Skip to content

P
pytensor
提交 1f5087d2 authored 作者: amrithasuresh's avatar amrithasuresh
浏览文件
操作

Updated numpy as np

上级 f2eca59f
隐藏空白字符变更
内嵌 并排
正在显示 包含 353 行增加 和 353 行删除
theano/scan_module/tests/test_scan.py
浏览文件 @ 1f5087d2
...@@ -11,11 +11,11 @@ from collections import OrderedDict ...@@ -11,11 +11,11 @@ from collections import OrderedDict
import six.moves.cPickle as pickle import six.moves.cPickle as pickle
from six.moves import xrange from six.moves import xrange
import numpy import numpy as np
from nose.plugins.skip import SkipTest from nose.plugins.skip import SkipTest
from nose.tools import assert_raises from nose.tools import assert_raises
from nose.tools import raises from nose.tools import raises
from numpy.testing import dec from np.testing import dec
import theano import theano
import theano.sandbox.rng_mrg import theano.sandbox.rng_mrg
...@@ -89,7 +89,7 @@ class multiple_outputs_numeric_grad: ...@@ -89,7 +89,7 @@ class multiple_outputs_numeric_grad:
for i, p in enumerate(pt): for i, p in enumerate(pt):
if ndarray_mask[i]: if ndarray_mask[i]:
pt[i] = numpy.array(p) pt[i] = np.array(p)
_eps = type_eps[str(pt[i].dtype)] _eps = type_eps[str(pt[i].dtype)]
if _eps > dtype_eps: if _eps > dtype_eps:
dtype_eps = _eps dtype_eps = _eps
...@@ -116,12 +116,12 @@ class multiple_outputs_numeric_grad: ...@@ -116,12 +116,12 @@ class multiple_outputs_numeric_grad:
t[pos] += _eps t[pos] += _eps
t = t.reshape(pt[i].shape) t = t.reshape(pt[i].shape)
f_eps = f(*(pt[:i] + [t] + pt[i + 1:])) f_eps = f(*(pt[:i] + [t] + pt[i + 1:]))
_g.append(numpy.asarray((f_eps - f_x) / _eps)) _g.append(np.asarray((f_eps - f_x) / _eps))
gx.append(numpy.asarray(_g).reshape(pt[i].shape)) gx.append(np.asarray(_g).reshape(pt[i].shape))
else: else:
t = numpy.array(pt[i] + _eps) t = np.array(pt[i] + _eps)
f_eps = f(*(pt[:i] + [t] + pt[i + 1:])) f_eps = f(*(pt[:i] + [t] + pt[i + 1:]))
gx.append(numpy.asarray((f_eps - f_x) / _eps)) gx.append(np.asarray((f_eps - f_x) / _eps))
self.gx = gx self.gx = gx
@staticmethod @staticmethod
...@@ -137,8 +137,8 @@ class multiple_outputs_numeric_grad: ...@@ -137,8 +137,8 @@ class multiple_outputs_numeric_grad:
for i in xrange(len(_g_pt)): for i in xrange(len(_g_pt)):
if self.ndarray_mask[i]: if self.ndarray_mask[i]:
g_pt.append(_g_pt[i]) g_pt.append(_g_pt[i])
elif isinstance(_g_pt[i], numpy.ndarray): elif isinstance(_g_pt[i], np.ndarray):
assert numpy.all(_g_pt[i] == 0) assert np.all(_g_pt[i] == 0)
if len(g_pt) != len(self.gx): if len(g_pt) != len(self.gx):
raise ValueError('argument has wrong number of elements', raise ValueError('argument has wrong number of elements',
len(g_pt)) len(g_pt))
...@@ -149,12 +149,12 @@ class multiple_outputs_numeric_grad: ...@@ -149,12 +149,12 @@ class multiple_outputs_numeric_grad:
raise ValueError('argument element %i has wrong shape %s' % raise ValueError('argument element %i has wrong shape %s' %
(i, str((a.shape, b.shape)))) (i, str((a.shape, b.shape))))
vv = multiple_outputs_numeric_grad.abs_rel_err(a, b) vv = multiple_outputs_numeric_grad.abs_rel_err(a, b)
errs.append(numpy.max( errs.append(np.max(
multiple_outputs_numeric_grad.abs_rel_err(a, b))) multiple_outputs_numeric_grad.abs_rel_err(a, b)))
if numpy.all(numpy.isfinite(errs)): if np.all(np.isfinite(errs)):
return numpy.max(errs), numpy.argmax(errs) return np.max(errs), np.argmax(errs)
else: else:
return numpy.inf, 0 return np.inf, 0
# TODO: Test this function, and if it works, # TODO: Test this function, and if it works,
...@@ -262,11 +262,11 @@ class T_Scan(unittest.TestCase): ...@@ -262,11 +262,11 @@ class T_Scan(unittest.TestCase):
if tmpdir is not None: if tmpdir is not None:
shutil.rmtree(tmpdir) shutil.rmtree(tmpdir)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
state = rng.uniform() state = rng.uniform()
steps = 5 steps = 5
numpy_values = numpy.array([state * (2 ** (k + 1)) for k numpy_values = np.array([state * (2 ** (k + 1)) for k
in xrange(steps)]) in xrange(steps)])
theano_values = my_f(state, steps) theano_values = my_f(state, steps)
utt.assert_allclose(numpy_values, theano_values) utt.assert_allclose(numpy_values, theano_values)
...@@ -300,7 +300,7 @@ class T_Scan(unittest.TestCase): ...@@ -300,7 +300,7 @@ class T_Scan(unittest.TestCase):
assert all(i.value is None for i in scan_node.op.fn.input_storage) assert all(i.value is None for i in scan_node.op.fn.input_storage)
assert all(o.value is None for o in scan_node.op.fn.output_storage) assert all(o.value is None for o in scan_node.op.fn.output_storage)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
state = rng.uniform() state = rng.uniform()
steps = 5 steps = 5
...@@ -332,11 +332,11 @@ class T_Scan(unittest.TestCase): ...@@ -332,11 +332,11 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
state = rng.uniform() state = rng.uniform()
steps = 5 steps = 5
numpy_values = numpy.array([state * (2 ** (k + 1)) for k numpy_values = np.array([state * (2 ** (k + 1)) for k
in xrange(steps)]) in xrange(steps)])
theano_values = my_f(state, steps) theano_values = my_f(state, steps)
utt.assert_allclose(numpy_values, theano_values[0]) utt.assert_allclose(numpy_values, theano_values[0])
...@@ -370,10 +370,10 @@ class T_Scan(unittest.TestCase): ...@@ -370,10 +370,10 @@ class T_Scan(unittest.TestCase):
# This assertation fails if savemem optimization failed on scan # This assertation fails if savemem optimization failed on scan
if theano.config.mode != "FAST_COMPILE": if theano.config.mode != "FAST_COMPILE":
assert nodes[0].op._scan_savemem_visited assert nodes[0].op._scan_savemem_visited
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
my_f(rng.uniform(size=(3,)), my_f(rng.uniform(size=(3,)),
4, 4,
numpy.int64([2, 2, 3])) np.int64([2, 2, 3]))
@attr('slow') @attr('slow')
def test_only_nonseq_inputs(self): def test_only_nonseq_inputs(self):
...@@ -388,9 +388,9 @@ class T_Scan(unittest.TestCase): ...@@ -388,9 +388,9 @@ class T_Scan(unittest.TestCase):
fun = theano.function([inp], [broadcasted_inp, gr]) fun = theano.function([inp], [broadcasted_inp, gr])
# Execute the Theano function and compare outputs to the expected outputs # Execute the Theano function and compare outputs to the expected outputs
inputs = numpy.array([[1, 2], [3, 4]], dtype=theano.config.floatX) inputs = np.array([[1, 2], [3, 4]], dtype=theano.config.floatX)
expected_out1 = numpy.repeat(inputs[None], n_steps, axis=0) expected_out1 = np.repeat(inputs[None], n_steps, axis=0)
expected_out2 = numpy.ones(inputs.shape, dtype="int8") * n_steps expected_out2 = np.ones(inputs.shape, dtype="int8") * n_steps
out1, out2 = fun(inputs) out1, out2 = fun(inputs)
utt.assert_allclose(out1, expected_out1) utt.assert_allclose(out1, expected_out1)
...@@ -420,14 +420,14 @@ class T_Scan(unittest.TestCase): ...@@ -420,14 +420,14 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
W = rng.uniform() W = rng.uniform()
W_in = rng.uniform() W_in = rng.uniform()
# compute the output in numpy # compute the output in numpy
v_out = numpy.zeros((4,)) v_out = np.zeros((4,))
v_out[0] = v_u[0] * W_in + v_x0 * W v_out[0] = v_u[0] * W_in + v_x0 * W
for step in xrange(1, 4): for step in xrange(1, 4):
v_out[step] = v_u[step] * W_in + v_out[step - 1] * W v_out[step] = v_u[step] * W_in + v_out[step - 1] * W
...@@ -437,7 +437,7 @@ class T_Scan(unittest.TestCase): ...@@ -437,7 +437,7 @@ class T_Scan(unittest.TestCase):
# simple rnn, one input, one state, weights for each; input/state # simple rnn, one input, one state, weights for each; input/state
# are vectors, weights are scalars; using shared variables # are vectors, weights are scalars; using shared variables
def test_one_sequence_one_output_weights_shared(self): def test_one_sequence_one_output_weights_shared(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
u = theano.tensor.vector('u') u = theano.tensor.vector('u')
x0 = theano.tensor.scalar('x0') x0 = theano.tensor.scalar('x0')
W_in = theano.shared(asarrayX(rng.uniform()), name='w_in') W_in = theano.shared(asarrayX(rng.uniform()), name='w_in')
...@@ -462,19 +462,19 @@ class T_Scan(unittest.TestCase): ...@@ -462,19 +462,19 @@ class T_Scan(unittest.TestCase):
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
# compute the output i numpy # compute the output i numpy
v_out = numpy.zeros((4,)) v_out = np.zeros((4,))
v_out[0] = v_u[0] * W_in.get_value() + v_x0 * W.get_value() v_out[0] = v_u[0] * W_in.get_value() + v_x0 * W.get_value()
for step in xrange(1, 4): for step in xrange(1, 4):
v_out[step] = (v_u[step] * W_in.get_value() + v_out[step] = (v_u[step] * W_in.get_value() +
v_out[step - 1] * W.get_value()) v_out[step - 1] * W.get_value())
theano_values = f3(v_u, v_x0) theano_values = f3(v_u, v_x0)
assert numpy.allclose(theano_values, v_out) assert np.allclose(theano_values, v_out)
# some rnn with multiple outputs and multiple inputs; other # some rnn with multiple outputs and multiple inputs; other
# dimension instead of scalars/vectors # dimension instead of scalars/vectors
def test_multiple_inputs_multiple_outputs(self): def test_multiple_inputs_multiple_outputs(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.)) vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.))
vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
...@@ -511,15 +511,15 @@ class T_Scan(unittest.TestCase): ...@@ -511,15 +511,15 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# compute the values in numpy # compute the values in numpy
v_x = numpy.zeros((3, 2), dtype=theano.config.floatX) v_x = np.zeros((3, 2), dtype=theano.config.floatX)
v_y = numpy.zeros((3,), dtype=theano.config.floatX) v_y = np.zeros((3,), dtype=theano.config.floatX)
v_x[0] = (numpy.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + v_x[0] = (np.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 +
numpy.dot(v_x0, vW)) np.dot(v_x0, vW))
v_y[0] = numpy.dot(v_x0, vWout) v_y[0] = np.dot(v_x0, vWout)
for i in xrange(1, 3): for i in xrange(1, 3):
v_x[i] = (numpy.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + v_x[i] = (np.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 +
numpy.dot(v_x[i - 1], vW)) np.dot(v_x[i - 1], vW))
v_y[i] = numpy.dot(v_x[i - 1], vWout) v_y[i] = np.dot(v_x[i - 1], vWout)
(theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1) (theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1)
utt.assert_allclose(theano_x, v_x) utt.assert_allclose(theano_x, v_x)
...@@ -527,7 +527,7 @@ class T_Scan(unittest.TestCase): ...@@ -527,7 +527,7 @@ class T_Scan(unittest.TestCase):
def test_multiple_outs_taps(self): def test_multiple_outs_taps(self):
l = 5 l = 5
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2)) vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2))
vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
...@@ -579,40 +579,40 @@ class T_Scan(unittest.TestCase): ...@@ -579,40 +579,40 @@ class T_Scan(unittest.TestCase):
v_y0, v_y0,
vW_in1) vW_in1)
ny0 = numpy.zeros((5, 2)) ny0 = np.zeros((5, 2))
ny1 = numpy.zeros((5,)) ny1 = np.zeros((5,))
ny2 = numpy.zeros((5, 2)) ny2 = np.zeros((5, 2))
ny0[0] = numpy.dot(v_u1[0], vW_in1) + \ ny0[0] = np.dot(v_u1[0], vW_in1) + \
(v_u2[1] + v_u2[0] * v_u2[2]) * vW_in2 + numpy.dot(v_x0, vW) (v_u2[1] + v_u2[0] * v_u2[2]) * vW_in2 + np.dot(v_x0, vW)
ny1[0] = (v_y0[2] + v_y0[0]) * numpy.dot(v_x0, vWout) ny1[0] = (v_y0[2] + v_y0[0]) * np.dot(v_x0, vWout)
ny2[0] = numpy.dot(v_u1[0], vW_in1) ny2[0] = np.dot(v_u1[0], vW_in1)
ny0[1] = numpy.dot(v_u1[1], vW_in1) + \ ny0[1] = np.dot(v_u1[1], vW_in1) + \
(v_u2[2] + v_u2[1] * v_u2[3]) * vW_in2 + numpy.dot(ny0[0], vW) (v_u2[2] + v_u2[1] * v_u2[3]) * vW_in2 + np.dot(ny0[0], vW)
ny1[1] = (ny1[0] + v_y0[1]) * numpy.dot(ny0[0], vWout) ny1[1] = (ny1[0] + v_y0[1]) * np.dot(ny0[0], vWout)
ny2[1] = numpy.dot(v_u1[1], vW_in1) ny2[1] = np.dot(v_u1[1], vW_in1)
ny0[2] = numpy.dot(v_u1[2], vW_in1) + \ ny0[2] = np.dot(v_u1[2], vW_in1) + \
(v_u2[3] + v_u2[2] * v_u2[4]) * vW_in2 + \ (v_u2[3] + v_u2[2] * v_u2[4]) * vW_in2 + \
numpy.dot(ny0[1], vW) np.dot(ny0[1], vW)
ny1[2] = (ny1[1] + v_y0[2]) * numpy.dot(ny0[1], vWout) ny1[2] = (ny1[1] + v_y0[2]) * np.dot(ny0[1], vWout)
ny2[2] = numpy.dot(v_u1[2], vW_in1) ny2[2] = np.dot(v_u1[2], vW_in1)
ny0[3] = numpy.dot(v_u1[3], vW_in1) + \ ny0[3] = np.dot(v_u1[3], vW_in1) + \
(v_u2[4] + v_u2[3] * v_u2[5]) * vW_in2 + \ (v_u2[4] + v_u2[3] * v_u2[5]) * vW_in2 + \
numpy.dot(ny0[2], vW) np.dot(ny0[2], vW)
ny1[3] = (ny1[2] + ny1[0]) * numpy.dot(ny0[2], vWout) ny1[3] = (ny1[2] + ny1[0]) * np.dot(ny0[2], vWout)
ny2[3] = numpy.dot(v_u1[3], vW_in1) ny2[3] = np.dot(v_u1[3], vW_in1)
ny0[4] = numpy.dot(v_u1[4], vW_in1) + \ ny0[4] = np.dot(v_u1[4], vW_in1) + \
(v_u2[5] + v_u2[4] * v_u2[6]) * vW_in2 + \ (v_u2[5] + v_u2[4] * v_u2[6]) * vW_in2 + \
numpy.dot(ny0[3], vW) np.dot(ny0[3], vW)
ny1[4] = (ny1[3] + ny1[1]) * numpy.dot(ny0[3], vWout) ny1[4] = (ny1[3] + ny1[1]) * np.dot(ny0[3], vWout)
ny2[4] = numpy.dot(v_u1[4], vW_in1) ny2[4] = np.dot(v_u1[4], vW_in1)
def test_using_taps_sequence(self): def test_using_taps_sequence(self):
# this test refers to a bug reported by Nicolas # this test refers to a bug reported by Nicolas
...@@ -621,9 +621,9 @@ class T_Scan(unittest.TestCase): ...@@ -621,9 +621,9 @@ class T_Scan(unittest.TestCase):
y, updates = theano.scan(lambda x: [x], y, updates = theano.scan(lambda x: [x],
sequences=dict(input=x, taps=[-1]), sequences=dict(input=x, taps=[-1]),
outputs_info=[None]) outputs_info=[None])
inp = numpy.arange(5).astype('float64') inp = np.arange(5).astype('float64')
rval = theano.function([x], y, updates=updates)(inp) rval = theano.function([x], y, updates=updates)(inp)
assert numpy.all(rval == inp[:-1]) assert np.all(rval == inp[:-1])
def test_using_negative_taps_sequence(self): def test_using_negative_taps_sequence(self):
# This test refers to a bug reported on github on May 22 2015 by # This test refers to a bug reported on github on May 22 2015 by
...@@ -636,7 +636,7 @@ class T_Scan(unittest.TestCase): ...@@ -636,7 +636,7 @@ class T_Scan(unittest.TestCase):
f = theano.function([x], res, updates = upd) f = theano.function([x], res, updates = upd)
output = f([1, 2, 3, 4, 5]) output = f([1, 2, 3, 4, 5])
expected_output = numpy.array([1, 2, 3], dtype="float32") expected_output = np.array([1, 2, 3], dtype="float32")
utt.assert_allclose(output, expected_output) utt.assert_allclose(output, expected_output)
def test_connection_pattern(self): def test_connection_pattern(self):
...@@ -649,8 +649,8 @@ class T_Scan(unittest.TestCase): ...@@ -649,8 +649,8 @@ class T_Scan(unittest.TestCase):
def fn(a_m2, a_m1, b_m2, b_m1): def fn(a_m2, a_m1, b_m2, b_m1):
return a_m1, b_m1 return a_m1, b_m1
a0 = theano.shared(numpy.arange(2)) a0 = theano.shared(np.arange(2))
b0 = theano.shared(numpy.arange(2)) b0 = theano.shared(np.arange(2))
(a, b), _ = theano.scan(fn, (a, b), _ = theano.scan(fn,
outputs_info=[{'initial': a0, 'taps': [-2, -1]}, outputs_info=[{'initial': a0, 'taps': [-2, -1]},
...@@ -741,7 +741,7 @@ class T_Scan(unittest.TestCase): ...@@ -741,7 +741,7 @@ class T_Scan(unittest.TestCase):
# Call verify_grad to ensure the correctness of the second gradients # Call verify_grad to ensure the correctness of the second gradients
floatX = theano.config.floatX floatX = theano.config.floatX
inputs_test_values = [numpy.random.random((3)).astype(floatX)] inputs_test_values = [np.random.random((3)).astype(floatX)]
theano.tests.unittest_tools.verify_grad(get_sum_of_grad, theano.tests.unittest_tools.verify_grad(get_sum_of_grad,
inputs_test_values) inputs_test_values)
...@@ -768,8 +768,8 @@ class T_Scan(unittest.TestCase): ...@@ -768,8 +768,8 @@ class T_Scan(unittest.TestCase):
# Call verify_grad to ensure the correctness of the second gradients # Call verify_grad to ensure the correctness of the second gradients
floatX = theano.config.floatX floatX = theano.config.floatX
inputs_test_values = [numpy.random.random((2, 3)).astype(floatX), inputs_test_values = [np.random.random((2, 3)).astype(floatX),
numpy.random.random((3)).astype(floatX)] np.random.random((3)).astype(floatX)]
theano.tests.unittest_tools.verify_grad(get_sum_of_grad, theano.tests.unittest_tools.verify_grad(get_sum_of_grad,
inputs_test_values) inputs_test_values)
...@@ -781,7 +781,7 @@ class T_Scan(unittest.TestCase): ...@@ -781,7 +781,7 @@ class T_Scan(unittest.TestCase):
# forward pass # forward pass
W = theano.shared( W = theano.shared(
numpy.random.randn(2, 2).astype('float32'), np.random.randn(2, 2).astype('float32'),
name="W", borrow=True) name="W", borrow=True)
def forward_scanner(x_t): def forward_scanner(x_t):
...@@ -807,7 +807,7 @@ class T_Scan(unittest.TestCase): ...@@ -807,7 +807,7 @@ class T_Scan(unittest.TestCase):
# vectors, weights are scalars; using shared variables and past # vectors, weights are scalars; using shared variables and past
# taps (sequences and outputs) # taps (sequences and outputs)
def test_using_taps_input_output(self): def test_using_taps_input_output(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW = asarrayX(rng.uniform()) vW = asarrayX(rng.uniform())
vW_in = asarrayX(rng.uniform()) vW_in = asarrayX(rng.uniform())
vu = asarrayX(rng.uniform(size=(4,), low=-5., high=5.)) vu = asarrayX(rng.uniform(size=(4,), low=-5., high=5.))
...@@ -843,7 +843,7 @@ class T_Scan(unittest.TestCase): ...@@ -843,7 +843,7 @@ class T_Scan(unittest.TestCase):
# in scan) which might seem strange, but then again why not use # in scan) which might seem strange, but then again why not use
# v_0[t] instead of v_0[t-2] in a real application ?? # v_0[t] instead of v_0[t-2] in a real application ??
# also vx0[0] corresponds to vx0[-2], vx0[1] to vx0[-1] # also vx0[0] corresponds to vx0[-2], vx0[1] to vx0[-1]
numpy_out = numpy.zeros((2,)) numpy_out = np.zeros((2,))
numpy_out[0] = vu[0] * vW_in + vx0[1] * vW + vx0[0] numpy_out[0] = vu[0] * vW_in + vx0[1] * vW + vx0[0]
numpy_out[1] = vu[1] * vW_in + numpy_out[0] * vW + vx0[1] numpy_out[1] = vu[1] * vW_in + numpy_out[0] * vW + vx0[1]
utt.assert_allclose(numpy_out, theano_out) utt.assert_allclose(numpy_out, theano_out)
...@@ -852,7 +852,7 @@ class T_Scan(unittest.TestCase): ...@@ -852,7 +852,7 @@ class T_Scan(unittest.TestCase):
# vectors, weights are scalars; using shared variables and past # vectors, weights are scalars; using shared variables and past
# taps (sequences and outputs) and future taps for sequences # taps (sequences and outputs) and future taps for sequences
def test_past_future_taps_shared(self): def test_past_future_taps_shared(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW = asarrayX(rng.uniform()) vW = asarrayX(rng.uniform())
vW_in = asarrayX(rng.uniform()) vW_in = asarrayX(rng.uniform())
vu = asarrayX(rng.uniform(size=(6,), low=-5., high=5.)) vu = asarrayX(rng.uniform(size=(6,), low=-5., high=5.))
...@@ -880,7 +880,7 @@ class T_Scan(unittest.TestCase): ...@@ -880,7 +880,7 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
theano_out = f8(vu, vx0) theano_out = f8(vu, vx0)
# compute output in numpy # compute output in numpy
numpy_out = numpy.zeros(2) numpy_out = np.zeros(2)
# think of vu[0] as vu[-2], vu[4] as vu[2] # think of vu[0] as vu[-2], vu[4] as vu[2]
# and vx0[0] as vx0[-2], vx0[1] as vx0[-1] # and vx0[0] as vx0[-2], vx0[1] as vx0[-1]
numpy_out[0] = (vu[0] + vu[4]) * vW_in + vx0[1] * vW + vx0[0] numpy_out[0] = (vu[0] + vu[4]) * vW_in + vx0[1] * vW + vx0[0]
...@@ -889,9 +889,9 @@ class T_Scan(unittest.TestCase): ...@@ -889,9 +889,9 @@ class T_Scan(unittest.TestCase):
# simple rnn ; compute inplace version 1 # simple rnn ; compute inplace version 1
def test_inplace1(self): def test_inplace1(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW = asarrayX(numpy.random.uniform()) vW = asarrayX(np.random.uniform())
vW_in = asarrayX(numpy.random.uniform()) vW_in = asarrayX(np.random.uniform())
vu0 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.)) vu0 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.))
vu1 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.)) vu1 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.))
vu2 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.)) vu2 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.))
...@@ -934,8 +934,8 @@ class T_Scan(unittest.TestCase): ...@@ -934,8 +934,8 @@ class T_Scan(unittest.TestCase):
assert 0 in scan_node[0].op.destroy_map.keys() assert 0 in scan_node[0].op.destroy_map.keys()
assert 1 in scan_node[0].op.destroy_map.keys() assert 1 in scan_node[0].op.destroy_map.keys()
# compute output in numpy # compute output in numpy
numpy_x0 = numpy.zeros((3,)) numpy_x0 = np.zeros((3,))
numpy_x1 = numpy.zeros((3,)) numpy_x1 = np.zeros((3,))
numpy_x0[0] = vu0[0] * vW_in + vx0 * vW + vu1[0] * vu2[0] numpy_x0[0] = vu0[0] * vW_in + vx0 * vW + vu1[0] * vu2[0]
numpy_x1[0] = vu0[0] * vW_in + vx1 * vW + vu1[0] + vu2[0] numpy_x1[0] = vu0[0] * vW_in + vx1 * vW + vu1[0] + vu2[0]
for i in xrange(1, 3): for i in xrange(1, 3):
...@@ -953,9 +953,9 @@ class T_Scan(unittest.TestCase): ...@@ -953,9 +953,9 @@ class T_Scan(unittest.TestCase):
# simple rnn ; compute inplace version 2 # simple rnn ; compute inplace version 2
def test_inplace2(self): def test_inplace2(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW = asarrayX(numpy.random.uniform()) vW = asarrayX(np.random.uniform())
vW_in = asarrayX(numpy.random.uniform()) vW_in = asarrayX(np.random.uniform())
vu0 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.)) vu0 = asarrayX(rng.uniform(size=(3,), low=-5., high=5.))
vu1 = asarrayX(rng.uniform(size=(4,), low=-5., high=5.)) vu1 = asarrayX(rng.uniform(size=(4,), low=-5., high=5.))
vu2 = asarrayX(rng.uniform(size=(5,), low=-5., high=5.)) vu2 = asarrayX(rng.uniform(size=(5,), low=-5., high=5.))
...@@ -1006,8 +1006,8 @@ class T_Scan(unittest.TestCase): ...@@ -1006,8 +1006,8 @@ class T_Scan(unittest.TestCase):
assert 0 in scan_node[0].op.destroy_map.keys() assert 0 in scan_node[0].op.destroy_map.keys()
assert 1 in scan_node[0].op.destroy_map.keys() assert 1 in scan_node[0].op.destroy_map.keys()
# compute output in numpy # compute output in numpy
numpy_x0 = numpy.zeros((3,)) numpy_x0 = np.zeros((3,))
numpy_x1 = numpy.zeros((3,)) numpy_x1 = np.zeros((3,))
numpy_x0[0] = vu0[0] * vW_in + vx0 * vW + vu1[0] * vu1[1] numpy_x0[0] = vu0[0] * vW_in + vx0 * vW + vu1[0] * vu1[1]
numpy_x1[0] = vu0[0] * vW_in + vx1 * vW + vu2[0] + vu2[1] + vu2[2] numpy_x1[0] = vu0[0] * vW_in + vx1 * vW + vu2[0] + vu2[1] + vu2[2]
for i in xrange(1, 3): for i in xrange(1, 3):
...@@ -1024,7 +1024,7 @@ class T_Scan(unittest.TestCase): ...@@ -1024,7 +1024,7 @@ class T_Scan(unittest.TestCase):
utt.assert_allclose(theano_x1, numpy_x1) utt.assert_allclose(theano_x1, numpy_x1)
def test_inplace3(self): def test_inplace3(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vx0 = asarrayX(rng.uniform()) vx0 = asarrayX(rng.uniform())
vx1 = asarrayX(rng.uniform()) vx1 = asarrayX(rng.uniform())
...@@ -1035,7 +1035,7 @@ class T_Scan(unittest.TestCase): ...@@ -1035,7 +1035,7 @@ class T_Scan(unittest.TestCase):
[], [],
[x0, x1], [x0, x1],
n_steps=3) n_steps=3)
x0 = asarrayX(numpy.zeros((3,))) x0 = asarrayX(np.zeros((3,)))
x0[0] = vx0 x0[0] = vx0
x0 = theano.tensor.constant(x0) x0 = theano.tensor.constant(x0)
to_replace = outputs[0].owner.inputs[0].owner.inputs[1] to_replace = outputs[0].owner.inputs[0].owner.inputs[1]
...@@ -1053,7 +1053,7 @@ class T_Scan(unittest.TestCase): ...@@ -1053,7 +1053,7 @@ class T_Scan(unittest.TestCase):
# Shared variable with updates # Shared variable with updates
def test_shared_arguments_with_updates(self): def test_shared_arguments_with_updates(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW1 = asarrayX(rng.rand(2, 3)) vW1 = asarrayX(rng.rand(2, 3))
vW2 = asarrayX(rng.rand(3, 2)) vW2 = asarrayX(rng.rand(3, 2))
...@@ -1128,22 +1128,22 @@ class T_Scan(unittest.TestCase): ...@@ -1128,22 +1128,22 @@ class T_Scan(unittest.TestCase):
theano_y0, theano_y1, theano_y2 = allstuff theano_y0, theano_y1, theano_y2 = allstuff
# do things in numpy # do things in numpy
numpy_y0 = numpy.zeros((6, 2)) numpy_y0 = np.zeros((6, 2))
numpy_y1 = numpy.zeros((4, 2)) numpy_y1 = np.zeros((4, 2))
numpy_y2 = numpy.zeros((3, 3)) numpy_y2 = np.zeros((3, 3))
numpy_y0[:3] = vy0 numpy_y0[:3] = vy0
numpy_y1[0] = vy1 numpy_y1[0] = vy1
numpy_W1 = vW1.copy() numpy_W1 = vW1.copy()
numpy_W2 = vW2.copy() numpy_W2 = vW2.copy()
for idx in xrange(3): for idx in xrange(3):
numpy_y0[idx + 3] = numpy.dot(numpy.dot(vu1[idx, :], numpy_W1), numpy_y0[idx + 3] = np.dot(np.dot(vu1[idx, :], numpy_W1),
numpy_W2) + \ numpy_W2) + \
0.1 * numpy_y0[idx + 2] + \ 0.1 * numpy_y0[idx + 2] + \
0.33 * numpy_y0[idx + 1] + \ 0.33 * numpy_y0[idx + 1] + \
0.17 * numpy_y0[idx] 0.17 * numpy_y0[idx]
numpy_y1[idx + 1] = (numpy.dot(vu2[idx, :], numpy_W2) + numpy_y1[idx + 1] = (np.dot(vu2[idx, :], numpy_W2) +
numpy_y1[idx]) numpy_y1[idx])
numpy_y2[idx] = numpy.dot(vu1[idx, :], numpy_W1) numpy_y2[idx] = np.dot(vu1[idx, :], numpy_W1)
numpy_W1 = numpy_W1 + .1 numpy_W1 = numpy_W1 + .1
numpy_W2 = numpy_W2 + .05 numpy_W2 = numpy_W2 + .05
...@@ -1174,7 +1174,7 @@ class T_Scan(unittest.TestCase): ...@@ -1174,7 +1174,7 @@ class T_Scan(unittest.TestCase):
f = theano.function([c, x, y], [gX, gY], f = theano.function([c, x, y], [gX, gY],
allow_input_downcast=True) allow_input_downcast=True)
# Check for runtime errors # Check for runtime errors
f(numpy.int32(0), numpy.float32(1.), numpy.float32(.5)) f(np.int32(0), np.float32(1.), np.float32(.5))
def test_simple_shared_mrg_random(self): def test_simple_shared_mrg_random(self):
theano_rng = theano.sandbox.rng_mrg.MRG_RandomStreams(utt.fetch_seed()) theano_rng = theano.sandbox.rng_mrg.MRG_RandomStreams(utt.fetch_seed())
...@@ -1211,10 +1211,10 @@ class T_Scan(unittest.TestCase): ...@@ -1211,10 +1211,10 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
rng_seed = numpy.random.RandomState(utt.fetch_seed()).randint(2 ** 30) rng_seed = np.random.RandomState(utt.fetch_seed()).randint(2 ** 30)
rng = numpy.random.RandomState(int(rng_seed)) # int() is for 32bit rng = np.random.RandomState(int(rng_seed)) # int() is for 32bit
numpy_v = numpy.zeros((10, 2)) numpy_v = np.zeros((10, 2))
for i in xrange(10): for i in xrange(10):
numpy_v[i] = rng.uniform(-1, 1, size=(2,)) numpy_v[i] = rng.uniform(-1, 1, size=(2,))
...@@ -1224,12 +1224,12 @@ class T_Scan(unittest.TestCase): ...@@ -1224,12 +1224,12 @@ class T_Scan(unittest.TestCase):
utt.assert_allclose(theano_v, numpy_v[5:, :]) utt.assert_allclose(theano_v, numpy_v[5:, :])
def test_gibbs_chain(self): def test_gibbs_chain(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_W = numpy.array(rng.rand(20, 30) - .5, dtype='float32') v_W = np.array(rng.rand(20, 30) - .5, dtype='float32')
v_vsample = numpy.array(rng.binomial(1, .5, size=(3, 20),), v_vsample = np.array(rng.binomial(1, .5, size=(3, 20),),
dtype='float32') dtype='float32')
v_bvis = numpy.array(rng.rand(20) - .5, dtype='float32') v_bvis = np.array(rng.rand(20) - .5, dtype='float32')
v_bhid = numpy.array(rng.rand(30) - .5, dtype='float32') v_bhid = np.array(rng.rand(30) - .5, dtype='float32')
W = theano.shared(v_W, 'vW') W = theano.shared(v_W, 'vW')
bhid = theano.shared(v_bhid, 'vbhid') bhid = theano.shared(v_bhid, 'vbhid')
bvis = theano.shared(v_bvis, 'vbvis') bvis = theano.shared(v_bvis, 'vbvis')
...@@ -1261,24 +1261,24 @@ class T_Scan(unittest.TestCase): ...@@ -1261,24 +1261,24 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
_rng = numpy.random.RandomState(utt.fetch_seed()) _rng = np.random.RandomState(utt.fetch_seed())
rng_seed = _rng.randint(2 ** 30) rng_seed = _rng.randint(2 ** 30)
nrng1 = numpy.random.RandomState(int(rng_seed)) # int() is for 32bit nrng1 = np.random.RandomState(int(rng_seed)) # int() is for 32bit
rng_seed = _rng.randint(2 ** 30) rng_seed = _rng.randint(2 ** 30)
nrng2 = numpy.random.RandomState(int(rng_seed)) # int() is for 32bit nrng2 = np.random.RandomState(int(rng_seed)) # int() is for 32bit
def numpy_implementation(vsample): def numpy_implementation(vsample):
for idx in range(10): for idx in range(10):
hmean = 1. / (1. + numpy.exp(-(numpy.dot(vsample, v_W) +\ hmean = 1. / (1. + np.exp(-(np.dot(vsample, v_W) +\
v_bhid))) v_bhid)))
hsample = numpy.array(nrng1.binomial(1, hsample = np.array(nrng1.binomial(1,
hmean, hmean,
size=hmean.shape), size=hmean.shape),
dtype='float32') dtype='float32')
vmean = 1. / (1. + numpy.exp(-(numpy.dot(hsample, v_W.T) +\ vmean = 1. / (1. + np.exp(-(np.dot(hsample, v_W.T) +\
v_bvis))) v_bvis)))
vsample = numpy.array(nrng2.binomial(1, vsample = np.array(nrng2.binomial(1,
vmean, vmean,
size=vmean.shape), size=vmean.shape),
dtype='float32') dtype='float32')
...@@ -1290,7 +1290,7 @@ class T_Scan(unittest.TestCase): ...@@ -1290,7 +1290,7 @@ class T_Scan(unittest.TestCase):
utt.assert_allclose(t_result, n_result) utt.assert_allclose(t_result, n_result)
def test_only_shared_no_input_no_output(self): def test_only_shared_no_input_no_output(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_state = asarrayX(rng.uniform()) v_state = asarrayX(rng.uniform())
state = theano.shared(v_state, 'vstate') state = theano.shared(v_state, 'vstate')
...@@ -1331,7 +1331,7 @@ class T_Scan(unittest.TestCase): ...@@ -1331,7 +1331,7 @@ class T_Scan(unittest.TestCase):
outputs, outputs,
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(5,), low=-5., high=5.) v_u = rng.uniform(size=(5,), low=-5., high=5.)
numpy_result = v_u + 3 numpy_result = v_u + 3
...@@ -1352,7 +1352,7 @@ class T_Scan(unittest.TestCase): ...@@ -1352,7 +1352,7 @@ class T_Scan(unittest.TestCase):
updates=abs_updates, updates=abs_updates,
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vals = rng.uniform(size=(10,), low=-5., high=5.) vals = rng.uniform(size=(10,), low=-5., high=5.)
abs_vals = abs(vals) abs_vals = abs(vals)
theano_vals = f(vals) theano_vals = f(vals)
...@@ -1380,14 +1380,14 @@ class T_Scan(unittest.TestCase): ...@@ -1380,14 +1380,14 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
W = rng.uniform() W = rng.uniform()
W_in = rng.uniform() W_in = rng.uniform()
# compute the output in numpy # compute the output in numpy
v_out = numpy.zeros((4,)) v_out = np.zeros((4,))
v_out[0] = v_u[3] * W_in + v_x0 * W v_out[0] = v_u[3] * W_in + v_x0 * W
for step in xrange(1, 4): for step in xrange(1, 4):
v_out[step] = v_u[3 - step] * W_in + v_out[step - 1] * W v_out[step] = v_u[3 - step] * W_in + v_out[step - 1] * W
...@@ -1404,9 +1404,9 @@ class T_Scan(unittest.TestCase): ...@@ -1404,9 +1404,9 @@ class T_Scan(unittest.TestCase):
result, result,
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_v = rng.uniform(size=(5,), low=-5., high=5.) v_v = rng.uniform(size=(5,), low=-5., high=5.)
assert abs(numpy.sum(v_v) - f(v_v, 0.)) < 1e-3 assert abs(np.sum(v_v) - f(v_v, 0.)) < 1e-3
def test_grad_one_output(self): def test_grad_one_output(self):
def f_rnn(u_t, x_tm1, W_in, W): def f_rnn(u_t, x_tm1, W_in, W):
...@@ -1440,12 +1440,12 @@ class T_Scan(unittest.TestCase): ...@@ -1440,12 +1440,12 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = numpy.array(rng.uniform(size=(10,), low=-.5, high=.5), v_u = np.array(rng.uniform(size=(10,), low=-.5, high=.5),
dtype=theano.config.floatX) dtype=theano.config.floatX)
v_x0 = numpy.array(rng.uniform(), dtype=theano.config.floatX) v_x0 = np.array(rng.uniform(), dtype=theano.config.floatX)
W = numpy.array(rng.uniform(), dtype=theano.config.floatX) W = np.array(rng.uniform(), dtype=theano.config.floatX)
W_in = numpy.array(rng.uniform(), dtype=theano.config.floatX) W_in = np.array(rng.uniform(), dtype=theano.config.floatX)
analytic_grad = grad_fn(v_u, v_x0, W_in, W) analytic_grad = grad_fn(v_u, v_x0, W_in, W)
num_grad = multiple_outputs_numeric_grad( num_grad = multiple_outputs_numeric_grad(
...@@ -1459,7 +1459,7 @@ class T_Scan(unittest.TestCase): ...@@ -1459,7 +1459,7 @@ class T_Scan(unittest.TestCase):
num_grad.gx[max_err_pos])) num_grad.gx[max_err_pos]))
def test_grad_multiple_outs(self): def test_grad_multiple_outs(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1))
vW = asarrayX(rng.uniform(size=(2, 2), low=-.1, high=.1)) vW = asarrayX(rng.uniform(size=(2, 2), low=-.1, high=.1))
vWout = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1)) vWout = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1))
...@@ -1524,7 +1524,7 @@ class T_Scan(unittest.TestCase): ...@@ -1524,7 +1524,7 @@ class T_Scan(unittest.TestCase):
@attr('slow') @attr('slow')
def test_grad_multiple_outs_taps(self): def test_grad_multiple_outs_taps(self):
l = 5 l = 5
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2)) vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2))
vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
...@@ -1618,7 +1618,7 @@ class T_Scan(unittest.TestCase): ...@@ -1618,7 +1618,7 @@ class T_Scan(unittest.TestCase):
@attr('slow') @attr('slow')
def test_grad_multiple_outs_taps_backwards(self): def test_grad_multiple_outs_taps_backwards(self):
l = 5 l = 5
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2)) vW = asarrayX(rng.uniform(size=(2, 2), low=-.2, high=.2))
vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2)) vWout = asarrayX(rng.uniform(size=(2,), low=-.2, high=.2))
...@@ -1685,10 +1685,10 @@ class T_Scan(unittest.TestCase): ...@@ -1685,10 +1685,10 @@ class T_Scan(unittest.TestCase):
num_grad.gx[max_err_pos])) num_grad.gx[max_err_pos]))
def test_grad_multiple_outs_some_uncomputable(self): def test_grad_multiple_outs_some_uncomputable(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in = asarrayX(rng.uniform(size=(2, 2), low=-3., high=3.)) vW_in = asarrayX(rng.uniform(size=(2, 2), low=-3., high=3.))
v_u = asarrayX(rng.uniform(size=(5, 2), low=-3., high=3.)) v_u = asarrayX(rng.uniform(size=(5, 2), low=-3., high=3.))
v_u2 = numpy.array([1, 3, 4, 6, 8], dtype='int32') v_u2 = np.array([1, 3, 4, 6, 8], dtype='int32')
v_x0 = asarrayX(rng.uniform(size=(2,), low=-3., high=3.)) v_x0 = asarrayX(rng.uniform(size=(2,), low=-3., high=3.))
W_in = theano.tensor.matrix('win') W_in = theano.tensor.matrix('win')
...@@ -1730,9 +1730,9 @@ class T_Scan(unittest.TestCase): ...@@ -1730,9 +1730,9 @@ class T_Scan(unittest.TestCase):
def reset_rng_fn(fn, *args): def reset_rng_fn(fn, *args):
for idx, arg in enumerate(fn.maker.expanded_inputs): for idx, arg in enumerate(fn.maker.expanded_inputs):
if (arg.value and type(arg.value.data) == \ if (arg.value and type(arg.value.data) == \
type(numpy.random.RandomState(123))): type(np.random.RandomState(123))):
obj = fn.maker.expanded_inputs[idx].value obj = fn.maker.expanded_inputs[idx].value
obj.data = numpy.random.RandomState(123) obj.data = np.random.RandomState(123)
fn.maker.expanded_inputs[idx].value = obj fn.maker.expanded_inputs[idx].value = obj
return fn(*args) return fn(*args)
...@@ -1764,7 +1764,7 @@ class T_Scan(unittest.TestCase): ...@@ -1764,7 +1764,7 @@ class T_Scan(unittest.TestCase):
assert(result == expected_result) assert(result == expected_result)
def test_grad_multiple_outs_some_truncate(self): def test_grad_multiple_outs_some_truncate(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in = asarrayX(rng.uniform(size=(2, 2), low=-.1, high=.1)) vW_in = asarrayX(rng.uniform(size=(2, 2), low=-.1, high=.1))
v_u = asarrayX(rng.uniform(size=(5, 2), low=-.1, high=.1)) v_u = asarrayX(rng.uniform(size=(5, 2), low=-.1, high=.1))
v_x0 = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1)) v_x0 = asarrayX(rng.uniform(size=(2,), low=-.1, high=.1))
...@@ -1807,9 +1807,9 @@ class T_Scan(unittest.TestCase): ...@@ -1807,9 +1807,9 @@ class T_Scan(unittest.TestCase):
def reset_rng_fn(fn, *args): def reset_rng_fn(fn, *args):
for idx, arg in enumerate(fn.maker.expanded_inputs): for idx, arg in enumerate(fn.maker.expanded_inputs):
if (arg.value and if (arg.value and
isinstance(arg.value.data, numpy.random.RandomState)): isinstance(arg.value.data, np.random.RandomState)):
obj = fn.maker.expanded_inputs[idx].value obj = fn.maker.expanded_inputs[idx].value
obj.data = numpy.random.RandomState(123) obj.data = np.random.RandomState(123)
fn.maker.expanded_inputs[idx].value = obj fn.maker.expanded_inputs[idx].value = obj
out = fn(*args) out = fn(*args)
return out return out
...@@ -1819,7 +1819,7 @@ class T_Scan(unittest.TestCase): ...@@ -1819,7 +1819,7 @@ class T_Scan(unittest.TestCase):
num_grad = multiple_outputs_numeric_grad( num_grad = multiple_outputs_numeric_grad(
reset_rng_cost_fn, [v_u, v_x0, vW_in]) reset_rng_cost_fn, [v_u, v_x0, vW_in])
analytic_grad = reset_rng_grad_fn(v_u, v_x0, vW_in) analytic_grad = reset_rng_grad_fn(v_u, v_x0, vW_in)
utt.assert_allclose(analytic_grad[0][:2], numpy.zeros((2, 2))) utt.assert_allclose(analytic_grad[0][:2], np.zeros((2, 2)))
def test_grad_multiple_outs_some_disconnected(self): def test_grad_multiple_outs_some_disconnected(self):
final_cost = self._grad_mout_helper(100, mode_nodebug) final_cost = self._grad_mout_helper(100, mode_nodebug)
...@@ -1833,7 +1833,7 @@ class T_Scan(unittest.TestCase): ...@@ -1833,7 +1833,7 @@ class T_Scan(unittest.TestCase):
def _grad_mout_helper(self, n_iters, mode): def _grad_mout_helper(self, n_iters, mode):
# Created on Tue Oct 07 13:28:51 2014 # Created on Tue Oct 07 13:28:51 2014
# @author: vaneetke # @author: vaneetke
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
n_hid = 3 n_hid = 3
n_in = 1 n_in = 1
n_out = 1 n_out = 1
...@@ -1897,10 +1897,10 @@ class T_Scan(unittest.TestCase): ...@@ -1897,10 +1897,10 @@ class T_Scan(unittest.TestCase):
mode=mode) mode=mode)
# artificial data # artificial data
x_v = numpy.arange(0., 10.49, 0.21, dtype=theano.config.floatX) x_v = np.arange(0., 10.49, 0.21, dtype=theano.config.floatX)
x_v = x_v.reshape(len(x_v), 1) x_v = x_v.reshape(len(x_v), 1)
s_v = numpy.sin(x_v) s_v = np.sin(x_v)
t_v = numpy.roll(s_v, -1)[:-1] t_v = np.roll(s_v, -1)[:-1]
s_v = s_v[:-1] s_v = s_v[:-1]
for i in xrange(n_iters): for i in xrange(n_iters):
cost = learn_rnn_fn(s_v, t_v) cost = learn_rnn_fn(s_v, t_v)
...@@ -1919,14 +1919,14 @@ class T_Scan(unittest.TestCase): ...@@ -1919,14 +1919,14 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
nx = rng.uniform(size=(10, 10)) nx = rng.uniform(size=(10, 10))
ny1, nz1 = f(nx) ny1, nz1 = f(nx)
ny2, nz2 = f(nx) ny2, nz2 = f(nx)
utt.assert_allclose([ny1, ny1], nz1) utt.assert_allclose([ny1, ny1], nz1)
utt.assert_allclose([ny2, ny2], nz2) utt.assert_allclose([ny2, ny2], nz2)
assert not numpy.allclose(ny1, ny2) assert not np.allclose(ny1, ny2)
def test_grad_of_shared(self): def test_grad_of_shared(self):
x1 = theano.shared(3.) x1 = theano.shared(3.)
...@@ -1942,7 +1942,7 @@ class T_Scan(unittest.TestCase): ...@@ -1942,7 +1942,7 @@ class T_Scan(unittest.TestCase):
def test_computing_gradient(self): def test_computing_gradient(self):
x1 = theano.tensor.scalar('x1') x1 = theano.tensor.scalar('x1')
x2 = theano.shared(numpy.array([1, 2, 3, 4, 5]), name='x2') x2 = theano.shared(np.array([1, 2, 3, 4, 5]), name='x2')
K = x2 * x1 K = x2 * x1
out, updates = theano.scan(lambda i, v: theano.tensor.grad(K[i], v), out, updates = theano.scan(lambda i, v: theano.tensor.grad(K[i], v),
...@@ -1950,10 +1950,10 @@ class T_Scan(unittest.TestCase): ...@@ -1950,10 +1950,10 @@ class T_Scan(unittest.TestCase):
non_sequences=x1) non_sequences=x1)
f = theano.function([x1], out, allow_input_downcast=True) f = theano.function([x1], out, allow_input_downcast=True)
assert numpy.all(f(3.) != 0.) assert np.all(f(3.) != 0.)
def test_shared_updates(self): def test_shared_updates(self):
X = theano.shared(numpy.array(1)) X = theano.shared(np.array(1))
out, updates = theano.scan( out, updates = theano.scan(
lambda: OrderedDict([(X, (X + 1))]), lambda: OrderedDict([(X, (X + 1))]),
...@@ -1967,8 +1967,8 @@ class T_Scan(unittest.TestCase): ...@@ -1967,8 +1967,8 @@ class T_Scan(unittest.TestCase):
assert X.get_value() == 11 assert X.get_value() == 11
def test_memory_aliasing_updates(self): def test_memory_aliasing_updates(self):
x = theano.shared(numpy.array(1)) x = theano.shared(np.array(1))
y = theano.shared(numpy.array(1)) y = theano.shared(np.array(1))
out, updates = theano.scan( out, updates = theano.scan(
lambda: OrderedDict([(x, x + 1), (y, x)]), lambda: OrderedDict([(x, x + 1), (y, x)]),
...@@ -1979,7 +1979,7 @@ class T_Scan(unittest.TestCase): ...@@ -1979,7 +1979,7 @@ class T_Scan(unittest.TestCase):
f = theano.function([], [], updates=updates) f = theano.function([], [], updates=updates)
f() f()
assert not numpy.may_share_memory(x.container.storage[0], assert not np.may_share_memory(x.container.storage[0],
y.container.storage[0]) y.container.storage[0])
assert x.get_value() != y.get_value() assert x.get_value() != y.get_value()
...@@ -1998,7 +1998,7 @@ class T_Scan(unittest.TestCase): ...@@ -1998,7 +1998,7 @@ class T_Scan(unittest.TestCase):
""" """
a = theano.tensor.vector() a = theano.tensor.vector()
init_a = theano.tensor.vector() init_a = theano.tensor.vector()
b = theano.shared(numpy.random.rand(5, 4)) b = theano.shared(np.random.rand(5, 4))
def inner_func(a): def inner_func(a):
return a + 1, OrderedDict([(b, 2 * b)]) return a + 1, OrderedDict([(b, 2 * b)])
...@@ -2032,9 +2032,9 @@ class T_Scan(unittest.TestCase): ...@@ -2032,9 +2032,9 @@ class T_Scan(unittest.TestCase):
non_sequences=[gy, x]) non_sequences=[gy, x])
f = theano.function([x, A], hy, allow_input_downcast=True) f = theano.function([x, A], hy, allow_input_downcast=True)
vx = numpy.array([1., 1.], dtype=theano.config.floatX) vx = np.array([1., 1.], dtype=theano.config.floatX)
vA = numpy.array([[1., 1.], [1., 0.]], dtype=theano.config.floatX) vA = np.array([[1., 1.], [1., 0.]], dtype=theano.config.floatX)
vR = numpy.array([[3.6, 1.8], [1.8, 0.9]], dtype=theano.config.floatX) vR = np.array([[3.6, 1.8], [1.8, 0.9]], dtype=theano.config.floatX)
out = f(vx, vA) out = f(vx, vA)
utt.assert_allclose(out, vR) utt.assert_allclose(out, vR)
...@@ -2157,7 +2157,7 @@ class T_Scan(unittest.TestCase): ...@@ -2157,7 +2157,7 @@ class T_Scan(unittest.TestCase):
# some rnn with multiple outputs and multiple inputs; other # some rnn with multiple outputs and multiple inputs; other
# dimension instead of scalars/vectors # dimension instead of scalars/vectors
def test_reordering(self): def test_reordering(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.)) vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.))
vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
...@@ -2200,15 +2200,15 @@ class T_Scan(unittest.TestCase): ...@@ -2200,15 +2200,15 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# compute the values in numpy # compute the values in numpy
v_x = numpy.zeros((3, 2), dtype=theano.config.floatX) v_x = np.zeros((3, 2), dtype=theano.config.floatX)
v_y = numpy.zeros((3,), dtype=theano.config.floatX) v_y = np.zeros((3,), dtype=theano.config.floatX)
v_x[0] = numpy.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \ v_x[0] = np.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \
numpy.dot(v_x0, vW) np.dot(v_x0, vW)
v_y[0] = numpy.dot(v_x0, vWout) + v_y0[2] v_y[0] = np.dot(v_x0, vWout) + v_y0[2]
for i in xrange(1, 3): for i in xrange(1, 3):
v_x[i] = numpy.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \ v_x[i] = np.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \
numpy.dot(v_x[i - 1], vW) np.dot(v_x[i - 1], vW)
v_y[i] = numpy.dot(v_x[i - 1], vWout) + v_y[i - 1] v_y[i] = np.dot(v_x[i - 1], vWout) + v_y[i - 1]
(theano_dump1, theano_dump2, theano_x, theano_y) = f4(v_u1, (theano_dump1, theano_dump2, theano_x, theano_y) = f4(v_u1,
v_u2, v_u2,
...@@ -2247,7 +2247,7 @@ class T_Scan(unittest.TestCase): ...@@ -2247,7 +2247,7 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
def test_save_mem(self): def test_save_mem(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.)) vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.))
vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
...@@ -2288,16 +2288,16 @@ class T_Scan(unittest.TestCase): ...@@ -2288,16 +2288,16 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# compute the values in numpy # compute the values in numpy
v_x = numpy.zeros((8, 2), dtype=theano.config.floatX) v_x = np.zeros((8, 2), dtype=theano.config.floatX)
v_y = numpy.zeros((8,), dtype=theano.config.floatX) v_y = np.zeros((8,), dtype=theano.config.floatX)
v_x[0] = numpy.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \ v_x[0] = np.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \
numpy.dot(v_x0, vW) np.dot(v_x0, vW)
v_y[0] = numpy.dot(v_x0, vWout) + v_y0[2] v_y[0] = np.dot(v_x0, vWout) + v_y0[2]
for i in xrange(1, 8): for i in xrange(1, 8):
v_x[i] = numpy.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \ v_x[i] = np.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \
numpy.dot(v_x[i - 1], vW) np.dot(v_x[i - 1], vW)
v_y[i] = numpy.dot(v_x[i - 1], vWout) + v_y[i - 1] v_y[i] = np.dot(v_x[i - 1], vWout) + v_y[i - 1]
(theano_dump, theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1) (theano_dump, theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1)
...@@ -2321,24 +2321,24 @@ class T_Scan(unittest.TestCase): ...@@ -2321,24 +2321,24 @@ class T_Scan(unittest.TestCase):
sh = expr.shape[0] sh = expr.shape[0]
v1 = theano.shared(numpy.ones(5, dtype=theano.config.floatX)) v1 = theano.shared(np.ones(5, dtype=theano.config.floatX))
v2 = theano.shared(numpy.ones((5, 5), dtype=theano.config.floatX)) v2 = theano.shared(np.ones((5, 5), dtype=theano.config.floatX))
shapef = theano.function([W], shapef = theano.function([W],
expr, expr,
givens=OrderedDict([(initial, v1), givens=OrderedDict([(initial, v1),
(inpt, v2)])) (inpt, v2)]))
# First execution to cache n_steps # First execution to cache n_steps
shapef(numpy.ones((5, 5), dtype=theano.config.floatX)) shapef(np.ones((5, 5), dtype=theano.config.floatX))
cost = expr.sum() cost = expr.sum()
d_cost_wrt_W = tensor.grad(cost, [W]) d_cost_wrt_W = tensor.grad(cost, [W])
f = theano.function( f = theano.function(
[W, inpt], d_cost_wrt_W, [W, inpt], d_cost_wrt_W,
givens=OrderedDict([(initial, theano.shared(numpy.zeros(5)))])) givens=OrderedDict([(initial, theano.shared(np.zeros(5)))]))
rval = numpy.asarray([[5187989] * 5] * 5, dtype=theano.config.floatX) rval = np.asarray([[5187989] * 5] * 5, dtype=theano.config.floatX)
arg1 = numpy.ones((5, 5), dtype=theano.config.floatX) arg1 = np.ones((5, 5), dtype=theano.config.floatX)
arg2 = numpy.ones((10, 5), dtype=theano.config.floatX) arg2 = np.ones((10, 5), dtype=theano.config.floatX)
utt.assert_allclose(f(arg1, arg2), rval) utt.assert_allclose(f(arg1, arg2), rval)
def test_save_mem_reduced_number_of_steps(self): def test_save_mem_reduced_number_of_steps(self):
...@@ -2372,7 +2372,7 @@ class T_Scan(unittest.TestCase): ...@@ -2372,7 +2372,7 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
allow_input_downcast=True) allow_input_downcast=True)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(20,), low=-5., high=5.) v_u = rng.uniform(size=(20,), low=-5., high=5.)
# compute the output in numpy # compute the output in numpy
...@@ -2428,7 +2428,7 @@ class T_Scan(unittest.TestCase): ...@@ -2428,7 +2428,7 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(20,), low=-5., high=5.) v_u = rng.uniform(size=(20,), low=-5., high=5.)
# compute the output in numpy # compute the output in numpy
...@@ -2474,7 +2474,7 @@ class T_Scan(unittest.TestCase): ...@@ -2474,7 +2474,7 @@ class T_Scan(unittest.TestCase):
floatX = theano.config.floatX floatX = theano.config.floatX
init_value = 5.0 init_value = 5.0
seq_value = numpy.arange(4, dtype=floatX) seq_value = np.arange(4, dtype=floatX)
output1, output2 = fct(init_value, seq_value) output1, output2 = fct(init_value, seq_value)
expected_output1 = [init_value] expected_output1 = [init_value]
...@@ -2509,13 +2509,13 @@ class T_Scan(unittest.TestCase): ...@@ -2509,13 +2509,13 @@ class T_Scan(unittest.TestCase):
[out1_direct, out2_direct]) [out1_direct, out2_direct])
# Test that the function returns valid outputs # Test that the function returns valid outputs
x_val = numpy.arange(0, 4)[:, None] x_val = np.arange(0, 4)[:, None]
seq_val = numpy.arange(4, 8)[:, None] seq_val = np.arange(4, 8)[:, None]
out1, out2 = fct(x_val, seq_val) out1, out2 = fct(x_val, seq_val)
expected_out1 = numpy.zeros((5, 4, 1)) expected_out1 = np.zeros((5, 4, 1))
expected_out2 = numpy.zeros((5, 4, 1)) expected_out2 = np.zeros((5, 4, 1))
for i in range(4): for i in range(4):
expected_out2[i + 1] = expected_out2[i] + seq_val[i] expected_out2[i + 1] = expected_out2[i] + seq_val[i]
for i in range(5): for i in range(5):
...@@ -2565,7 +2565,7 @@ class T_Scan(unittest.TestCase): ...@@ -2565,7 +2565,7 @@ class T_Scan(unittest.TestCase):
diff = mitsot_m1 + seq1 diff = mitsot_m1 + seq1
next_mitsot_val = mitsot_m2 + diff next_mitsot_val = mitsot_m2 + diff
next_sitsot_val = sitsot_m1 - diff next_sitsot_val = sitsot_m1 - diff
nitsot_out = tensor.alloc(numpy.asarray(0., 'float32'), nitsot_out = tensor.alloc(np.asarray(0., 'float32'),
next_mitsot_val + next_mitsot_val +
next_sitsot_val) next_sitsot_val)
return next_sitsot_val, next_mitsot_val, nitsot_out return next_sitsot_val, next_mitsot_val, nitsot_out
...@@ -2584,7 +2584,7 @@ class T_Scan(unittest.TestCase): ...@@ -2584,7 +2584,7 @@ class T_Scan(unittest.TestCase):
assert(len(scan_nodes_from_fct(f)) == 1) assert(len(scan_nodes_from_fct(f)) == 1)
# This generate a scan crash during execution. # This generate a scan crash during execution.
# output_shape = f(numpy.arange(5), 5, [1, 2]) # output_shape = f(np.arange(5), 5, [1, 2])
# assert(all(output_shape == (5, 6))) # assert(all(output_shape == (5, 6)))
# The following test will fail in DebugMode if there are # The following test will fail in DebugMode if there are
...@@ -2608,7 +2608,7 @@ class T_Scan(unittest.TestCase): ...@@ -2608,7 +2608,7 @@ class T_Scan(unittest.TestCase):
go1 = theano.tensor.grad(o1.mean(), wrt=x) go1 = theano.tensor.grad(o1.mean(), wrt=x)
f = theano.function([x], go1, updates=updates, f = theano.function([x], go1, updates=updates,
allow_input_downcast=True, mode=mode_with_opt) allow_input_downcast=True, mode=mode_with_opt)
self.assertTrue(numpy.allclose(f([1, 2, 3]), 2. / 3)) self.assertTrue(np.allclose(f([1, 2, 3]), 2. / 3))
topo = f.maker.fgraph.toposort() topo = f.maker.fgraph.toposort()
# this new assert is here to test if scan_merging works .. # this new assert is here to test if scan_merging works ..
...@@ -2711,7 +2711,7 @@ class T_Scan(unittest.TestCase): ...@@ -2711,7 +2711,7 @@ class T_Scan(unittest.TestCase):
n.op, theano.scan_module.scan_op.Scan)] n.op, theano.scan_module.scan_op.Scan)]
self.assertTrue(len(scans) == 2) self.assertTrue(len(scans) == 2)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
x_val = rng.uniform(size=(4,)).astype(theano.config.floatX) x_val = rng.uniform(size=(4,)).astype(theano.config.floatX)
y_val = rng.uniform(size=(4,)).astype(theano.config.floatX) y_val = rng.uniform(size=(4,)).astype(theano.config.floatX)
# Run it so DebugMode can detect optimization problems. # Run it so DebugMode can detect optimization problems.
...@@ -2752,7 +2752,7 @@ class T_Scan(unittest.TestCase): ...@@ -2752,7 +2752,7 @@ class T_Scan(unittest.TestCase):
return M return M
# some initializations # some initializations
hypx = numpy.log(numpy.tile([1,1,1,1,1,1,0.01], (3,1))) hypx = np.log(np.tile([1,1,1,1,1,1,0.01], (3,1)))
# variables used in the following expressions # variables used in the following expressions
hyp = theano.shared(hypx) hyp = theano.shared(hypx)
...@@ -2763,10 +2763,10 @@ class T_Scan(unittest.TestCase): ...@@ -2763,10 +2763,10 @@ class T_Scan(unittest.TestCase):
M = init_predictive_output(inputs,targets,hyp,x_star,s_star) M = init_predictive_output(inputs,targets,hyp,x_star,s_star)
X = numpy.random.random((10,4)) X = np.random.random((10,4))
Y = numpy.random.random((10,3)) Y = np.random.random((10,3))
test_m = numpy.random.random((4,)) test_m = np.random.random((4,))
test_s = numpy.eye(4) test_s = np.eye(4)
# Compute expected outputs (jacobian of M wrt x_star) # Compute expected outputs (jacobian of M wrt x_star)
dfdm = theano.function([inputs,targets,x_star,s_star], dfdm = theano.function([inputs,targets,x_star,s_star],
...@@ -2851,9 +2851,9 @@ class T_Scan(unittest.TestCase): ...@@ -2851,9 +2851,9 @@ class T_Scan(unittest.TestCase):
x = theano.tensor.fmatrix('x') x = theano.tensor.fmatrix('x')
mem_val = numpy.zeros((2,), dtype='float32') mem_val = np.zeros((2,), dtype='float32')
memory = theano.shared(mem_val) memory = theano.shared(mem_val)
W = theano.shared(numpy.random.random((5, 2)).astype('float32')) W = theano.shared(np.random.random((5, 2)).astype('float32'))
def f(inp, mem): def f(inp, mem):
i = theano.tensor.join(0, inp, mem) i = theano.tensor.join(0, inp, mem)
...@@ -2867,7 +2867,7 @@ class T_Scan(unittest.TestCase): ...@@ -2867,7 +2867,7 @@ class T_Scan(unittest.TestCase):
f = theano.function([x], outs[0]) f = theano.function([x], outs[0])
f2 = theano.function([x], outs[1]) f2 = theano.function([x], outs[1])
x_val = numpy.random.random((4, 3)).astype('float32') x_val = np.random.random((4, 3)).astype('float32')
f_vals = f(x_val) f_vals = f(x_val)
memory.set_value(mem_val) memory.set_value(mem_val)
...@@ -2876,12 +2876,12 @@ class T_Scan(unittest.TestCase): ...@@ -2876,12 +2876,12 @@ class T_Scan(unittest.TestCase):
def test_reduce_memory_consumption(self): def test_reduce_memory_consumption(self):
x = theano.shared(numpy.asarray( x = theano.shared(np.asarray(
numpy.random.uniform(size=(10,)), dtype=theano.config.floatX)) np.random.uniform(size=(10,)), dtype=theano.config.floatX))
o, _ = theano.reduce(lambda v, acc: acc + v, o, _ = theano.reduce(lambda v, acc: acc + v,
x, x,
theano.tensor.constant( theano.tensor.constant(
numpy.asarray(0., np.asarray(0.,
dtype=theano.config.floatX))) dtype=theano.config.floatX)))
mode = theano.compile.mode.FAST_RUN mode = theano.compile.mode.FAST_RUN
mode = mode.excluding('inplace') mode = mode.excluding('inplace')
...@@ -2905,15 +2905,15 @@ class T_Scan(unittest.TestCase): ...@@ -2905,15 +2905,15 @@ class T_Scan(unittest.TestCase):
gx = theano.tensor.grad(o, x) gx = theano.tensor.grad(o, x)
f2 = theano.function([], gx) f2 = theano.function([], gx)
utt.assert_allclose(f2(), numpy.ones((10,))) utt.assert_allclose(f2(), np.ones((10,)))
def test_foldl_memory_consumption(self): def test_foldl_memory_consumption(self):
x = theano.shared(numpy.asarray( x = theano.shared(np.asarray(
numpy.random.uniform(size=(10,)), dtype=theano.config.floatX)) np.random.uniform(size=(10,)), dtype=theano.config.floatX))
o, _ = theano.foldl(lambda v, acc: acc + v, o, _ = theano.foldl(lambda v, acc: acc + v,
x, x,
theano.tensor.constant( theano.tensor.constant(
numpy.asarray(0., np.asarray(0.,
dtype=theano.config.floatX))) dtype=theano.config.floatX)))
mode = theano.compile.mode.FAST_RUN mode = theano.compile.mode.FAST_RUN
...@@ -2938,16 +2938,16 @@ class T_Scan(unittest.TestCase): ...@@ -2938,16 +2938,16 @@ class T_Scan(unittest.TestCase):
gx = theano.tensor.grad(o, x) gx = theano.tensor.grad(o, x)
f2 = theano.function([], gx) f2 = theano.function([], gx)
utt.assert_allclose(f2(), numpy.ones((10,))) utt.assert_allclose(f2(), np.ones((10,)))
def test_foldr_memory_consumption(self): def test_foldr_memory_consumption(self):
x = theano.shared(numpy.asarray( x = theano.shared(np.asarray(
numpy.random.uniform(size=(10,)), dtype=theano.config.floatX)) np.random.uniform(size=(10,)), dtype=theano.config.floatX))
o, _ = theano.foldr(lambda v, acc: acc + v, o, _ = theano.foldr(lambda v, acc: acc + v,
x, x,
theano.tensor.constant( theano.tensor.constant(
numpy.asarray(0., np.asarray(0.,
dtype=theano.config.floatX))) dtype=theano.config.floatX)))
mode = theano.compile.mode.FAST_RUN mode = theano.compile.mode.FAST_RUN
...@@ -2972,26 +2972,26 @@ class T_Scan(unittest.TestCase): ...@@ -2972,26 +2972,26 @@ class T_Scan(unittest.TestCase):
gx = theano.tensor.grad(o, x) gx = theano.tensor.grad(o, x)
f2 = theano.function([], gx) f2 = theano.function([], gx)
utt.assert_allclose(f2(), numpy.ones((10,))) utt.assert_allclose(f2(), np.ones((10,)))
@attr('slow') @attr('slow')
def test_rop2(self): def test_rop2(self):
seed = utt.fetch_seed() seed = utt.fetch_seed()
rng = numpy.random.RandomState(seed) rng = np.random.RandomState(seed)
floatX = theano.config.floatX floatX = theano.config.floatX
v_u = numpy.array(rng.uniform(size=(3, 5)) - .5, dtype=floatX) v_u = np.array(rng.uniform(size=(3, 5)) - .5, dtype=floatX)
v_W = numpy.array(rng.uniform(size=(5, 5)) - .5, dtype=floatX) v_W = np.array(rng.uniform(size=(5, 5)) - .5, dtype=floatX)
v_h0 = numpy.array(rng.uniform(size=(5,)) - .5, dtype=floatX) v_h0 = np.array(rng.uniform(size=(5,)) - .5, dtype=floatX)
v_eu = numpy.array(rng.uniform(size=(3, 5)) - .5, dtype=floatX) v_eu = np.array(rng.uniform(size=(3, 5)) - .5, dtype=floatX)
v_eW = numpy.array(rng.uniform(size=(5, 5)) - .5, dtype=floatX) v_eW = np.array(rng.uniform(size=(5, 5)) - .5, dtype=floatX)
v_eh0 = numpy.array(rng.uniform(size=(5,)) - .5, dtype=floatX) v_eh0 = np.array(rng.uniform(size=(5,)) - .5, dtype=floatX)
def rnn_fn(_u, _y, _W): def rnn_fn(_u, _y, _W):
srng = theano.tensor.shared_randomstreams.RandomStreams(seed) srng = theano.tensor.shared_randomstreams.RandomStreams(seed)
tmp_val = _u + _y + srng.uniform(size=v_h0.shape) *\ tmp_val = _u + _y + srng.uniform(size=v_h0.shape) *\
numpy.asarray(1e-6, dtype=floatX) np.asarray(1e-6, dtype=floatX)
sl_o = theano.tensor.tanh(theano.tensor.dot(_W, tmp_val)) sl_o = theano.tensor.tanh(theano.tensor.dot(_W, tmp_val))
return sl_o, tmp_val return sl_o, tmp_val
...@@ -3053,15 +3053,15 @@ class T_Scan(unittest.TestCase): ...@@ -3053,15 +3053,15 @@ class T_Scan(unittest.TestCase):
def test_rop(self): def test_rop(self):
seed = utt.fetch_seed() seed = utt.fetch_seed()
rng = numpy.random.RandomState(seed) rng = np.random.RandomState(seed)
floatX = theano.config.floatX floatX = theano.config.floatX
v_u = numpy.array(rng.uniform(size=(20, 5)), dtype=floatX) v_u = np.array(rng.uniform(size=(20, 5)), dtype=floatX)
v_W = numpy.array(rng.uniform(size=(5, 5)), dtype=floatX) v_W = np.array(rng.uniform(size=(5, 5)), dtype=floatX)
v_h0 = numpy.array(rng.uniform(size=(5,)), dtype=floatX) v_h0 = np.array(rng.uniform(size=(5,)), dtype=floatX)
v_eu = numpy.array(rng.uniform(size=(20, 5)), dtype=floatX) v_eu = np.array(rng.uniform(size=(20, 5)), dtype=floatX)
v_eW = numpy.array(rng.uniform(size=(5, 5)), dtype=floatX) v_eW = np.array(rng.uniform(size=(5, 5)), dtype=floatX)
v_eh0 = numpy.array(rng.uniform(size=(5,)), dtype=floatX) v_eh0 = np.array(rng.uniform(size=(5,)), dtype=floatX)
def rnn_fn(_u, _y, _W): def rnn_fn(_u, _y, _W):
sl_o = theano.tensor.tanh(theano.tensor.dot(_W, (_u + _y))) sl_o = theano.tensor.tanh(theano.tensor.dot(_W, (_u + _y)))
...@@ -3163,14 +3163,14 @@ class T_Scan(unittest.TestCase): ...@@ -3163,14 +3163,14 @@ class T_Scan(unittest.TestCase):
assert len(scan_nodes) == 0 assert len(scan_nodes) == 0
seed = utt.fetch_seed() seed = utt.fetch_seed()
rng = numpy.random.RandomState(seed) rng = np.random.RandomState(seed)
floatX = theano.config.floatX floatX = theano.config.floatX
v_h = numpy.array(rng.uniform(size=(2,)), dtype=floatX) v_h = np.array(rng.uniform(size=(2,)), dtype=floatX)
v_W1 = numpy.array(rng.uniform(size=(2, 2)), dtype=floatX) v_W1 = np.array(rng.uniform(size=(2, 2)), dtype=floatX)
v_W2 = numpy.array(rng.uniform(size=(2, 2)), dtype=floatX) v_W2 = np.array(rng.uniform(size=(2, 2)), dtype=floatX)
v_out = numpy.dot(v_h, v_W1 + v_W2) v_out = np.dot(v_h, v_W1 + v_W2)
sol = numpy.zeros((5, 2)) sol = np.zeros((5, 2))
# This line is here to make sol have the same shape as the output of # This line is here to make sol have the same shape as the output of
# theano. Note that what we ask theano to do is to repeat the 2 # theano. Note that what we ask theano to do is to repeat the 2
# elements vector v_out 5 times # elements vector v_out 5 times
...@@ -3206,9 +3206,9 @@ class T_Scan(unittest.TestCase): ...@@ -3206,9 +3206,9 @@ class T_Scan(unittest.TestCase):
f_ref = theano.function([W1, W2, step_indices], o, mode='FAST_COMPILE') f_ref = theano.function([W1, W2, step_indices], o, mode='FAST_COMPILE')
# Compare the results of the two implementations # Compare the results of the two implementations
input_values = [numpy.random.random((5, 5)).astype("float32"), input_values = [np.random.random((5, 5)).astype("float32"),
numpy.random.random((5, 5)).astype("float32"), np.random.random((5, 5)).astype("float32"),
numpy.arange(5).astype("float32")] np.arange(5).astype("float32")]
out = f(*input_values) out = f(*input_values)
out_ref = f_ref(*input_values) out_ref = f_ref(*input_values)
...@@ -3243,10 +3243,10 @@ class T_Scan(unittest.TestCase): ...@@ -3243,10 +3243,10 @@ class T_Scan(unittest.TestCase):
([i_t, i_tm1], _) = theano.scan( ([i_t, i_tm1], _) = theano.scan(
fn, sequences=[inp], fn, sequences=[inp],
outputs_info=[numpy.asarray([0.0, 0.0], theano.config.floatX), outputs_info=[np.asarray([0.0, 0.0], theano.config.floatX),
None]) None])
f = theano.function([inp], [i_t, i_tm1]) f = theano.function([inp], [i_t, i_tm1])
val = numpy.arange(10).reshape(5, 2).astype(theano.config.floatX) val = np.arange(10).reshape(5, 2).astype(theano.config.floatX)
ret = f(val) ret = f(val)
utt.assert_allclose(ret[0], val + 10) utt.assert_allclose(ret[0], val + 10)
utt.assert_allclose(ret[1], [[0., 0.], utt.assert_allclose(ret[1], [[0., 0.],
...@@ -3330,7 +3330,7 @@ class T_Scan(unittest.TestCase): ...@@ -3330,7 +3330,7 @@ class T_Scan(unittest.TestCase):
return x_t + 1, theano.scan_module.until(x_t > 3) return x_t + 1, theano.scan_module.until(x_t > 3)
o, _ = theano.scan(lambda_fn, x) o, _ = theano.scan(lambda_fn, x)
f = theano.function([x], o) f = theano.function([x], o)
vx = numpy.zeros((50,), dtype=theano.config.floatX) vx = np.zeros((50,), dtype=theano.config.floatX)
vx[23] = 4 vx[23] = 4
out = f(vx) out = f(vx)
assert len(out) == 24 assert len(out) == 24
...@@ -3344,11 +3344,11 @@ class T_Scan(unittest.TestCase): ...@@ -3344,11 +3344,11 @@ class T_Scan(unittest.TestCase):
o2, _ = theano.scan(lambda x_t: x_t + 2, x) o2, _ = theano.scan(lambda x_t: x_t + 2, x)
f = theano.function([x], [o, o2], mode=mode_with_opt) f = theano.function([x], [o, o2], mode=mode_with_opt)
vx = numpy.zeros((50,), dtype=theano.config.floatX) vx = np.zeros((50,), dtype=theano.config.floatX)
vx[23] = 4 vx[23] = 4
out, out2 = f(vx) out, out2 = f(vx)
assert len(out) == 24 assert len(out) == 24
assert numpy.all(out2 == vx + 2) assert np.all(out2 == vx + 2)
lssc = [x for x in f.maker.fgraph.toposort() lssc = [x for x in f.maker.fgraph.toposort()
if isinstance(x.op, theano.scan_module.scan_op.Scan)] if isinstance(x.op, theano.scan_module.scan_op.Scan)]
# One scan node gets optimnized out # One scan node gets optimnized out
...@@ -3402,7 +3402,7 @@ class T_Scan(unittest.TestCase): ...@@ -3402,7 +3402,7 @@ class T_Scan(unittest.TestCase):
polynomial3[-1], polynomial3[-1],
polynomial4[-1]]) polynomial4[-1]])
test_coeff = numpy.asarray([1, 0, 2], dtype=theano.config.floatX) test_coeff = np.asarray([1, 0, 2], dtype=theano.config.floatX)
# This will be tested by DEBUG_MODE # This will be tested by DEBUG_MODE
out = calculate_polynomial(test_coeff, 3) out = calculate_polynomial(test_coeff, 3)
assert out[0] == 19 assert out[0] == 19
...@@ -3480,7 +3480,7 @@ class T_Scan(unittest.TestCase): ...@@ -3480,7 +3480,7 @@ class T_Scan(unittest.TestCase):
x) x)
f = theano.function([x], [o, o2], mode=mode_with_opt) f = theano.function([x], [o, o2], mode=mode_with_opt)
vx = numpy.zeros((50,), dtype=theano.config.floatX) vx = np.zeros((50,), dtype=theano.config.floatX)
vx[23] = 4 vx[23] = 4
out, out2 = f(vx) out, out2 = f(vx)
assert len(out) == 24 assert len(out) == 24
...@@ -3497,7 +3497,7 @@ class T_Scan(unittest.TestCase): ...@@ -3497,7 +3497,7 @@ class T_Scan(unittest.TestCase):
o, _ = theano.scan(lambda_fn, x) o, _ = theano.scan(lambda_fn, x)
f = theano.function([x], o.shape[0], mode=mode_with_opt) f = theano.function([x], o.shape[0], mode=mode_with_opt)
vx = numpy.zeros((50,), dtype=theano.config.floatX) vx = np.zeros((50,), dtype=theano.config.floatX)
vx[23] = 4 vx[23] = 4
out = f(vx) out = f(vx)
assert out == 24 assert out == 24
...@@ -3516,7 +3516,7 @@ class T_Scan(unittest.TestCase): ...@@ -3516,7 +3516,7 @@ class T_Scan(unittest.TestCase):
[o1.shape[0], o2.shape[0]], [o1.shape[0], o2.shape[0]],
mode=mode_with_opt) mode=mode_with_opt)
vx = numpy.ones((10,), dtype=theano.config.floatX) vx = np.ones((10,), dtype=theano.config.floatX)
out1, out2 = f(vx) out1, out2 = f(vx)
assert out1 == 10 assert out1 == 10
assert out2 == 10 assert out2 == 10
...@@ -3535,7 +3535,7 @@ class T_Scan(unittest.TestCase): ...@@ -3535,7 +3535,7 @@ class T_Scan(unittest.TestCase):
[o1.shape[0], o2.shape[0]], [o1.shape[0], o2.shape[0]],
mode=mode_with_opt) mode=mode_with_opt)
vx = numpy.ones((30,), dtype=theano.config.floatX) vx = np.ones((30,), dtype=theano.config.floatX)
o1, o2 = f(vx) o1, o2 = f(vx)
assert o1 == 20 assert o1 == 20
assert o2 == 20 assert o2 == 20
...@@ -3635,13 +3635,13 @@ class T_Scan(unittest.TestCase): ...@@ -3635,13 +3635,13 @@ class T_Scan(unittest.TestCase):
# Run the function and validate the outputs # Run the function and validate the outputs
dtype = theano.config.floatX dtype = theano.config.floatX
seq_value = numpy.random.random((10, 3)).astype(dtype) seq_value = np.random.random((10, 3)).astype(dtype)
out_init_value = numpy.random.random((3, 3)).astype(dtype) out_init_value = np.random.random((3, 3)).astype(dtype)
non_seq_value = numpy.random.random((3)).astype(dtype) non_seq_value = np.random.random((3)).astype(dtype)
outputs = fct(seq_value, out_init_value, non_seq_value) outputs = fct(seq_value, out_init_value, non_seq_value)
expected_g_seq = numpy.array([[4, 4, 4], expected_g_seq = np.array([[4, 4, 4],
[3, 3, 3], [3, 3, 3],
[3, 3, 3], [3, 3, 3],
[3, 3, 3], [3, 3, 3],
...@@ -3652,7 +3652,7 @@ class T_Scan(unittest.TestCase): ...@@ -3652,7 +3652,7 @@ class T_Scan(unittest.TestCase):
[1, 1, 1], [1, 1, 1],
[1, 1, 1]]) [1, 1, 1]])
expected_g_out_init = expected_g_seq[:3] expected_g_out_init = expected_g_seq[:3]
expected_g_non_seq = numpy.array([22, 22, 22]) expected_g_non_seq = np.array([22, 22, 22])
utt.assert_allclose(outputs[0], expected_g_seq) utt.assert_allclose(outputs[0], expected_g_seq)
utt.assert_allclose(outputs[1], expected_g_out_init) utt.assert_allclose(outputs[1], expected_g_out_init)
...@@ -3729,7 +3729,7 @@ class T_Scan(unittest.TestCase): ...@@ -3729,7 +3729,7 @@ class T_Scan(unittest.TestCase):
assert tf([1.0, 2.0, -3.0, 4.0], 2.0) == 42 assert tf([1.0, 2.0, -3.0, 4.0], 2.0) == 42
def test_return_steps(self): def test_return_steps(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vW_in2 = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.)) vW = asarrayX(rng.uniform(size=(2, 2), low=-5., high=5.))
vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.)) vWout = asarrayX(rng.uniform(size=(2,), low=-5., high=5.))
...@@ -3774,16 +3774,16 @@ class T_Scan(unittest.TestCase): ...@@ -3774,16 +3774,16 @@ class T_Scan(unittest.TestCase):
allow_input_downcast=True) allow_input_downcast=True)
# compute the values in numpy # compute the values in numpy
v_x = numpy.zeros((8, 2), dtype=theano.config.floatX) v_x = np.zeros((8, 2), dtype=theano.config.floatX)
v_y = numpy.zeros((8,), dtype=theano.config.floatX) v_y = np.zeros((8,), dtype=theano.config.floatX)
v_x[0] = numpy.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \ v_x[0] = np.dot(v_u1[0], vW_in1) + v_u2[0] * vW_in2 + \
numpy.dot(v_x0, vW) np.dot(v_x0, vW)
v_y[0] = numpy.dot(v_x0, vWout) + v_y0[2] v_y[0] = np.dot(v_x0, vWout) + v_y0[2]
for i in xrange(1, 8): for i in xrange(1, 8):
v_x[i] = numpy.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \ v_x[i] = np.dot(v_u1[i], vW_in1) + v_u2[i] * vW_in2 + \
numpy.dot(v_x[i - 1], vW) np.dot(v_x[i - 1], vW)
v_y[i] = numpy.dot(v_x[i - 1], vWout) + v_y[i - 1] v_y[i] = np.dot(v_x[i - 1], vWout) + v_y[i - 1]
(theano_dump, theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1) (theano_dump, theano_x, theano_y) = f4(v_u1, v_u2, v_x0, v_y0, vW_in1)
...@@ -3811,14 +3811,14 @@ class T_Scan(unittest.TestCase): ...@@ -3811,14 +3811,14 @@ class T_Scan(unittest.TestCase):
assert any([isinstance(node.op, tensor.blas.Dot22) assert any([isinstance(node.op, tensor.blas.Dot22)
for node in topo]) for node in topo])
vx = numpy.array([[1., 1.], [2., 2.]], dtype=theano.config.floatX) vx = np.array([[1., 1.], [2., 2.]], dtype=theano.config.floatX)
vA = numpy.array([[1., 1.], [1., 0.]], dtype=theano.config.floatX) vA = np.array([[1., 1.], [1., 0.]], dtype=theano.config.floatX)
vR = numpy.array([[[2, 1], [4, 2]], [[2, 1], [4, 2]]], vR = np.array([[[2, 1], [4, 2]], [[2, 1], [4, 2]]],
dtype=theano.config.floatX) dtype=theano.config.floatX)
utt.assert_allclose(f(vx, vA), vR) utt.assert_allclose(f(vx, vA), vR)
def test_savemem_opt(self): def test_savemem_opt(self):
y0 = theano.shared(numpy.ones((2, 10))) y0 = theano.shared(np.ones((2, 10)))
[y1, y2], updates = theano.scan(lambda y: [y, y], [y1, y2], updates = theano.scan(lambda y: [y, y],
outputs_info=[dict(initial=y0, outputs_info=[dict(initial=y0,
taps=[-2]), None], taps=[-2]), None],
...@@ -3860,9 +3860,9 @@ class T_Scan(unittest.TestCase): ...@@ -3860,9 +3860,9 @@ class T_Scan(unittest.TestCase):
f = theano.function(inputs=[x, w], outputs=get_outputs(x, w)) f = theano.function(inputs=[x, w], outputs=get_outputs(x, w))
# Test the function to ensure it returns valid results # Test the function to ensure it returns valid results
x_value = numpy.random.random((2, 2, 3)).astype(theano.config.floatX) x_value = np.random.random((2, 2, 3)).astype(theano.config.floatX)
w_value = numpy.random.random((3, 3)).astype(theano.config.floatX) w_value = np.random.random((3, 3)).astype(theano.config.floatX)
expected_output = numpy.tile(x_value[:, 0].sum(0), (3, 1)).transpose() expected_output = np.tile(x_value[:, 0].sum(0), (3, 1)).transpose()
output = f(x_value, w_value) output = f(x_value, w_value)
utt.assert_allclose(output, expected_output) utt.assert_allclose(output, expected_output)
...@@ -3891,17 +3891,17 @@ class T_Scan(unittest.TestCase): ...@@ -3891,17 +3891,17 @@ class T_Scan(unittest.TestCase):
gw, gx = tensor.grad(loss, [w, xinit]) gw, gx = tensor.grad(loss, [w, xinit])
grad_fn = theano.function([xinit, w], [gx, gw], grad_fn = theano.function([xinit, w], [gx, gw],
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
# If numbers are small, the gradients with respect to x are small # If numbers are small, the gradients with respect to x are small
# and the numeric differentiation becomes unstable. # and the numeric differentiation becomes unstable.
# To fix this issue I ensure we are sampling numbers larger in # To fix this issue I ensure we are sampling numbers larger in
# absolute value than 1. # absolute value than 1.
v_x = numpy.array(rng.uniform(size=(5, 2, 2), low=1., high=3.), v_x = np.array(rng.uniform(size=(5, 2, 2), low=1., high=3.),
dtype=theano.config.floatX) dtype=theano.config.floatX)
# Making some entries to be negative. # Making some entries to be negative.
pos = rng.uniform(size=(5, 2, 2), low=0., high=1) < .5 pos = rng.uniform(size=(5, 2, 2), low=0., high=1) < .5
v_x[pos] = -1 * v_x[pos] v_x[pos] = -1 * v_x[pos]
v_w = numpy.array(rng.uniform(size=(2, 2), low=1., high=3.), v_w = np.array(rng.uniform(size=(2, 2), low=1., high=3.),
dtype=theano.config.floatX) dtype=theano.config.floatX)
pos = rng.uniform(size=(2, 2), low=0., high=1.) < .5 pos = rng.uniform(size=(2, 2), low=0., high=1.) < .5
v_w[pos] = -1 * v_w[pos] v_w[pos] = -1 * v_w[pos]
...@@ -3916,11 +3916,11 @@ class T_Scan(unittest.TestCase): ...@@ -3916,11 +3916,11 @@ class T_Scan(unittest.TestCase):
num_grad.gx[max_err_pos])) num_grad.gx[max_err_pos]))
def test_grad_numeric_shared(self): def test_grad_numeric_shared(self):
shared_var = theano.shared(numpy.float32(1.)) shared_var = theano.shared(np.float32(1.))
def inner_fn(): def inner_fn():
return [], OrderedDict( return [], OrderedDict(
[(shared_var, shared_var + numpy.float32(1.))]) [(shared_var, shared_var + np.float32(1.))])
_, updates = theano.scan(inner_fn, _, updates = theano.scan(inner_fn,
n_steps=10, n_steps=10,
truncate_gradient=-1, truncate_gradient=-1,
...@@ -3940,7 +3940,7 @@ class T_Scan(unittest.TestCase): ...@@ -3940,7 +3940,7 @@ class T_Scan(unittest.TestCase):
n_pars = 1 * 3 + 3 * 3 n_pars = 1 * 3 + 3 * 3
# Allocate big parameter array. # Allocate big parameter array.
pars = theano.shared(numpy.empty(n_pars)) pars = theano.shared(np.empty(n_pars))
# Assign slices. # Assign slices.
W1 = pars[:3].reshape(W1shape) W1 = pars[:3].reshape(W1shape)
...@@ -3983,15 +3983,15 @@ class T_Scan(unittest.TestCase): ...@@ -3983,15 +3983,15 @@ class T_Scan(unittest.TestCase):
Hp = tensor.Rop(d_cost_wrt_pars, pars, p) Hp = tensor.Rop(d_cost_wrt_pars, pars, p)
def test_seq_tap_bug_jeremiah(self): def test_seq_tap_bug_jeremiah(self):
inp = numpy.arange(10).reshape(-1, 1).astype(theano.config.floatX) inp = np.arange(10).reshape(-1, 1).astype(theano.config.floatX)
exp_out = numpy.zeros((10, 1)).astype(theano.config.floatX) exp_out = np.zeros((10, 1)).astype(theano.config.floatX)
exp_out[4:] = inp[:-4] exp_out[4:] = inp[:-4]
def onestep(x, x_tm4): def onestep(x, x_tm4):
return x, x_tm4 return x, x_tm4
seq = tensor.matrix() seq = tensor.matrix()
initial_value = theano.shared(numpy.zeros((4, 1), initial_value = theano.shared(np.zeros((4, 1),
dtype=theano.config.floatX)) dtype=theano.config.floatX))
outputs_info = [OrderedDict( outputs_info = [OrderedDict(
[('initial', initial_value), ('taps', [-4])]), None] [('initial', initial_value), ('taps', [-4])]), None]
...@@ -4000,7 +4000,7 @@ class T_Scan(unittest.TestCase): ...@@ -4000,7 +4000,7 @@ class T_Scan(unittest.TestCase):
outputs_info=outputs_info) outputs_info=outputs_info)
f = theano.function([seq], results[1]) f = theano.function([seq], results[1])
assert numpy.all(exp_out == f(inp)) assert np.all(exp_out == f(inp))
def test_borrow_bug_jeremiah(self): def test_borrow_bug_jeremiah(self):
# This tests two things. The first is a bug occuring when scan wrongly # This tests two things. The first is a bug occuring when scan wrongly
...@@ -4008,29 +4008,29 @@ class T_Scan(unittest.TestCase): ...@@ -4008,29 +4008,29 @@ class T_Scan(unittest.TestCase):
# method will be able to remove the Scan node from the graph in this # method will be able to remove the Scan node from the graph in this
# case. # case.
inp = numpy.arange(10).reshape(-1, 1).astype(theano.config.floatX) inp = np.arange(10).reshape(-1, 1).astype(theano.config.floatX)
exp_out = numpy.zeros((10, 1)).astype(theano.config.floatX) exp_out = np.zeros((10, 1)).astype(theano.config.floatX)
exp_out[4:] = inp[:-4] exp_out[4:] = inp[:-4]
def onestep(x, x_tm4): def onestep(x, x_tm4):
return x, x_tm4 return x, x_tm4
seq = tensor.matrix() seq = tensor.matrix()
initial_value = theano.shared(numpy.zeros((4, 1), initial_value = theano.shared(np.zeros((4, 1),
dtype=theano.config.floatX)) dtype=theano.config.floatX))
outputs_info = [OrderedDict([('initial', initial_value), outputs_info = [OrderedDict([('initial', initial_value),
('taps', [-4])]), None] ('taps', [-4])]), None]
results, _ = theano.scan(fn=onestep, results, _ = theano.scan(fn=onestep,
sequences=seq, sequences=seq,
outputs_info=outputs_info) outputs_info=outputs_info)
sharedvar = theano.shared(numpy.zeros((1, 1), sharedvar = theano.shared(np.zeros((1, 1),
dtype=theano.config.floatX)) dtype=theano.config.floatX))
updates = OrderedDict([(sharedvar, results[0][-1:])]) updates = OrderedDict([(sharedvar, results[0][-1:])])
f = theano.function([seq], results[1], updates=updates) f = theano.function([seq], results[1], updates=updates)
# This fails if scan uses wrongly the borrow flag # This fails if scan uses wrongly the borrow flag
assert numpy.all(exp_out == f(inp)) assert np.all(exp_out == f(inp))
# This fails if Scan's infer_shape() is unable to remove the Scan # This fails if Scan's infer_shape() is unable to remove the Scan
# node from the graph. # node from the graph.
...@@ -4070,9 +4070,9 @@ class T_Scan(unittest.TestCase): ...@@ -4070,9 +4070,9 @@ class T_Scan(unittest.TestCase):
# Compare obtained outputs with expected outputs # Compare obtained outputs with expected outputs
floatX = theano.config.floatX floatX = theano.config.floatX
outputs = fct(numpy.arange(9, dtype=floatX).reshape(3,3)) outputs = fct(np.arange(9, dtype=floatX).reshape(3,3))
states = numpy.array([[0, 1, 2], states = np.array([[0, 1, 2],
[3, 4, 5], [3, 4, 5],
[6, 7, 8], [6, 7, 8],
[9, 12, 15], [9, 12, 15],
...@@ -4144,8 +4144,8 @@ class T_Scan(unittest.TestCase): ...@@ -4144,8 +4144,8 @@ class T_Scan(unittest.TestCase):
f = theano.function([v], gv) f = theano.function([v], gv)
# Ensure the output of the function is valid # Ensure the output of the function is valid
output = f(numpy.random.random(5)) output = f(np.random.random(5))
utt.assert_allclose(output, numpy.ones(5)) utt.assert_allclose(output, np.ones(5))
def test_dot_optimization(self): def test_dot_optimization(self):
A = tensor.matrix('A') A = tensor.matrix('A')
...@@ -4155,10 +4155,10 @@ class T_Scan(unittest.TestCase): ...@@ -4155,10 +4155,10 @@ class T_Scan(unittest.TestCase):
B.dimshuffle(0, 'x', 1)], B.dimshuffle(0, 'x', 1)],
outputs_info=[tensor.zeros_like(A)]) outputs_info=[tensor.zeros_like(A)])
f = theano.function([A, B], S.owner.inputs[0][-1]) f = theano.function([A, B], S.owner.inputs[0][-1])
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
vA = rng.uniform(size=(5, 5)).astype(theano.config.floatX) vA = rng.uniform(size=(5, 5)).astype(theano.config.floatX)
vB = rng.uniform(size=(5, 5)).astype(theano.config.floatX) vB = rng.uniform(size=(5, 5)).astype(theano.config.floatX)
utt.assert_allclose(f(vA, vB), numpy.dot(vA.T, vB)) utt.assert_allclose(f(vA, vB), np.dot(vA.T, vB))
def test_pregreedy_optimizer(self): def test_pregreedy_optimizer(self):
W = tensor.zeros((5, 4)) W = tensor.zeros((5, 4))
...@@ -4171,7 +4171,7 @@ class T_Scan(unittest.TestCase): ...@@ -4171,7 +4171,7 @@ class T_Scan(unittest.TestCase):
lambda x: tensor.dot(tensor.dot(x, W) + bh_t, W.T) + bv_t, lambda x: tensor.dot(tensor.dot(x, W) + bh_t, W.T) + bv_t,
outputs_info=v, outputs_info=v,
n_steps=2) n_steps=2)
theano.function([v], chain)(numpy.zeros((3, 5), theano.function([v], chain)(np.zeros((3, 5),
dtype=theano.config.floatX)) dtype=theano.config.floatX))
def test_savemem_does_not_duplicate_number_of_scan_nodes(self): def test_savemem_does_not_duplicate_number_of_scan_nodes(self):
...@@ -4210,7 +4210,7 @@ class T_Scan(unittest.TestCase): ...@@ -4210,7 +4210,7 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
mode=theano.Mode(linker='py'), mode=theano.Mode(linker='py'),
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = asarrayX(rng.uniform(size=(5,))) v_u = asarrayX(rng.uniform(size=(5,)))
outs = f(v_u, [0, 0, 0], 0) outs = f(v_u, [0, 0, 0], 0)
utt.assert_allclose(outs[0], v_u + 1) utt.assert_allclose(outs[0], v_u + 1)
...@@ -4243,7 +4243,7 @@ class T_Scan(unittest.TestCase): ...@@ -4243,7 +4243,7 @@ class T_Scan(unittest.TestCase):
updates=updates, updates=updates,
mode=theano.Mode(linker='py'), mode=theano.Mode(linker='py'),
allow_input_downcast=True) allow_input_downcast=True)
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_w = asarrayX(rng.uniform()) v_w = asarrayX(rng.uniform())
outs = f(v_w, [0, 0, 0], 0) outs = f(v_w, [0, 0, 0], 0)
utt.assert_allclose(outs[0], v_w + 1) utt.assert_allclose(outs[0], v_w + 1)
...@@ -4252,7 +4252,7 @@ class T_Scan(unittest.TestCase): ...@@ -4252,7 +4252,7 @@ class T_Scan(unittest.TestCase):
utt.assert_allclose(sh.get_value(), v_w + 4) utt.assert_allclose(sh.get_value(), v_w + 4)
def test_grad_bug_disconnected_input(self): def test_grad_bug_disconnected_input(self):
W = theano.shared(numpy.zeros((3, 3)), name='W') W = theano.shared(np.zeros((3, 3)), name='W')
v = theano.tensor.ivector(name='v') v = theano.tensor.ivector(name='v')
y, _ = theano.scan(lambda i, W: W[i], sequences=v, outputs_info=None, non_sequences=W) y, _ = theano.scan(lambda i, W: W[i], sequences=v, outputs_info=None, non_sequences=W)
...@@ -4270,14 +4270,14 @@ class T_Scan(unittest.TestCase): ...@@ -4270,14 +4270,14 @@ class T_Scan(unittest.TestCase):
# theano.printing.debugprint(out) # theano.printing.debugprint(out)
return theano.function([], out)() return theano.function([], out)()
x = theano.shared(numpy.asarray(0., dtype=theano.config.floatX)) x = theano.shared(np.asarray(0., dtype=theano.config.floatX))
utt.assert_allclose(test(x, tensor.sum((x+1)**2), mention_y=False), utt.assert_allclose(test(x, tensor.sum((x+1)**2), mention_y=False),
1.21000003815) 1.21000003815)
utt.assert_allclose(test(x, tensor.sum((x+1)**2), mention_y=True), utt.assert_allclose(test(x, tensor.sum((x+1)**2), mention_y=True),
1.21000003815) 1.21000003815)
def test_grad_find_input(self): def test_grad_find_input(self):
w = theano.shared(numpy.array(0, dtype='float32'), name='w') w = theano.shared(np.array(0, dtype='float32'), name='w')
init = tensor.fscalar('init') init = tensor.fscalar('init')
out, _ = theano.scan( out, _ = theano.scan(
...@@ -4333,7 +4333,7 @@ class T_Scan(unittest.TestCase): ...@@ -4333,7 +4333,7 @@ class T_Scan(unittest.TestCase):
for out in [y1, y2, y3, y4, y5, y6]: for out in [y1, y2, y3, y4, y5, y6]:
# This used to raise an exception # This used to raise an exception
f = theano.function([W, v], out, mode=mode_with_opt) f = theano.function([W, v], out, mode=mode_with_opt)
f(numpy.zeros((3, 3), dtype=theano.config.floatX), [1, 2]) f(np.zeros((3, 3), dtype=theano.config.floatX), [1, 2])
scan_nodes = scan_nodes_from_fct(f) scan_nodes = scan_nodes_from_fct(f)
assert len(scan_nodes) == 1 assert len(scan_nodes) == 1
...@@ -4375,9 +4375,9 @@ class T_Scan(unittest.TestCase): ...@@ -4375,9 +4375,9 @@ class T_Scan(unittest.TestCase):
# This used to raise an exception # This used to raise an exception
f = theano.function([W, v, vv], out, on_unused_input='ignore', f = theano.function([W, v, vv], out, on_unused_input='ignore',
mode=mode_with_opt) mode=mode_with_opt)
f(numpy.zeros((3, 3), theano.config.floatX), f(np.zeros((3, 3), theano.config.floatX),
[1, 2], [1, 2],
numpy.zeros((3, 3), theano.config.floatX)) np.zeros((3, 3), theano.config.floatX))
scan_nodes = scan_nodes_from_fct(f) scan_nodes = scan_nodes_from_fct(f)
assert len(scan_nodes) == 1 assert len(scan_nodes) == 1
...@@ -4413,7 +4413,7 @@ class T_Scan(unittest.TestCase): ...@@ -4413,7 +4413,7 @@ class T_Scan(unittest.TestCase):
result_inner, _ = theano.scan( result_inner, _ = theano.scan(
fn=loss_inner, fn=loss_inner,
outputs_info=tensor.as_tensor_variable( outputs_info=tensor.as_tensor_variable(
numpy.asarray(0, dtype=numpy.float32)), np.asarray(0, dtype=np.float32)),
non_sequences=[W], non_sequences=[W],
n_steps=1, n_steps=1,
) )
...@@ -4422,7 +4422,7 @@ class T_Scan(unittest.TestCase): ...@@ -4422,7 +4422,7 @@ class T_Scan(unittest.TestCase):
result_outer, _ = theano.scan( result_outer, _ = theano.scan(
fn=loss_outer, fn=loss_outer,
outputs_info=tensor.as_tensor_variable( outputs_info=tensor.as_tensor_variable(
numpy.asarray(0, dtype=numpy.float32)), np.asarray(0, dtype=np.float32)),
non_sequences=[W], non_sequences=[W],
n_steps=n_steps, n_steps=n_steps,
return_list=True, return_list=True,
...@@ -4432,14 +4432,14 @@ class T_Scan(unittest.TestCase): ...@@ -4432,14 +4432,14 @@ class T_Scan(unittest.TestCase):
H = theano.gradient.hessian(cost, W) H = theano.gradient.hessian(cost, W)
print(".", file=sys.stderr) print(".", file=sys.stderr)
f = theano.function([W, n_steps], H) f = theano.function([W, n_steps], H)
f(numpy.ones((8,), dtype='float32'), 1) f(np.ones((8,), dtype='float32'), 1)
def test_strict_mode(self): def test_strict_mode(self):
n = 10 n = 10
w = numpy.array([[-1, 2], [3, -4]]).astype(theano.config.floatX) w = np.array([[-1, 2], [3, -4]]).astype(theano.config.floatX)
w_ = theano.shared(w) w_ = theano.shared(w)
x0 = numpy.array([1, 2]).astype(theano.config.floatX) x0 = np.array([1, 2]).astype(theano.config.floatX)
x0_ = tensor.vector(name='x0', dtype=theano.config.floatX) x0_ = tensor.vector(name='x0', dtype=theano.config.floatX)
def _scan_loose(x): def _scan_loose(x):
...@@ -4474,9 +4474,9 @@ class T_Scan(unittest.TestCase): ...@@ -4474,9 +4474,9 @@ class T_Scan(unittest.TestCase):
def test_strict_mode_ex(self): def test_strict_mode_ex(self):
n = 10 n = 10
w = numpy.array([[-1, 2], [3, -4]]).astype(theano.config.floatX) w = np.array([[-1, 2], [3, -4]]).astype(theano.config.floatX)
w_ = theano.shared(w) w_ = theano.shared(w)
x0 = numpy.array([1, 2]).astype(theano.config.floatX) x0 = np.array([1, 2]).astype(theano.config.floatX)
x0_ = tensor.vector(name='x0', dtype=theano.config.floatX) x0_ = tensor.vector(name='x0', dtype=theano.config.floatX)
def _scan_loose(x): def _scan_loose(x):
...@@ -4497,7 +4497,7 @@ class T_Scan(unittest.TestCase): ...@@ -4497,7 +4497,7 @@ class T_Scan(unittest.TestCase):
# Build a MonitorMode that counts how many values are greater than 10 # Build a MonitorMode that counts how many values are greater than 10
def detect_large_outputs(i, node, fn): def detect_large_outputs(i, node, fn):
for output in fn.outputs: for output in fn.outputs:
if isinstance(output[0], numpy.ndarray): if isinstance(output[0], np.ndarray):
detect_large_outputs.large_count += (output[0] > 10).sum() detect_large_outputs.large_count += (output[0] > 10).sum()
detect_large_outputs.large_count = 0 detect_large_outputs.large_count = 0
...@@ -4516,7 +4516,7 @@ class T_Scan(unittest.TestCase): ...@@ -4516,7 +4516,7 @@ class T_Scan(unittest.TestCase):
f = theano.function(inputs=[A, k], f = theano.function(inputs=[A, k],
outputs=final_result, outputs=final_result,
updates=updates) updates=updates)
f(numpy.asarray([2, 3, .1, 0, 1], dtype=theano.config.floatX), 4) f(np.asarray([2, 3, .1, 0, 1], dtype=theano.config.floatX), 4)
# There should be 3 outputs greater than 10: prior_result[0] at step 3, # There should be 3 outputs greater than 10: prior_result[0] at step 3,
# and prior_result[1] at steps 2 and 3. # and prior_result[1] at steps 2 and 3.
...@@ -4574,19 +4574,19 @@ class ScanGpuTests: ...@@ -4574,19 +4574,19 @@ class ScanGpuTests:
mode=self.mode_with_gpu) mode=self.mode_with_gpu)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
W = rng.uniform() W = rng.uniform()
W_in = rng.uniform() W_in = rng.uniform()
v_u = numpy.asarray(v_u, dtype='float32') v_u = np.asarray(v_u, dtype='float32')
v_x0 = numpy.asarray(v_x0, dtype='float32') v_x0 = np.asarray(v_x0, dtype='float32')
W = numpy.asarray(W, dtype='float32') W = np.asarray(W, dtype='float32')
W_in = numpy.asarray(W_in, dtype='float32') W_in = np.asarray(W_in, dtype='float32')
# compute the output in numpy # compute the output in numpy
v_out = numpy.zeros((4,)) v_out = np.zeros((4,))
v_out[0] = v_u[0] * W_in + v_x0 * W v_out[0] = v_u[0] * W_in + v_x0 * W
for step in xrange(1, 4): for step in xrange(1, 4):
v_out[step] = v_u[step] * W_in + v_out[step - 1] * W v_out[step] = v_u[step] * W_in + v_out[step - 1] * W
...@@ -4646,14 +4646,14 @@ class ScanGpuTests: ...@@ -4646,14 +4646,14 @@ class ScanGpuTests:
mode=self.mode_with_gpu) mode=self.mode_with_gpu)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
W = rng.uniform() W = rng.uniform()
W_in = rng.uniform() W_in = rng.uniform()
# compute the output in numpy # compute the output in numpy
v_out = numpy.zeros((4,)) v_out = np.zeros((4,))
v_out[0] = v_u[0] * W_in + v_x0 * W v_out[0] = v_u[0] * W_in + v_x0 * W
for step in xrange(1, 4): for step in xrange(1, 4):
v_out[step] = v_u[step] * W_in + v_out[step - 1] * W v_out[step] = v_u[step] * W_in + v_out[step - 1] * W
...@@ -4708,20 +4708,20 @@ class ScanGpuTests: ...@@ -4708,20 +4708,20 @@ class ScanGpuTests:
mode=self.mode_with_gpu) mode=self.mode_with_gpu)
# get random initial values # get random initial values
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_u = rng.uniform(size=(4,), low=-5., high=5.) v_u = rng.uniform(size=(4,), low=-5., high=5.)
v_x0 = rng.uniform() v_x0 = rng.uniform()
W = rng.uniform() W = rng.uniform()
W_in = rng.uniform() W_in = rng.uniform()
# compute the output in numpy # compute the output in numpy
v_out1 = numpy.zeros((4,)) v_out1 = np.zeros((4,))
v_out2 = numpy.zeros((4,), dtype='int64') v_out2 = np.zeros((4,), dtype='int64')
v_out1[0] = v_u[0] * W_in + v_x0 * W v_out1[0] = v_u[0] * W_in + v_x0 * W
v_out2[0] = v_u[0] + v_x0 v_out2[0] = v_u[0] + v_x0
for step in xrange(1, 4): for step in xrange(1, 4):
v_out1[step] = v_u[step] * W_in + v_out1[step - 1] * W v_out1[step] = v_u[step] * W_in + v_out1[step - 1] * W
v_out2[step] = numpy.int64(v_u[step] + v_out1[step - 1]) v_out2[step] = np.int64(v_u[step] + v_out1[step - 1])
theano_out1, theano_out2 = f2(v_u, v_x0, W_in, W) theano_out1, theano_out2 = f2(v_u, v_x0, W_in, W)
utt.assert_allclose(theano_out1, v_out1) utt.assert_allclose(theano_out1, v_out1)
...@@ -4735,8 +4735,8 @@ class ScanGpuTests: ...@@ -4735,8 +4735,8 @@ class ScanGpuTests:
assert self.is_scan_on_gpu(scan_node) assert self.is_scan_on_gpu(scan_node)
def test_gibbs_chain(self): def test_gibbs_chain(self):
rng = numpy.random.RandomState(utt.fetch_seed()) rng = np.random.RandomState(utt.fetch_seed())
v_vsample = numpy.array(rng.binomial(1, .5, size=(3, 20),), v_vsample = np.array(rng.binomial(1, .5, size=(3, 20),),
dtype='float32') dtype='float32')
vsample = theano.shared(v_vsample) vsample = theano.shared(v_vsample)
trng = theano.sandbox.rng_mrg.MRG_RandomStreams( trng = theano.sandbox.rng_mrg.MRG_RandomStreams(
...@@ -4788,11 +4788,11 @@ class ScanGpuTests: ...@@ -4788,11 +4788,11 @@ class ScanGpuTests:
# Initialize the network parameters # Initialize the network parameters
floatX = theano.config.floatX floatX = theano.config.floatX
U = theano.shared(numpy.zeros((n_in, n_hid), dtype="float32"), U = theano.shared(np.zeros((n_in, n_hid), dtype="float32"),
name='W_xin_to_l1') name='W_xin_to_l1')
V = theano.shared(numpy.zeros((n_hid, n_hid), dtype="float32"), V = theano.shared(np.zeros((n_hid, n_hid), dtype="float32"),
name='W_l1_to_l1') name='W_l1_to_l1')
W = theano.shared(numpy.zeros((n_hid, n_out), dtype="float32"), W = theano.shared(np.zeros((n_hid, n_out), dtype="float32"),
name='W_l1_to_l2') name='W_l1_to_l2')
nparams = [U, V, W] nparams = [U, V, W]
...@@ -4802,7 +4802,7 @@ class ScanGpuTests: ...@@ -4802,7 +4802,7 @@ class ScanGpuTests:
def scan_l(baseline, last_step): def scan_l(baseline, last_step):
return baseline + tensor.dot(last_step, V) return baseline + tensor.dot(last_step, V)
zero_output = tensor.alloc(numpy.asarray(0., dtype="float32"), zero_output = tensor.alloc(np.asarray(0., dtype="float32"),
mb_size, n_hid) mb_size, n_hid)
l1_out, _ = theano.scan(scan_l, sequences=[l1_base], l1_out, _ = theano.scan(scan_l, sequences=[l1_base],
...@@ -4833,9 +4833,9 @@ class ScanGpuTests: ...@@ -4833,9 +4833,9 @@ class ScanGpuTests:
assert len(grad_scan_node.outputs) == 2, len(grad_scan_node.outputs) assert len(grad_scan_node.outputs) == 2, len(grad_scan_node.outputs)
# Call the theano function to ensure the absence of a memory error # Call the theano function to ensure the absence of a memory error
feval_backprop(numpy.zeros((mb_length, mb_size, n_in), feval_backprop(np.zeros((mb_length, mb_size, n_in),
dtype="float32"), dtype="float32"),
numpy.zeros((mb_length, mb_size, n_out), np.zeros((mb_length, mb_size, n_out),
dtype="float32")) dtype="float32"))
def test_memory_reuse_gpudimshuffle(self): def test_memory_reuse_gpudimshuffle(self):
...@@ -4864,11 +4864,11 @@ class ScanGpuTests: ...@@ -4864,11 +4864,11 @@ class ScanGpuTests:
fct = theano.function([input1, init], [out1, out2], fct = theano.function([input1, init], [out1, out2],
mode=self.mode_with_gpu) mode=self.mode_with_gpu)
output = fct(numpy.ones((2, 1, 1), dtype="float32"), output = fct(np.ones((2, 1, 1), dtype="float32"),
numpy.ones((1, 1, 1), dtype="float32")) np.ones((1, 1, 1), dtype="float32"))
expected_output = (numpy.array([2, 4], dtype="float32"), expected_output = (np.array([2, 4], dtype="float32"),
numpy.array([3, 7], dtype="float32")) np.array([3, 7], dtype="float32"))
utt.assert_allclose(output, expected_output) utt.assert_allclose(output, expected_output)
...@@ -4985,7 +4985,7 @@ def test_speed(): ...@@ -4985,7 +4985,7 @@ def test_speed():
if not theano.config.cxx: if not theano.config.cxx:
raise SkipTest("G++ not available, so we need to skip this test.") raise SkipTest("G++ not available, so we need to skip this test.")
r = numpy.arange(10000).astype(theano.config.floatX).reshape(1000, 10) r = np.arange(10000).astype(theano.config.floatX).reshape(1000, 10)
t0 = time.time() t0 = time.time()
for i in xrange(1, 1000): for i in xrange(1, 1000):
...@@ -4993,7 +4993,7 @@ def test_speed(): ...@@ -4993,7 +4993,7 @@ def test_speed():
t1 = time.time() t1 = time.time()
print('python', t1 - t0) print('python', t1 - t0)
r = numpy.arange(10000).astype(theano.config.floatX).reshape(1000, 10) r = np.arange(10000).astype(theano.config.floatX).reshape(1000, 10)
t0 = time.time() t0 = time.time()
r_i = iter(r[1:]) r_i = iter(r[1:])
r_ii = iter(r[:-1]) r_ii = iter(r[:-1])
...@@ -5015,7 +5015,7 @@ def test_speed(): ...@@ -5015,7 +5015,7 @@ def test_speed():
print('python with builtin iterator', t1 - t0) print('python with builtin iterator', t1 - t0)
if 1: if 1:
r = numpy.arange(10000).astype(theano.config.floatX).reshape(1000, 10) r = np.arange(10000).astype(theano.config.floatX).reshape(1000, 10)
s_r = tensor.matrix() s_r = tensor.matrix()
s_y, updates = theano.scan(fn=lambda ri, rii: ri + rii, s_y, updates = theano.scan(fn=lambda ri, rii: ri + rii,
sequences=[s_r[1:]], sequences=[s_r[1:]],
...@@ -5030,9 +5030,9 @@ def test_speed(): ...@@ -5030,9 +5030,9 @@ def test_speed():
print('theano (scan, cvm)', t3 - t2) print('theano (scan, cvm)', t3 - t2)
if 1: if 1:
r = numpy.arange(10000).astype(theano.config.floatX).reshape(-1, 10) r = np.arange(10000).astype(theano.config.floatX).reshape(-1, 10)
shared_r = theano.shared(r) shared_r = theano.shared(r)
s_i = theano.shared(numpy.array(1)) s_i = theano.shared(np.array(1))
s_rinc = tensor.inc_subtensor(shared_r[s_i], shared_r[s_i - 1], s_rinc = tensor.inc_subtensor(shared_r[s_i], shared_r[s_i - 1],
tolerate_inplace_aliasing=True) tolerate_inplace_aliasing=True)
# theano.printing.debugprint(s_rinc) # theano.printing.debugprint(s_rinc)
...@@ -5075,18 +5075,18 @@ def test_speed_rnn(): ...@@ -5075,18 +5075,18 @@ def test_speed_rnn():
L = 10000 L = 10000
N = 50 N = 50
numpy.random.seed(2523452) np.random.seed(2523452)
r = numpy.arange(L * N).astype(theano.config.floatX).reshape(L, N) r = np.arange(L * N).astype(theano.config.floatX).reshape(L, N)
w = numpy.random.randn(N, N).astype(theano.config.floatX) w = np.random.randn(N, N).astype(theano.config.floatX)
t0 = time.time() t0 = time.time()
for i in xrange(1, L): for i in xrange(1, L):
r[i] = numpy.tanh(numpy.dot(r[i - 1], w)) r[i] = np.tanh(np.dot(r[i - 1], w))
t1 = time.time() t1 = time.time()
print('python', t1 - t0) print('python', t1 - t0)
if 1: if 1:
r = numpy.arange(L * N).astype(theano.config.floatX).reshape(L, N) r = np.arange(L * N).astype(theano.config.floatX).reshape(L, N)
s_r = tensor.matrix() s_r = tensor.matrix()
s_y, updates = theano.scan( s_y, updates = theano.scan(
fn=lambda ri, rii: tensor.tanh(tensor.dot(rii, w)), fn=lambda ri, rii: tensor.tanh(tensor.dot(rii, w)),
...@@ -5102,7 +5102,7 @@ def test_speed_rnn(): ...@@ -5102,7 +5102,7 @@ def test_speed_rnn():
print('theano (scan, cvm)', t3 - t2) print('theano (scan, cvm)', t3 - t2)
if 1: if 1:
r = numpy.arange(L * N).astype(theano.config.floatX).reshape(L, N) r = np.arange(L * N).astype(theano.config.floatX).reshape(L, N)
s_w = theano.shared(w) s_w = theano.shared(w)
shared_r = theano.shared(r) shared_r = theano.shared(r)
s_i = theano.scalar.sharedvar.shared(1) s_i = theano.scalar.sharedvar.shared(1)
...@@ -5154,18 +5154,18 @@ def test_speed_batchrnn(): ...@@ -5154,18 +5154,18 @@ def test_speed_batchrnn():
B = 50 B = 50
N = 400 N = 400
numpy.random.seed(2523452) np.random.seed(2523452)
r = numpy.arange(B * L * N).astype(theano.config.floatX).reshape(L, B, N) r = np.arange(B * L * N).astype(theano.config.floatX).reshape(L, B, N)
w = numpy.random.randn(N, N).astype(theano.config.floatX) w = np.random.randn(N, N).astype(theano.config.floatX)
t0 = time.time() t0 = time.time()
for i in xrange(1, L): for i in xrange(1, L):
r[i] = numpy.tanh(numpy.dot(r[i - 1], w)) r[i] = np.tanh(np.dot(r[i - 1], w))
t1 = time.time() t1 = time.time()
print('python', t1 - t0) print('python', t1 - t0)
if 1: if 1:
r = numpy.arange(B * L * N).astype( r = np.arange(B * L * N).astype(
theano.config.floatX).reshape(L, B, N) theano.config.floatX).reshape(L, B, N)
s_w = theano.shared(w) s_w = theano.shared(w)
shared_r = theano.shared(r) shared_r = theano.shared(r)
...@@ -5328,9 +5328,9 @@ def test_compute_test_value(): ...@@ -5328,9 +5328,9 @@ def test_compute_test_value():
theano.config.compute_test_value = 'raise' theano.config.compute_test_value = 'raise'
try: try:
x = tensor.vector('x') x = tensor.vector('x')
xv = numpy.ones(3, dtype=theano.config.floatX) xv = np.ones(3, dtype=theano.config.floatX)
x.tag.test_value = xv x.tag.test_value = xv
y = theano.shared(numpy.arange(3, dtype=theano.config.floatX), y = theano.shared(np.arange(3, dtype=theano.config.floatX),
name='y') name='y')
z, updates = theano.scan( z, updates = theano.scan(
fn=lambda u, v: u + v, fn=lambda u, v: u + v,
...@@ -5351,10 +5351,10 @@ def test_compute_test_value_nonseq(): ...@@ -5351,10 +5351,10 @@ def test_compute_test_value_nonseq():
theano.config.compute_test_value = 'raise' theano.config.compute_test_value = 'raise'
try: try:
x = tensor.vector('x') x = tensor.vector('x')
xv = numpy.ones(3, dtype=theano.config.floatX) xv = np.ones(3, dtype=theano.config.floatX)
x.tag.test_value = xv x.tag.test_value = xv
y = theano.shared( y = theano.shared(
numpy.arange(9, dtype=theano.config.floatX).reshape(3, 3), np.arange(9, dtype=theano.config.floatX).reshape(3, 3),
name='y') name='y')
z, updates = theano.scan( z, updates = theano.scan(
fn=lambda u, v: u + v, fn=lambda u, v: u + v,
...@@ -5373,7 +5373,7 @@ def test_compute_test_value_nonseq(): ...@@ -5373,7 +5373,7 @@ def test_compute_test_value_nonseq():
def test_compute_test_value_grad(): def test_compute_test_value_grad():
# Test case originally reported by Bitton Tenessi # Test case originally reported by Bitton Tenessi
# https://groups.google.com/d/msg/theano-users/fAP3i2CbskQ/3OgBf4yjqiQJ # https://groups.google.com/d/msg/theano-users/fAP3i2CbskQ/3OgBf4yjqiQJ
WEIGHT = numpy.array([1, 2, 1, 3, 4, 1, 5, 6, 1, 7, 8, 1], WEIGHT = np.array([1, 2, 1, 3, 4, 1, 5, 6, 1, 7, 8, 1],
dtype='float32') dtype='float32')
old_compute_test_val = theano.config.compute_test_value old_compute_test_val = theano.config.compute_test_value
...@@ -5387,13 +5387,13 @@ def test_compute_test_value_grad(): ...@@ -5387,13 +5387,13 @@ def test_compute_test_value_grad():
W = W_flat.reshape((2, 2, 3)) W = W_flat.reshape((2, 2, 3))
outputs_mi = tensor.as_tensor_variable( outputs_mi = tensor.as_tensor_variable(
numpy.asarray(0, dtype='float32')) np.asarray(0, dtype='float32'))
outputs_mi.tag.test_value = numpy.asarray(0, dtype='float32') outputs_mi.tag.test_value = np.asarray(0, dtype='float32')
def loss_mi(mi, sum_mi, W): def loss_mi(mi, sum_mi, W):
outputs_ti = tensor.as_tensor_variable( outputs_ti = tensor.as_tensor_variable(
numpy.asarray(0, dtype='float32')) np.asarray(0, dtype='float32'))
outputs_ti.tag.test_value = numpy.asarray(0, dtype='float32') outputs_ti.tag.test_value = np.asarray(0, dtype='float32')
def loss_ti(ti, sum_ti, mi, W): def loss_ti(ti, sum_ti, mi, W):
return W.sum().sum().sum() + sum_ti return W.sum().sum().sum() + sum_ti
...@@ -5430,10 +5430,10 @@ def test_compute_test_value_grad_cast(): ...@@ -5430,10 +5430,10 @@ def test_compute_test_value_grad_cast():
theano.config.compute_test_value = 'raise' theano.config.compute_test_value = 'raise'
try: try:
h = tensor.matrix('h') h = tensor.matrix('h')
h.tag.test_value = numpy.array([[1, 2, 3, 4], [5, 6, 7, 8]], h.tag.test_value = np.array([[1, 2, 3, 4], [5, 6, 7, 8]],
dtype=floatX) dtype=floatX)
w = theano.shared(numpy.random.randn(4, 3).astype(floatX), name='w') w = theano.shared(np.random.randn(4, 3).astype(floatX), name='w')
outputs, _ = theano.scan(lambda i, h, w: (theano.dot(h[i], w), i), outputs, _ = theano.scan(lambda i, h, w: (theano.dot(h[i], w), i),
outputs_info=[None, 0], non_sequences=[h, w], outputs_info=[None, 0], non_sequences=[h, w],
...@@ -5473,10 +5473,10 @@ def test_outputs_taps_check(): ...@@ -5473,10 +5473,10 @@ def test_outputs_taps_check():
def test_default_value_broadcasted(): def test_default_value_broadcasted():
def floatx(X): def floatx(X):
return numpy.asarray(X, dtype=theano.config.floatX) return np.asarray(X, dtype=theano.config.floatX)
def init_weights(shape, name): def init_weights(shape, name):
return theano.shared(floatx(numpy.random.randn(*shape) * 0.1), name) return theano.shared(floatx(np.random.randn(*shape) * 0.1), name)
X = theano.tensor.matrix('X') X = theano.tensor.matrix('X')
in_size = 2 in_size = 2
...@@ -5494,14 +5494,14 @@ def test_default_value_broadcasted(): ...@@ -5494,14 +5494,14 @@ def test_default_value_broadcasted():
gW_x = theano.tensor.grad(cost, W_x) gW_x = theano.tensor.grad(cost, W_x)
updates = [(W_x, W_x - 0.1 * gW_x)] updates = [(W_x, W_x - 0.1 * gW_x)]
f = theano.function([X], outputs=cost, updates=updates) f = theano.function([X], outputs=cost, updates=updates)
f(numpy.random.rand(10, in_size).astype(X.dtype)) f(np.random.rand(10, in_size).astype(X.dtype))
class TestInconsistentBroadcast(unittest.TestCase): class TestInconsistentBroadcast(unittest.TestCase):
def test_raise_error(self): def test_raise_error(self):
x = tensor.tensor3() x = tensor.tensor3()
initial_x = tensor.constant(numpy.zeros((1, 10))) initial_x = tensor.constant(np.zeros((1, 10)))
y, updates = theano.scan(fn=lambda x, prev_x: x + prev_x, y, updates = theano.scan(fn=lambda x, prev_x: x + prev_x,
sequences=x, sequences=x,
outputs_info=[dict(initial=initial_x)]) outputs_info=[dict(initial=initial_x)])
......
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