Skip to content

P
pytensor
提交 f61e8099 authored 作者: lamblin's avatar lamblin
浏览文件
操作

Merge pull request #639 from nouiz/ifelse

Make ifelse work on gpu
上级 4ebf9e1a b31fda26
隐藏空白字符变更
内嵌 并排
正在显示 包含 289 行增加 和 211 行删除
NEWS.txt
浏览文件 @ f61e8099
......@@ -88,6 +88,8 @@ New Features
* Garbage collection of intermediate results during Theano function calls
for Ops with C code (Pascal L.)
* Theano flags compiledir_format now support the parameter numpy_version.
* Theano GPU variables, shared variable and constant now support <, <=,
> and >= as as those not on the GPU.
Sparse
* Implement theano.sparse.mul(sparse1, sparse2) when both inputs don't
......
theano/ifelse.py
浏览文件 @ f61e8099
......@@ -340,7 +340,7 @@ def ifelse(condition, then_branch, else_branch, name=None):
if then_branch_elem.type != else_branch_elem.type:
# If the types still don't match, there is a problem.
raise ValueError(
raise TypeError(
'The two branches should have identical types, but '
'they are %s and %s respectively. This error could be '
'raised if for example you provided a one element '
......
theano/sandbox/cuda/opt.py
浏览文件 @ f61e8099
......@@ -11,6 +11,7 @@ import theano
from theano.scan_module import scan_utils, scan_op, scan_opt
from theano import scalar as scal
from theano import tensor, compile, gof
import theano.ifelse
from theano.compile import optdb
from theano.gof import (local_optimizer, EquilibriumDB, SequenceDB, ProxyDB,
......@@ -366,36 +367,47 @@ def local_gpu_lazy_ifelse(node):
ifelse(host_from_gpu) -> host_from_gpu(ifelse)
"""
if hasattr(theano, "lazycond"):
gpu_ifelse = theano.lazycond.IfElse(gpu=True)
if node.op == gpu_from_host:
host_input = node.inputs[0]
if (host_input.owner
and host_input.owner.op == theano.lazycond.ifelse):
c, t, f = host_input.owner.inputs
if not isinstance(f.type, CudaNdarrayType):
f = gpu_from_host(f)
if not isinstance(t.type, CudaNdarrayType):
t = gpu_from_host(t)
if isinstance(c.type, CudaNdarrayType):
c = host_from_gpu(c)
return [gpu_ifelse(c, t, f)]
if node.op == theano.lazycond.ifelse:
if numpy.any([(i.owner and i.owner.op == host_from_gpu)
for i in node.inputs]):
c, t, f = node.inputs
if not isinstance(f.type, CudaNdarrayType):
f = gpu_from_host(f)
if not isinstance(t.type, CudaNdarrayType):
t = gpu_from_host(t)
if isinstance(c.type, CudaNdarrayType):
c = host_from_gpu(c)
return [host_from_gpu(gpu_ifelse(c, t, f))]
if isinstance(node.op, theano.ifelse.IfElse) and not node.op.gpu:
gpu_ifelse = theano.ifelse.IfElse(node.op.n_outs, gpu=True)
outs_clients = reduce(list.__add__,
[out.clients for out in node.outputs])
if numpy.any([(i.owner and i.owner.op == host_from_gpu)
for i in node.inputs]) or numpy.any(
[c != 'output' and c.op == gpu_from_host for c, idx
in outs_clients]):
c = node.inputs[0]
outs = node.inputs[1:]
# Should not happen, but just in case
if isinstance(c.type, CudaNdarrayType):
c = host_from_gpu(c)
for i in range(len(outs)):
if not isinstance(outs[i], CudaNdarrayType):
outs[i] = gpu_from_host(outs[i])
return [host_from_gpu(out) for out in
gpu_ifelse.make_node(c, *outs).outputs]
if node.op == gpu_from_host:
host_input = node.inputs[0]
if (host_input.owner and
isinstance(host_input.owner.op, theano.ifelse.IfElse) and
not host_input.owner.op.gpu):
gpu_ifelse = theano.ifelse.IfElse(host_input.owner.op.n_outs,
gpu=True)
c = host_input.owner.inputs[0]
outs = host_input.owner.inputs[1:]
# Should not happen, but just in case
if isinstance(c.type, CudaNdarrayType):
c = host_from_gpu(c)
for i in range(len(outs)):
if not isinstance(outs[i], CudaNdarrayType):
outs[i] = gpu_from_host(outs[i])
outs = gpu_ifelse.make_node(c, *outs).outputs
return outs
return False
......@@ -1306,11 +1318,11 @@ def local_gpualloc(node):
if node.inputs[0].owner and \
node.inputs[0].owner.op == host_from_gpu:
replace = True
if all([c != 'output' and c.op == gpu_from_host
elif all([c != 'output' and c.op == gpu_from_host
for c, idx in node.outputs[0].clients]):
# if all clients are on gpu
replace = True
if all([c != 'output' and
elif all([c != 'output' and
c.op == tensor.join and
all([i.owner and
i.owner.op in [host_from_gpu, tensor.alloc]
......
theano/sandbox/cuda/tests/test_basic_ops.py
浏览文件 @ f61e8099
......@@ -265,11 +265,7 @@ def test_elemwise0():
assert f.maker.env.toposort()[1].op.destroy_map.items() == [(0, [0])]
a0 = a.get_value() * 1.0
print 'BEFORE ADD', a.get_value()
for i, node in enumerate(f.maker.env.toposort()):
print i, node
f(numpy.ones((4, 4), dtype='float32'))
print 'AFTER ADD', a.get_value()
assert numpy.all(a0 + 1.0 == a.get_value())
......@@ -279,7 +275,6 @@ def test_elemwise_bad_broadcast():
y = cuda.fmatrix('y')
f = theano.function([x, y], x * y, mode=mode_with_gpu)
print f.maker.env.toposort()
assert len(f.maker.env.toposort()) == 2
assert isinstance(f.maker.env.toposort()[0].op, cuda.GpuElemwise)
assert f.maker.env.toposort()[1].op == cuda.host_from_gpu
......@@ -302,20 +297,13 @@ def test_elemwise1():
b = tensor.fmatrix()
#let debugmode catch any mistakes
print >> sys.stdout, "STARTING FUNCTION 1"
f = pfunc([b], [], updates=[(a, b ** a)], mode=mode_with_gpu)
for i, node in enumerate(f.maker.env.toposort()):
print i, node
f(theano._asarray(numpy.random.rand(*shape), dtype='float32') + 0.3)
print >> sys.stdout, "STARTING FUNCTION 2"
#let debugmode catch any mistakes
f = pfunc([b], [], updates=[(a, tensor.exp(b ** a))], mode=mode_with_gpu)
for i, node in enumerate(f.maker.env.toposort()):
print i, node
f(theano._asarray(numpy.random.rand(*shape), dtype='float32') + 0.3)
print >> sys.stdout, "STARTING FUNCTION 3"
#let debugmode catch any mistakes
f = pfunc([b], [], updates=[(a, a + b * tensor.exp(b ** a))],
mode=mode_with_gpu)
......@@ -325,7 +313,6 @@ def test_elemwise1():
def test_elemwise2():
""" Several kinds of elemwise expressions with dimension permutations """
rng = numpy.random.RandomState(int(time.time()))
print 'random?', rng.rand(3)
shape = (3, 5)
for pattern in [(0, 1), (1, 0)]:
a = tcn.shared_constructor(theano._asarray(rng.rand(*shape),
......@@ -335,11 +322,9 @@ def test_elemwise2():
mode=mode_with_gpu)
has_elemwise = False
for i, node in enumerate(f.maker.env.toposort()):
print >> sys.stdout, i, node
has_elemwise = has_elemwise or isinstance(node.op, tensor.Elemwise)
assert not has_elemwise
#let debugmode catch errors
print >> sys.stdout, 'pattern', pattern
f(theano._asarray(rng.rand(*shape), dtype='float32') * .3)
shape = (3, 4, 5, 6)
......@@ -350,7 +335,6 @@ def test_elemwise2():
tensor.exp(b ** a).dimshuffle([2, 0, 3, 1]))], mode=mode_with_gpu)
has_elemwise = False
for i, node in enumerate(f.maker.env.toposort()):
print i, node
has_elemwise = has_elemwise or isinstance(node.op, tensor.Elemwise)
assert not has_elemwise
#let debugmode catch errors
......@@ -365,17 +349,11 @@ def test_elemwise3():
a = tcn.shared_constructor(theano._asarray(numpy.random.rand(*shape),
dtype='float32'), 'a')
b = tensor.fvector()
print b.type
print tensor.constant(1).type
print (1 + b).type
print (1 + b ** a).type
print tensor.exp((1 + b ** a)).type
new_val = (a + b).dimshuffle([2, 0, 3, 1])
new_val *= tensor.exp(1 + b ** a).dimshuffle([2, 0, 3, 1])
f = pfunc([b], [], updates=[(a, new_val)], mode=mode_with_gpu)
has_elemwise = False
for i, node in enumerate(f.maker.env.toposort()):
print >> sys.stdout, i, node
has_elemwise = has_elemwise or isinstance(node.op, tensor.Elemwise)
assert not has_elemwise
#let debugmode catch errors
......@@ -396,7 +374,6 @@ def test_elemwise4():
mode=mode_with_gpu)
has_elemwise = False
for i, node in enumerate(f.maker.env.toposort()):
print >> sys.stdout, i, node
has_elemwise = has_elemwise or isinstance(node.op, tensor.Elemwise)
assert not has_elemwise
#let debugmode catch errors
......@@ -420,7 +397,6 @@ def test_elemwise_comparaison_cast():
f = pfunc([a, b], tensor.cast(g(a, b), 'float32'), mode=mode_with_gpu)
#theano.printing.debugprint(f)
out = f(av, bv)
assert numpy.all(out == ans)
assert any([isinstance(node.op, cuda.GpuElemwise)
......@@ -451,7 +427,6 @@ def test_elemwise_composite_float64():
b),
'float32'), mode=mode)
#theano.printing.debugprint(f, print_type=True)
out = f(av, bv)
assert numpy.all(out == ((av ** 2) < bv))
for node in f.maker.env.toposort():
......@@ -509,8 +484,6 @@ def speed_elemwise_collapse():
v = theano._asarray(numpy.random.rand(*shape), dtype='float32')
v = v[:, ::2, :, :]
v = cuda_ndarray.CudaNdarray(v)
for id, n in enumerate(f.maker.env.toposort()):
print id, n
t1 = time.time()
for i in range(100):
#let debugmode catch errors
......@@ -535,8 +508,6 @@ def speed_elemwise_collapse2():
v = theano._asarray(numpy.random.rand(*shape), dtype='float32')
v = v[:, :, :, ::2]
v = cuda_ndarray.CudaNdarray(v)
for id, n in enumerate(f.maker.env.toposort()):
print id, n
t1 = time.time()
for i in range(100):
#let debugmode catch errors
......@@ -560,13 +531,11 @@ def test_elemwise_collapse():
v = theano._asarray(numpy.random.rand(shape[0], 1, *shape[1:]),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(shape[0], 1, *shape[1:]) + v)
print "Expected collapse of all dimensions"
#print "Expected collapse of all dimensions"
def test_elemwise_collapse2():
......@@ -585,13 +554,10 @@ def test_elemwise_collapse2():
v = theano._asarray(numpy.random.rand(shape[0], 5, *shape[1:]),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(shape[0], 1, *shape[1:]) + v)
print "Expected collapse to 3 dimensions"
#print "Expected collapse to 3 dimensions"
def test_elemwise_collapse3():
......@@ -611,13 +577,11 @@ def test_elemwise_collapse3():
v = theano._asarray(numpy.random.rand(5, shape[0], shape[1], 4),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(1, shape[0], shape[1], 1) + v)
print "Expected collapse to 3 dimensions"
#print "Expected collapse to 3 dimensions"
def test_elemwise_collapse4():
......@@ -637,13 +601,10 @@ def test_elemwise_collapse4():
v = theano._asarray(numpy.random.rand(5, shape[0], shape[1], 4),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(1, shape[0], shape[1], 1) + v + 2)
print "Expected collapse to 3 dimensions"
#print "Expected collapse to 3 dimensions"
def test_elemwise_collapse5():
......@@ -663,13 +624,11 @@ def test_elemwise_collapse5():
v = theano._asarray(numpy.random.rand(5, 4, shape[0], shape[1]),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(1, 1, shape[0], shape[1]) + v + 2)
print "Expected collapse to 2 dimensions"
#print "Expected collapse to 2 dimensions"
def test_elemwise_collapse6():
......@@ -688,13 +647,10 @@ def test_elemwise_collapse6():
v = theano._asarray(numpy.random.rand(1, 1, shape[0], shape[1]),
dtype='float32')
v = cuda_ndarray.CudaNdarray(v)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f(v)[0]
assert numpy.allclose(out, a.reshape(1, 1, shape[0], shape[1]) + v)
print "Expected collapse to c contiguous"
#print "Expected collapse to c contiguous"
def test_elemwise_collapse7(atol=1e-6):
......@@ -709,14 +665,11 @@ def test_elemwise_collapse7(atol=1e-6):
a3 = a2.dimshuffle(0, 'x', 1, 2)
f = pfunc([], [a3 + 2], mode=mode_with_gpu)
if False:
for id, n in enumerate(f.maker.env.toposort()):
print id, n
#let debugmode catch errors
out = f()[0]
ans = (a + 2).reshape(shape[0], 1, shape[1], shape[2])
assert numpy.allclose(out, ans, atol=atol)
print "Expected collapse to c contiguous"
#print "Expected collapse to c contiguous"
def test_hostfromgpu_shape_i():
......@@ -838,10 +791,8 @@ def test_gpualloc_output_to_gpu():
f_gpu = theano.function([b], B.gpu_from_host(T.ones_like(a)) + b,
mode=mode_with_gpu)
print f.maker.env.toposort()
print f_gpu.maker.env.toposort()
print f(2)
print f_gpu(2)
f(2)
f_gpu(2)
assert sum([node.op == T.alloc for node in f.maker.env.toposort()]) == 1
assert sum([node.op == B.gpu_alloc
......@@ -924,7 +875,7 @@ def test_inc_subtensor():
dtype='float32')
expr = T.inc_subtensor(x[:, 1:3], y[:, 1:3])
f = theano.function([x, y], expr, mode=mode_with_gpu)
print f.maker.env.toposort()
assert sum([isinstance(node.op, cuda.GpuSubtensor)
for node in f.maker.env.toposort()]) == 1
assert sum([isinstance(node.op, cuda.GpuIncSubtensor) and
......@@ -949,7 +900,7 @@ def test_set_subtensor():
assert sum([isinstance(node.op, cuda.GpuIncSubtensor) and
node.op.set_instead_of_inc == True
for node in f.maker.env.toposort()]) == 1
print f(xval, yval)
f(xval, yval)
def test_many_arg_elemwise():
......
theano/sandbox/cuda/tests/test_memory.py
浏览文件 @ f61e8099
......@@ -5,6 +5,7 @@ import numpy as np
import theano
from theano import tensor
from theano.sandbox import cuda
from theano import ifelse
# Skip test if cuda_ndarray is not available.
from nose.plugins.skip import SkipTest
......@@ -112,3 +113,65 @@ def test_memory():
del derp, variables, grad_derp
print "After deleting shared variable and ref to it", freemem()
assert mem1 == freemem(), (mem1, freemem())
def test_memory_lazy():
"""As test_memory, but with the ifelse op.
We need to test it as the ifelse op with the [c]vm create op not
executed in the graph. This mess with [c]vm gc implementation.
"""
shapes = (200, 100)
# more_alloc1 and more_alloc2 is not the same for both dtype.
# when dtype is float32, the computation is done on the gpu.
# This insert constant on the gpu during compilation
# that raise the number of alloc.
# When dtype is float64, only the shared is on the gpu and it is transferd
# to the cpu for computation. So no extra alloc after compilation.
# more_alloc1 if after the first compilation, more_alloc2 after the second.
for dtype, more_alloc1 in [("float32", 3),
("float64", 0)]:
print dtype
test_params = np.asarray(np.random.randn(np.prod(shapes)), dtype)
some_vector = tensor.vector('some_vector', dtype=dtype)
some_matrix = some_vector.reshape(shapes)
branch_select = tensor.iscalar()
mem1 = freemem()
print "Before shared variable", mem1
variables = cuda.shared_constructor(np.ones((shapes[1],),
dtype='float32'))
derp = tensor.sum(tensor.dot(some_matrix[:shapes[0]], variables))
derp = ifelse.IfElse(1)(branch_select,
derp, some_matrix[:shapes[0]].sum())
derp += 1
print "Shared took ", np.prod(variables.get_value(
borrow=True,
return_internal_type=True).shape) * 4 / 1024, "kB"
mem2 = freemem()
print "Before compilation", mem2
mem2_1 = freemem(extra_alloc=more_alloc1)
obj = theano.function([some_vector, branch_select], derp,
mode=mode_with_gpu)
#theano.printing.debugprint(obj, print_type=True)
mem3 = freemem()
print "After function compilation 1", mem3
assert mem2_1 == mem3, (mem2_1, mem3)
for i in range(3):
obj(test_params, 1)
print "After function evaluation branch true", freemem()
assert mem2_1 == freemem(), (mem2_1, freemem())
obj(test_params, 0)
print "After function evaluation branch false", freemem()
assert mem2_1 == freemem(), (mem2_1, freemem())
del obj
print "After deleting function 1", freemem()
assert mem2 == freemem(), (mem2, freemem())
del derp, variables
print "After deleting shared variable and ref to it", freemem()
assert mem1 == freemem(), (mem1, freemem())
theano/sandbox/cuda/tests/test_opt.py
浏览文件 @ f61e8099
......@@ -11,6 +11,8 @@ import theano
from theano.tests import unittest_tools as utt
import theano.sandbox.cuda as cuda
from theano.sandbox.cuda import basic_ops
if cuda.cuda_available == False:
raise SkipTest('Optional package cuda disabled')
......@@ -330,6 +332,18 @@ class test_local_gpu_tensordot(unittest.TestCase):
f3(tensor1, tensor3)
import theano.tests.test_ifelse
class TestIfElse(theano.tests.test_ifelse.test_ifelse):
dtype = "float32"
mode = mode_with_gpu
cast_output = staticmethod(basic_ops.as_cuda_ndarray_variable)
shared = staticmethod(cuda.shared_constructor)
def get_ifelse(self, n):
return theano.ifelse.IfElse(n, gpu=True, as_view=True)
if __name__ == '__main__':
test_gpualloc()
test_opt_gpujoin_onlyajoin()
......
theano/sandbox/cuda/tests/test_var.py
浏览文件 @ f61e8099
......@@ -5,7 +5,6 @@ from nose.plugins.skip import SkipTest
import theano
from theano import tensor
from theano.ifelse import ifelse
from theano import sparse
from theano.tensor import TensorType
from theano.tests import unittest_tools as utt
......@@ -91,77 +90,3 @@ class T_updates(unittest.TestCase):
output_func = theano.function(inputs=[], outputs=[],
updates={output_var: output_var.sum().dimshuffle('x', 'x')})
output_func()
class T_ifelse(unittest.TestCase):
def setUp(self):
utt.seed_rng()
self.rng = numpy.random.RandomState(seed=utt.fetch_seed())
def test_cuda_tensor(self):
data = self.rng.rand(4).astype('float32')
x = f32sc(data)
y = x + 1
cond = theano.tensor.iscalar('cond')
assert isinstance(x.type, CudaNdarrayType)
assert isinstance(y.type, TensorType)
out1 = ifelse(cond, x, y)
out2 = ifelse(cond, y, x)
assert isinstance(out1.type, TensorType)
assert isinstance(out2.type, TensorType)
f = theano.function([cond], out1)
g = theano.function([cond], out2)
assert numpy.all(f(0) == data + 1)
assert numpy.all(f(1) == data)
assert numpy.all(g(0) == data)
assert numpy.all(g(1) == data + 1)
def test_dtype_mismatch(self):
data = self.rng.rand(5).astype('float32')
x = f32sc(data)
y = tensor.cast(x, 'float64')
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_ndim_mismatch(self):
data = self.rng.rand(5).astype('float32')
x = f32sc(data)
y = tensor.fcol('y')
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_broadcast_mismatch(self):
data = self.rng.rand(2, 3).astype('float32')
x = f32sc(data)
print x.broadcastable
y = tensor.frow('y')
print y.broadcastable
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_sparse_tensor_error(self):
data = self.rng.rand(2, 3).astype('float32')
x = f32sc(data)
y = sparse.matrix('csc', dtype='float32', name='y')
z = sparse.matrix('csr', dtype='float32', name='z')
cond = theano.tensor.iscalar('cond')
# Right now (2012-01-19), a ValueError gets raised, but I thing
# a TypeError (like in the other cases) would be fine.
self.assertRaises((TypeError, ValueError), ifelse, cond, x, y)
self.assertRaises((TypeError, ValueError), ifelse, cond, y, x)
self.assertRaises((TypeError, ValueError), ifelse, cond, x, z)
self.assertRaises((TypeError, ValueError), ifelse, cond, z, x)
self.assertRaises((TypeError, ValueError), ifelse, cond, y, z)
self.assertRaises((TypeError, ValueError), ifelse, cond, z, y)
theano/sandbox/cuda/var.py
浏览文件 @ f61e8099
......@@ -36,14 +36,14 @@ class _operators(tensor.basic._tensor_py_operators):
ndim = property(lambda s:s.type.ndim)
class CudaNdarrayVariable(Variable, _operators):
class CudaNdarrayVariable(_operators, Variable):
pass
CudaNdarrayType.Variable = CudaNdarrayVariable
class CudaNdarrayConstantSignature(tensor.TensorConstantSignature):
pass
class CudaNdarrayConstant(Constant, _operators):
class CudaNdarrayConstant(_operators, Constant):
def signature(self):
return CudaNdarrayConstantSignature((self.type, numpy.asarray(self.data)))
def __str__(self):
......@@ -52,7 +52,7 @@ class CudaNdarrayConstant(Constant, _operators):
return "CudaNdarrayConstant{"+str(numpy.asarray(self.data))+"}"
CudaNdarrayType.Constant = CudaNdarrayConstant
class CudaNdarraySharedVariable(SharedVariable, _operators):
class CudaNdarraySharedVariable(_operators, SharedVariable):
"""
Shared Variable interface to CUDA-allocated arrays
"""
......
theano/tensor/tests/test_sharedvar.py
浏览文件 @ f61e8099
......@@ -432,7 +432,7 @@ def makeSharedTester(shared_constructor_,
else:
shape_grad = tensor.grad(x1_specify_shape.sum(), x1_shared)
shape_constant_fct_grad = theano.function([], shape_grad)
theano.printing.debugprint(shape_constant_fct_grad)
#theano.printing.debugprint(shape_constant_fct_grad)
shape_constant_fct_grad()
#Test that we can replace with values of the different shape
......
theano/tests/test_ifelse.py
浏览文件 @ f61e8099
......@@ -13,48 +13,40 @@ from nose.plugins.skip import SkipTest
import theano
from theano import tensor
import theano.ifelse
from theano.ifelse import IfElse, ifelse
from theano.tests import unittest_tools as utt
class test_ifelse(unittest.TestCase):
class test_ifelse(unittest.TestCase, utt.TestOptimizationMixin):
mode = None
dtype = theano.config.floatX
cast_output = staticmethod(tensor.as_tensor_variable)
shared = staticmethod(theano.shared)
def get_ifelse(self, n):
if theano.config.mode == "FAST_COMPILE":
return IfElse(n)
else:
return IfElse(n, as_view=True)
def test_lazy_if(self):
# Tests that lazy if works .. even if the two results have different
# shapes but the same type (i.e. both vectors, or matrices or
# whatnot of same dtype)
x = tensor.vector('x')
y = tensor.vector('y')
x = tensor.vector('x', dtype=self.dtype)
y = tensor.vector('y', dtype=self.dtype)
c = tensor.iscalar('c')
f = theano.function([c, x, y], ifelse(c, x, y))
f = theano.function([c, x, y], ifelse(c, x, y), mode=self.mode)
self.assertFunctionContains1(f, self.get_ifelse(1))
rng = numpy.random.RandomState(utt.fetch_seed())
xlen = rng.randint(200)
ylen = rng.randint(200)
vx = numpy.asarray(rng.uniform(size=(xlen,)), theano.config.floatX)
vy = numpy.asarray(rng.uniform(size=(ylen,)), theano.config.floatX)
assert numpy.allclose(vx, f(1, vx, vy))
assert numpy.allclose(vy, f(0, vx, vy))
def test_lazy_if_inplace(self):
# Tests that lazy if works inplace
x = tensor.vector('x')
y = tensor.vector('y')
c = tensor.iscalar('c')
f = theano.function([c, x, y], ifelse(c, x, y))
rng = numpy.random.RandomState(utt.fetch_seed())
xlen = rng.randint(200)
ylen = rng.randint(200)
vx = numpy.asarray(rng.uniform(size=(xlen,)), self.dtype)
vy = numpy.asarray(rng.uniform(size=(ylen,)), self.dtype)
vx = numpy.asarray(rng.uniform(size=(xlen,)), theano.config.floatX)
vy = numpy.asarray(rng.uniform(size=(ylen,)), theano.config.floatX)
if theano.config.mode != "FAST_COMPILE":
assert numpy.all([x.op.as_view for x in f.maker.env.toposort() if
isinstance(x.op, IfElse)])
assert len([x.op for x in f.maker.env.toposort()
if isinstance(x.op, IfElse)]) > 0
assert numpy.allclose(vx, f(1, vx, vy))
assert numpy.allclose(vy, f(0, vx, vy))
......@@ -71,31 +63,150 @@ class test_ifelse(unittest.TestCase):
def test_grad_lazy_if(self):
# Tests that we can compute the gradients through lazy if
x = tensor.vector('x')
y = tensor.vector('y')
x = tensor.vector('x', dtype=self.dtype)
y = tensor.vector('y', dtype=self.dtype)
c = tensor.iscalar('c')
z = ifelse(c, x, y)
gx, gy = tensor.grad(z.sum(), [x, y])
f = theano.function([c, x, y], [gx, gy])
f = theano.function([c, x, y], [self.cast_output(gx),
self.cast_output(gy)],
mode=self.mode)
# There is only 2 of the 3 ifelse that are moved on the GPU.
# The one that stay on the CPU is for the shape.
self.assertFunctionContains(f, self.get_ifelse(1), min=2, max=3)
rng = numpy.random.RandomState(utt.fetch_seed())
xlen = rng.randint(200)
ylen = rng.randint(200)
vx = numpy.asarray(rng.uniform(size=(xlen,)), theano.config.floatX)
vy = numpy.asarray(rng.uniform(size=(ylen,)), theano.config.floatX)
vx = numpy.asarray(rng.uniform(size=(xlen,)), self.dtype)
vy = numpy.asarray(rng.uniform(size=(ylen,)), self.dtype)
gx0, gy0 = f(1, vx, vy)
assert numpy.allclose(gx0.shape, vx.shape)
assert numpy.allclose(gy0.shape, vy.shape)
assert numpy.all(gx0 == 1.)
assert numpy.all(gy0 == 0.)
assert numpy.all(numpy.asarray(gx0) == 1.)
assert numpy.all(numpy.asarray(gy0) == 0.)
gx0, gy0 = f(0, vx, vy)
assert numpy.allclose(gx0.shape, vx.shape)
assert numpy.allclose(gy0.shape, vy.shape)
assert numpy.all(gx0 == 0.)
assert numpy.all(gy0 == 1.)
assert numpy.all(numpy.asarray(gx0) == 0.)
assert numpy.all(numpy.asarray(gy0) == 1.)
def test_multiple_out(self):
x1 = tensor.vector('x1', dtype=self.dtype)
x2 = tensor.vector('x2', dtype=self.dtype)
y1 = tensor.vector('y1', dtype=self.dtype)
y2 = tensor.vector('y2', dtype=self.dtype)
c = tensor.iscalar('c')
z = ifelse(c, (x1, x2), (y1, y2))
f = theano.function([c, x1, x2, y1, y2], z, mode=self.mode)
self.assertFunctionContains1(f, self.get_ifelse(2))
ifnode = [x for x in f.maker.env.toposort()
if isinstance(x.op, IfElse)][0]
assert len(ifnode.outputs) == 2
rng = numpy.random.RandomState(utt.fetch_seed())
x1len = rng.randint(200)
x2len = rng.randint(200)
y1len = rng.randint(200)
y2len = rng.randint(200)
vx1 = numpy.asarray(rng.uniform(size=(x1len,)), self.dtype)
vx2 = numpy.asarray(rng.uniform(size=(x2len,)), self.dtype)
vy1 = numpy.asarray(rng.uniform(size=(y1len,)), self.dtype)
vy2 = numpy.asarray(rng.uniform(size=(y2len,)), self.dtype)
ovx1, ovx2 = f(1, vx1, vx2, vy1, vy2)
ovy1, ovy2 = f(0, vx1, vx2, vy1, vy2)
assert numpy.allclose(vx1, ovx1)
assert numpy.allclose(vy1, ovy1)
assert numpy.allclose(vx2, ovx2)
assert numpy.allclose(vy2, ovy2)
def test_multiple_out_grad(self):
# Tests that we can compute the gradients through lazy if
x1 = tensor.vector('x1')
x2 = tensor.vector('x2')
y1 = tensor.vector('y1')
y2 = tensor.vector('y2')
c = tensor.iscalar('c')
z = ifelse(c, (x1, x2), (y1, y2))
grads = tensor.grad(z[0].sum() + z[1].sum(),
[x1, x2, y1, y2])
f = theano.function([c, x1, x2, y1, y2], grads)
rng = numpy.random.RandomState(utt.fetch_seed())
lens = [rng.randint(200) for i in range(4)]
values = [numpy.asarray(rng.uniform(size=(l,)), theano.config.floatX)
for l in lens]
outs_1 = f(1, *values)
assert all([x.shape[0] == y for x, y in zip(outs_1, lens)])
assert numpy.all(outs_1[0] == 1.)
assert numpy.all(outs_1[1] == 1.)
assert numpy.all(outs_1[2] == 0.)
assert numpy.all(outs_1[3] == 0.)
outs_0 = f(0, *values)
assert all([x.shape[0] == y for x, y in zip(outs_1, lens)])
assert numpy.all(outs_0[0] == 0.)
assert numpy.all(outs_0[1] == 0.)
assert numpy.all(outs_0[2] == 1.)
assert numpy.all(outs_0[3] == 1.)
def test_dtype_mismatch(self):
rng = numpy.random.RandomState(utt.fetch_seed())
data = rng.rand(5).astype(self.dtype)
x = self.shared(data)
y = tensor.cast(x * 10, 'int8')
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_ndim_mismatch(self):
rng = numpy.random.RandomState(utt.fetch_seed())
data = rng.rand(5).astype(self.dtype)
x = self.shared(data)
y = tensor.col('y', self.dtype)
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_broadcast_mismatch(self):
rng = numpy.random.RandomState(utt.fetch_seed())
data = rng.rand(5).astype(self.dtype)
x = self.shared(data)
#print x.broadcastable
y = tensor.row('y', self.dtype)
#print y.broadcastable
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
def test_sparse_tensor_error(self):
import theano.sparse
if not theano.sparse.enable_sparse:
raise SkipTest("Optimization temporarily disabled")
rng = numpy.random.RandomState(utt.fetch_seed())
data = rng.rand(2, 3).astype(self.dtype)
x = self.shared(data)
y = theano.sparse.matrix('csc', dtype=self.dtype, name='y')
z = theano.sparse.matrix('csr', dtype=self.dtype, name='z')
cond = theano.tensor.iscalar('cond')
self.assertRaises(TypeError, ifelse, cond, x, y)
self.assertRaises(TypeError, ifelse, cond, y, x)
self.assertRaises(TypeError, ifelse, cond, x, z)
self.assertRaises(TypeError, ifelse, cond, z, x)
self.assertRaises(TypeError, ifelse, cond, y, z)
self.assertRaises(TypeError, ifelse, cond, z, y)
def test_merge(self):
raise SkipTest("Optimization temporarily disabled")
......
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