inc_n_dims,
dtype=self.dtype)()
# Trick for the case where `inc_shape` is the same as
# `data_shape`: what we actually want is the first
# shape element to be equal to the number of rows to
......
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