Ejemplo n.º 1
0
    def test_default_updates_multiple(self):
        x = shared(0)
        y = shared(1)

        x.default_update = x - 1
        y.default_update = y + 1

        f1 = pfunc([], [x, y])
        f1()
        assert x.get_value() == -1
        assert y.get_value() == 2

        f2 = pfunc([], [x, y], updates=[(x, (x - 2))], no_default_updates=[y])
        f2()
        assert x.get_value() == -3
        assert y.get_value() == 2

        f3 = pfunc([], [x, y], updates=[(x, (x - 2))], no_default_updates=True)
        f3()
        assert x.get_value() == -5
        assert y.get_value() == 2

        f4 = pfunc([], [x, y], updates=[(y, (y - 2))])
        f4()
        assert x.get_value() == -6
        assert y.get_value() == 0
Ejemplo n.º 2
0
    def test_doc(self):
        """Ensure the code given in pfunc.txt works as expected"""

        # Example #1.
        a = lscalar()
        b = shared(1)
        f1 = pfunc([a], (a + b))
        f2 = pfunc([In(a, value=44)], a + b, updates={b: b + 1})
        self.assertTrue(b.get_value() == 1)
        self.assertTrue(f1(3) == 4)
        self.assertTrue(f2(3) == 4)
        self.assertTrue(b.get_value() == 2)
        self.assertTrue(f1(3) == 5)
        b.set_value(0)
        self.assertTrue(f1(3) == 3)

        # Example #2.
        a = tensor.lscalar()
        b = shared(7)
        f1 = pfunc([a], a + b)
        f2 = pfunc([a], a * b)
        self.assertTrue(f1(5) == 12)
        b.set_value(8)
        self.assertTrue(f1(5) == 13)
        self.assertTrue(f2(4) == 32)
Ejemplo n.º 3
0
    def test_no_default_updates(self):
        x = shared(0)
        y = shared(1)
        x.default_update = x + 2

        # Test that the default update is taken into account in the right cases
        f1 = pfunc([], [x], no_default_updates=True)
        f1()
        assert x.get_value() == 0

        f2 = pfunc([], [x], no_default_updates=[x])
        f2()
        assert x.get_value() == 0

        f3 = pfunc([], [x], no_default_updates=[x, y])
        f3()
        assert x.get_value() == 0

        f4 = pfunc([], [x], no_default_updates=[y])
        f4()
        assert x.get_value() == 2

        f5 = pfunc([], [x], no_default_updates=[])
        f5()
        assert x.get_value() == 4

        f5 = pfunc([], [x], no_default_updates=False)
        f5()
        assert x.get_value() == 6

        self.assertRaises(TypeError, pfunc, [], [x], no_default_updates=(x))
        self.assertRaises(TypeError, pfunc, [], [x], no_default_updates=x)
        self.assertRaises(TypeError,
                          pfunc, [], [x],
                          no_default_updates='canard')

        # Mix explicit updates and no_default_updates
        g1 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=True)
        g1()
        assert x.get_value() == 5

        g2 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[x])
        g2()
        assert x.get_value() == 4

        g3 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[x, y])
        g3()
        assert x.get_value() == 3

        g4 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[y])
        g4()
        assert x.get_value() == 2

        g5 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[])
        g5()
        assert x.get_value() == 1

        g5 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=False)
        g5()
        assert x.get_value() == 0
Ejemplo n.º 4
0
    def test_doc(self):
        # Ensure the code given in pfunc.txt works as expected

        # Example #1.
        a = lscalar()
        b = shared(1)
        f1 = pfunc([a], (a + b))
        f2 = pfunc([In(a, value=44)], a + b, updates={b: b + 1})
        assert b.get_value() == 1
        assert f1(3) == 4
        assert f2(3) == 4
        assert b.get_value() == 2
        assert f1(3) == 5
        b.set_value(0)
        assert f1(3) == 3

        # Example #2.
        a = tensor.lscalar()
        b = shared(7)
        f1 = pfunc([a], a + b)
        f2 = pfunc([a], a * b)
        assert f1(5) == 12
        b.set_value(8)
        assert f1(5) == 13
        assert f2(4) == 32
Ejemplo n.º 5
0
    def test_default_updates_multiple(self):
        x = shared(0)
        y = shared(1)

        x.default_update = x - 1
        y.default_update = y + 1

        f1 = pfunc([], [x, y])
        f1()
        assert x.get_value() == -1
        assert y.get_value() == 2

        f2 = pfunc([], [x, y], updates=[(x, (x - 2))], no_default_updates=[y])
        f2()
        assert x.get_value() == -3
        assert y.get_value() == 2

        f3 = pfunc([], [x, y], updates=[(x, (x - 2))], no_default_updates=True)
        f3()
        assert x.get_value() == -5
        assert y.get_value() == 2

        f4 = pfunc([], [x, y], updates=[(y, (y - 2))])
        f4()
        assert x.get_value() == -6
        assert y.get_value() == 0
Ejemplo n.º 6
0
    def test_doc(self):
        # Ensure the code given in pfunc.txt works as expected

        # Example #1.
        a = lscalar()
        b = shared(1)
        f1 = pfunc([a], (a + b))
        f2 = pfunc([In(a, value=44)], a + b, updates={b: b + 1})
        self.assertTrue(b.get_value() == 1)
        self.assertTrue(f1(3) == 4)
        self.assertTrue(f2(3) == 4)
        self.assertTrue(b.get_value() == 2)
        self.assertTrue(f1(3) == 5)
        b.set_value(0)
        self.assertTrue(f1(3) == 3)

        # Example #2.
        a = tensor.lscalar()
        b = shared(7)
        f1 = pfunc([a], a + b)
        f2 = pfunc([a], a * b)
        self.assertTrue(f1(5) == 12)
        b.set_value(8)
        self.assertTrue(f1(5) == 13)
        self.assertTrue(f2(4) == 32)
Ejemplo n.º 7
0
    def test_no_default_updates(self):
        x = shared(0)
        y = shared(1)
        x.default_update = x + 2

        # Test that the default update is taken into account in the right cases
        f1 = pfunc([], [x], no_default_updates=True)
        f1()
        assert x.get_value() == 0

        f2 = pfunc([], [x], no_default_updates=[x])
        f2()
        assert x.get_value() == 0

        f3 = pfunc([], [x], no_default_updates=[x, y])
        f3()
        assert x.get_value() == 0

        f4 = pfunc([], [x], no_default_updates=[y])
        f4()
        assert x.get_value() == 2

        f5 = pfunc([], [x], no_default_updates=[])
        f5()
        assert x.get_value() == 4

        f5 = pfunc([], [x], no_default_updates=False)
        f5()
        assert x.get_value() == 6

        self.assertRaises(TypeError, pfunc, [], [x], no_default_updates=(x))
        self.assertRaises(TypeError, pfunc, [], [x], no_default_updates=x)
        self.assertRaises(TypeError, pfunc, [], [x],
                          no_default_updates='canard')

        # Mix explicit updates and no_default_updates
        g1 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=True)
        g1()
        assert x.get_value() == 5

        g2 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[x])
        g2()
        assert x.get_value() == 4

        g3 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[x, y])
        g3()
        assert x.get_value() == 3

        g4 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[y])
        g4()
        assert x.get_value() == 2

        g5 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=[])
        g5()
        assert x.get_value() == 1

        g5 = pfunc([], [x], updates=[(x, (x - 1))], no_default_updates=False)
        g5()
        assert x.get_value() == 0
Ejemplo n.º 8
0
 def new(cls, input, n_in, n_out, dtype=None, name=None):
     if dtype is None:
         dtype = input.dtype
     if name is None:
         name = cls.__name__
     w = shared(np.zeros((n_in, n_out), dtype=dtype), name='%s.w'%name)
     b = shared(np.zeros((n_out,), dtype=dtype), name='%s.b'%name)
     return cls(input, w, b, params=[w,b])
Ejemplo n.º 9
0
    def test_clone0(self):
        x = shared(np.asarray([4, 4, 4]))
        y = shared(np.asarray([4, 4, 4]))
        z = shared(np.asarray([2, 2, 2]))
        up = pfunc(
            [], [], updates={x: (x * 5), y: ((x * 5) + y), z: (((x * 5) + y) ** z)}
        )

        up()
        assert np.all(x.get_value() == 20)
        assert np.all(y.get_value() == 24)
        assert np.all(z.get_value() == (24 ** 2))
Ejemplo n.º 10
0
    def test_clone0(self):
        x = shared(numpy.asarray([4, 4, 4]))
        y = shared(numpy.asarray([4, 4, 4]))
        z = shared(numpy.asarray([2, 2, 2]))
        up = pfunc([], [], updates={
            x: (x * 5),
            y: ((x * 5) + y),
            z: (((x * 5) + y) ** z)})

        up()
        assert numpy.all(x.get_value() == 20)
        assert numpy.all(y.get_value() == 24)
        assert numpy.all(z.get_value() == (24 ** 2))
Ejemplo n.º 11
0
    def test_shared_mutable(self):
        bval = np.arange(5)
        b = shared(bval)
        b_out = b * 2

        # shared vars copy args.
        assert b.get_value(borrow=True) is not bval
        # so we do this to get at the underlying data
        bval = data_of(b)

        # by default, shared are not mutable unless doing an explicit update
        f = pfunc([], [b_out], mode="FAST_RUN")
        assert (f() == np.arange(5) * 2).all()
        assert np.all(b.get_value(borrow=True) == np.arange(5))

        # using updates, b is now a mutable parameter
        f = pfunc([], [b_out], updates=[(b, b_out)], mode="FAST_RUN")
        assert (f() == (np.arange(5) * 2)).all()
        # because of the update
        assert (b.get_value(borrow=True) == (np.arange(5) * 2)).all()
        assert (bval == (np.arange(5) * 2)).all()  # because of mutable=True

        # do not depend on updates being in-place though!
        bval = np.arange(5)
        b.set_value(bval, borrow=True)
        bval = data_of(b)
        f = pfunc([], [b_out], updates=[(b, (b_out + 3))], mode="FAST_RUN")
        assert (f() == (np.arange(5) * 2)).all()
        # because of the update
        assert (b.get_value(borrow=True) == ((np.arange(5) * 2) + 3)).all()
        # bval got modified to something...
        assert not (bval == np.arange(5)).all()
        # ... but not to b.value !
        assert not (bval == b.get_value(borrow=True)).all()
Ejemplo n.º 12
0
    def test_shared(self):

        # CHECK: two functions (f1 and f2) can share w
        w = shared(numpy.random.rand(2, 2), 'w')
        wval = w.get_value(borrow=False)

        x = dmatrix()
        out1 = w + x
        out2 = w * x
        f1 = pfunc([x], [out1])
        f2 = pfunc([x], [out2])
        xval = numpy.random.rand(2, 2)
        assert numpy.all(f1(xval) == xval + wval)
        assert numpy.all(f2(xval) == xval * wval)

        # CHECK: updating a shared value
        f3 = pfunc([x], out1, updates=[(w, (w - 1))])
        # f3 changes the value of w
        assert numpy.all(f3(xval) == xval + wval)
        # this same value is read by f1
        assert numpy.all(f1(xval) == xval + (wval - 1))

        w.set_value(w.get_value(borrow=True) * 10, borrow=True)
        # this same value is read by f1
        assert numpy.all(f1(xval) == xval + w.get_value(borrow=True))
Ejemplo n.º 13
0
    def test_shared_mutable(self):
        bval = numpy.arange(5)
        b = shared(bval)
        b_out = b * 2

        # shared vars copy args.
        assert b.get_value(borrow=True) is not bval
        # so we do this to get at the underlying data
        bval = data_of(b)

        # by default, shared are not mutable unless doing an explicit update
        f = pfunc([], [b_out], mode='FAST_RUN')
        assert (f() == numpy.arange(5) * 2).all()
        assert numpy.all(b.get_value(borrow=True) == numpy.arange(5))

        # using updates, b is now a mutable parameter
        f = pfunc([], [b_out], updates=[(b, b_out)], mode='FAST_RUN')
        assert (f() == (numpy.arange(5) * 2)).all()
        # because of the update
        assert (b.get_value(borrow=True) == (numpy.arange(5) * 2)).all()
        assert (bval == (numpy.arange(5) * 2)).all()  # because of mutable=True

        # do not depend on updates being in-place though!
        bval = numpy.arange(5)
        b.set_value(bval, borrow=True)
        bval = data_of(b)
        f = pfunc([], [b_out], updates=[(b, (b_out + 3))], mode='FAST_RUN')
        assert (f() == (numpy.arange(5) * 2)).all()
        # because of the update
        assert (b.get_value(borrow=True) == ((numpy.arange(5) * 2) + 3)).all()
        # bval got modified to something...
        assert not (bval == numpy.arange(5)).all()
        # ... but not to b.value !
        assert not (bval == b.get_value(borrow=True)).all()
Ejemplo n.º 14
0
    def test_shared(self):

        # CHECK: two functions (f1 and f2) can share w
        w = shared(np.random.rand(2, 2), "w")
        wval = w.get_value(borrow=False)

        x = dmatrix()
        out1 = w + x
        out2 = w * x
        f1 = pfunc([x], [out1])
        f2 = pfunc([x], [out2])
        xval = np.random.rand(2, 2)
        assert np.all(f1(xval) == xval + wval)
        assert np.all(f2(xval) == xval * wval)

        # CHECK: updating a shared value
        f3 = pfunc([x], out1, updates=[(w, (w - 1))])
        # f3 changes the value of w
        assert np.all(f3(xval) == xval + wval)
        # this same value is read by f1
        assert np.all(f1(xval) == xval + (wval - 1))

        w.set_value(w.get_value(borrow=True) * 10, borrow=True)
        # this same value is read by f1
        assert np.all(f1(xval) == xval + w.get_value(borrow=True))
Ejemplo n.º 15
0
    def test_givens_replaces_shared_variable2(self):
        a = shared(1., 'a')
        a.default_update = a + 3
        c = a + 10
        f = pfunc([], c, givens={a: (a + 10)})

        assert f() == 21
        assert f() == 34
Ejemplo n.º 16
0
 def test_default_scalar_container(self):
     # Similar in spirit to test_default_container, but updating a scalar
     # variable. This is a sanity check for non mutable types.
     x = shared(0.0, "x")
     f = pfunc([], x)
     assert f() == 0
     x.set_value(x.get_value(borrow=True) + 1, borrow=True)
     assert f() == 1
Ejemplo n.º 17
0
 def test_default_scalar_container(self):
     # Similar in spirit to test_default_container, but updating a scalar
     # variable. This is a sanity check for non mutable types.
     x = shared(0.0, 'x')
     f = pfunc([], x)
     assert f() == 0
     x.set_value(x.get_value(borrow=True) + 1, borrow=True)
     assert f() == 1
Ejemplo n.º 18
0
    def test_update_equiv(self):
        # Like test_update_same, but the update expression is simplified until
        # it is found to be equal to the original variable
        a = shared(1.0, "a")
        b = shared(np.ones((2, 3)), "b")

        # See comment in test_update_same about why we try both
        # shared variables.
        f = theano.function([], [], updates=[(a, a), (b, (2 * b - b))])
        g = theano.function([], [], updates=[(a, (a * 2 - a)), (b, b)])

        f()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
        g()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
Ejemplo n.º 19
0
    def test_update_equiv(self):
        # Like test_update_same, but the update expression is simplified until
        # it is found to be equal to the original variable
        a = shared(1., 'a')
        b = shared(numpy.ones((2, 3)), 'b')

        # See comment in test_update_same about why we try both
        # shared variables.
        f = theano.function([], [], updates=[(a, a), (b, (2 * b - b))])
        g = theano.function([], [], updates=[(a, (a * 2 - a)), (b, b)])

        f()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
        g()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
Ejemplo n.º 20
0
    def test_givens_replaces_shared_variable2(self):
        a = shared(1.0, "a")
        a.default_update = a + 3
        c = a + 10
        f = pfunc([], c, givens={a: (a + 10)})

        assert f() == 21
        assert f() == 34
Ejemplo n.º 21
0
    def __init__(self,
                 window_size=HYPERPARAMETERS["WINDOW_SIZE"],
                 vocab_size=vocabulary.wordmap.len,
                 embedding_size=HYPERPARAMETERS["EMBEDDING_SIZE"],
                 hidden_size=HYPERPARAMETERS["HIDDEN_SIZE"],
                 seed=miscglobals.RANDOMSEED):
        """
        Initialize L{Model} parameters.
        """

        self.vocab_size = vocab_size
        self.window_size = window_size
        self.embedding_size = embedding_size
        if LBL:
            self.hidden_size = hidden_size
            self.output_size = self.embedding_size
        else:
            self.hidden_size = hidden_size
            self.output_size = 1

        import numpy
        import hyperparameters

        numpy.random.seed(seed)
        self.embeddings = numpy.asarray(
            (numpy.random.rand(self.vocab_size,
                               HYPERPARAMETERS["EMBEDDING_SIZE"]) - 0.5) * 2 *
            HYPERPARAMETERS["INITIAL_EMBEDDING_RANGE"],
            dtype=floatX)
        if HYPERPARAMETERS["NORMALIZE_EMBEDDINGS"]:
            self.normalize(range(self.vocab_size))
        if LBL:
            self.output_weights = shared(
                numpy.asarray(random_weights(
                    self.input_size,
                    self.output_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.output_biases = shared(
                numpy.asarray(numpy.zeros((1, self.output_size)),
                              dtype=floatX))
            self.score_biases = shared(
                numpy.asarray(numpy.zeros(self.vocab_size), dtype=floatX))
        else:
            self.hidden_weights = shared(
                numpy.asarray(random_weights(
                    self.input_size,
                    self.hidden_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.output_weights = shared(
                numpy.asarray(random_weights(
                    self.hidden_size,
                    self.output_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.hidden_biases = shared(
                numpy.asarray(numpy.zeros((self.hidden_size, )), dtype=floatX))
            self.output_biases = shared(
                numpy.asarray(numpy.zeros((self.output_size, )), dtype=floatX))
Ejemplo n.º 22
0
    def test_givens_replaces_shared_variable(self):
        a = shared(1., 'a')
        a.default_update = a + 3.
        b = tensor.dscalar('b')
        c = a + 10
        f = pfunc([b], c, givens={a: b})

        assert len(f.maker.fgraph.inputs) == 1
        assert len(f.maker.fgraph.outputs) == 1
Ejemplo n.º 23
0
 def test_default_updates_partial_graph(self):
     a = shared(0)
     a.default_update = a + 1  # Increment a each time it is used
     b = 2 * a
     # Use only the tip of the graph, a is not used
     f = pfunc([b], b)
     assert a.get_value() == 0
     f(21)
     assert a.get_value() == 0
Ejemplo n.º 24
0
    def test_update_err_broadcast(self):
        # Test that broadcastable dimensions raise error
        data = numpy.random.rand(10, 10).astype('float32')
        output_var = shared(name="output", value=data)

        # the update_var has type matrix, and the update expression
        # is a broadcasted scalar, and that should be allowed.
        self.assertRaises(TypeError, theano.function, inputs=[], outputs=[],
                          updates={output_var: output_var.sum().dimshuffle('x', 'x')})
Ejemplo n.º 25
0
 def test_default_updates_partial_graph(self):
     a = shared(0)
     a.default_update = a + 1  # Increment a each time it is used
     b = 2 * a
     # Use only the tip of the graph, a is not used
     f = pfunc([b], b)
     assert a.get_value() == 0
     f(21)
     assert a.get_value() == 0
Ejemplo n.º 26
0
 def test_no_shared_as_input(self):
     # Test that shared variables cannot be used as function inputs.
     w_init = np.random.rand(2, 2)
     w = shared(w_init.copy(), "w")
     with pytest.raises(
             TypeError,
             match=r"^Cannot use a shared variable \(w\) as explicit input"
     ):
         pfunc([w], theano.tensor.sum(w * w))
Ejemplo n.º 27
0
    def test_givens_replaces_shared_variable(self):
        a = shared(1.0, "a")
        a.default_update = a + 3.0
        b = tensor.dscalar("b")
        c = a + 10
        f = pfunc([b], c, givens={a: b})

        assert len(f.maker.fgraph.inputs) == 1
        assert len(f.maker.fgraph.outputs) == 1
Ejemplo n.º 28
0
    def test_default_updates_expressions(self):
        x = shared(0)
        y = shared(1)
        a = lscalar("a")

        z = a * x
        x.default_update = x + y

        f1 = pfunc([a], z)
        f1(12)
        assert x.get_value() == 1

        f2 = pfunc([a], z, no_default_updates=True)
        assert f2(7) == 7
        assert x.get_value() == 1

        f3 = pfunc([a], z, no_default_updates=[x])
        assert f3(9) == 9
        assert x.get_value() == 1
Ejemplo n.º 29
0
    def test_default_updates_expressions(self):
        x = shared(0)
        y = shared(1)
        a = lscalar('a')

        z = a * x
        x.default_update = x + y

        f1 = pfunc([a], z)
        f1(12)
        assert x.get_value() == 1

        f2 = pfunc([a], z, no_default_updates=True)
        assert f2(7) == 7
        assert x.get_value() == 1

        f3 = pfunc([a], z, no_default_updates=[x])
        assert f3(9) == 9
        assert x.get_value() == 1
Ejemplo n.º 30
0
 def test_no_shared_as_input(self):
     # Test that shared variables cannot be used as function inputs.
     w_init = np.random.rand(2, 2)
     w = shared(w_init.copy(), "w")
     try:
         pfunc([w], theano.tensor.sum(w * w))
         assert False
     except TypeError as e:
         msg = "Cannot use a shared variable (w) as explicit input"
         if str(e).find(msg) < 0:
             raise
Ejemplo n.º 31
0
 def test_no_shared_as_input(self):
     """Test that shared variables cannot be used as function inputs."""
     w_init = numpy.random.rand(2, 2)
     w = shared(w_init.copy(), 'w')
     try:
         pfunc([w], theano.tensor.sum(w * w))
         assert False
     except TypeError as e:
         msg = 'Cannot use a shared variable (w) as explicit input'
         if str(e).find(msg) < 0:
             raise
Ejemplo n.º 32
0
    def test_update(self):
        """Test update mechanism in different settings."""

        # Simple value assignment.
        x = shared(0)
        assign = pfunc([], [], updates={x: 3})
        assign()
        self.assertTrue(x.get_value() == 3)

        # Basic increment function.
        x.set_value(0)
        inc = pfunc([], [], updates={x: x + 1})
        inc()
        self.assertTrue(x.get_value() == 1)

        # Increment by a constant value.
        x.set_value(-1)
        y = shared(2)
        inc_by_y = pfunc([], [], updates={x: x + y})
        inc_by_y()
        self.assertTrue(x.get_value() == 1)
Ejemplo n.º 33
0
    def test_update(self):
        # Test update mechanism in different settings.

        # Simple value assignment.
        x = shared(0)
        assign = pfunc([], [], updates={x: 3})
        assign()
        assert x.get_value() == 3

        # Basic increment function.
        x.set_value(0)
        inc = pfunc([], [], updates={x: x + 1})
        inc()
        assert x.get_value() == 1

        # Increment by a constant value.
        x.set_value(-1)
        y = shared(2)
        inc_by_y = pfunc([], [], updates={x: x + y})
        inc_by_y()
        assert x.get_value() == 1
Ejemplo n.º 34
0
    def test_default_updates_input(self):
        x = shared(0)
        y = shared(1)
        if theano.configdefaults.python_int_bitwidth() == 32:
            a = iscalar("a")
        else:
            a = lscalar("a")

        x.default_update = y
        y.default_update = y + a

        f1 = pfunc([], x, no_default_updates=True)
        f1()
        assert x.get_value() == 0
        assert y.get_value() == 1

        f2 = pfunc([], x, no_default_updates=[x])
        f2()
        assert x.get_value() == 0
        assert y.get_value() == 1

        f3 = pfunc([], x, no_default_updates=[y])
        f3()
        assert x.get_value() == 1
        assert y.get_value() == 1

        f4 = pfunc([a], x)
        f4(2)
        assert x.get_value() == 1
        assert y.get_value() == 3

        f5 = pfunc([], x, updates={y: (y - 1)})
        f5()
        assert x.get_value() == 3
        assert y.get_value() == 2

        # a is needed as input if y.default_update is used
        with pytest.raises(theano.gof.MissingInputError):
            pfunc([], x)
Ejemplo n.º 35
0
    def test_update_err_broadcast(self):
        # Test that broadcastable dimensions raise error
        data = np.random.rand(10, 10).astype("float32")
        output_var = shared(name="output", value=data)

        # the update_var has type matrix, and the update expression
        # is a broadcasted scalar, and that should be allowed.
        with pytest.raises(TypeError):
            theano.function(
                inputs=[],
                outputs=[],
                updates={output_var: output_var.sum().dimshuffle("x", "x")},
            )
Ejemplo n.º 36
0
    def test_default_updates_chained(self):
        x = shared(2)
        y = shared(1)
        z = shared(-1)

        x.default_update = x - y
        y.default_update = z
        z.default_update = z - 1

        f1 = pfunc([], [x])
        f1()
        assert x.get_value() == 1
        assert y.get_value() == -1
        assert z.get_value() == -2

        f2 = pfunc([], [x, y])
        f2()
        assert x.get_value() == 2
        assert y.get_value() == -2
        assert z.get_value() == -3

        f3 = pfunc([], [y])
        f3()
        assert x.get_value() == 2
        assert y.get_value() == -3
        assert z.get_value() == -4

        f4 = pfunc([], [x, y], no_default_updates=[x])
        f4()
        assert x.get_value() == 2
        assert y.get_value() == -4
        assert z.get_value() == -5

        f5 = pfunc([], [x, y, z], no_default_updates=[z])
        f5()
        assert x.get_value() == 6
        assert y.get_value() == -5
        assert z.get_value() == -5
Ejemplo n.º 37
0
    def test_default_updates_input(self):
        x = shared(0)
        y = shared(1)
        if theano.configdefaults.python_int_bitwidth() == 32:
            a = iscalar('a')
        else:
            a = lscalar('a')

        x.default_update = y
        y.default_update = y + a

        f1 = pfunc([], x, no_default_updates=True)
        f1()
        assert x.get_value() == 0
        assert y.get_value() == 1

        f2 = pfunc([], x, no_default_updates=[x])
        f2()
        assert x.get_value() == 0
        assert y.get_value() == 1

        f3 = pfunc([], x, no_default_updates=[y])
        f3()
        assert x.get_value() == 1
        assert y.get_value() == 1

        f4 = pfunc([a], x)
        f4(2)
        assert x.get_value() == 1
        assert y.get_value() == 3

        f5 = pfunc([], x, updates={y: (y - 1)})
        f5()
        assert x.get_value() == 3
        assert y.get_value() == 2

        # a is needed as input if y.default_update is used
        self.assertRaises(theano.gof.MissingInputError, pfunc, [], x)
Ejemplo n.º 38
0
    def test_default_updates_chained(self):
        x = shared(2)
        y = shared(1)
        z = shared(-1)

        x.default_update = x - y
        y.default_update = z
        z.default_update = z - 1

        f1 = pfunc([], [x])
        f1()
        assert x.get_value() == 1
        assert y.get_value() == -1
        assert z.get_value() == -2

        f2 = pfunc([], [x, y])
        f2()
        assert x.get_value() == 2
        assert y.get_value() == -2
        assert z.get_value() == -3

        f3 = pfunc([], [y])
        f3()
        assert x.get_value() == 2
        assert y.get_value() == -3
        assert z.get_value() == -4

        f4 = pfunc([], [x, y], no_default_updates=[x])
        f4()
        assert x.get_value() == 2
        assert y.get_value() == -4
        assert z.get_value() == -5

        f5 = pfunc([], [x, y, z], no_default_updates=[z])
        f5()
        assert x.get_value() == 6
        assert y.get_value() == -5
        assert z.get_value() == -5
Ejemplo n.º 39
0
    def test_default_container(self):
        # Ensure it is possible to (implicitly) use a shared variable in a
        # function, as a 'state' that can be updated at will.

        rng = numpy.random.RandomState(1827)
        w_init = rng.rand(5)
        w = shared(w_init.copy(), 'w')
        reg = theano.tensor.sum(w * w)
        f = pfunc([], reg)

        assert f() == numpy.sum(w_init * w_init)
        # Change the value of w and ensure the output changes accordingly.
        w.set_value(w.get_value(borrow=True) + 1.0, borrow=True)
        assert f() == numpy.sum((w_init + 1) ** 2)
Ejemplo n.º 40
0
    def test_default_container(self):
        # Ensure it is possible to (implicitly) use a shared variable in a
        # function, as a 'state' that can be updated at will.

        rng = np.random.RandomState(1827)
        w_init = rng.rand(5)
        w = shared(w_init.copy(), "w")
        reg = theano.tensor.sum(w * w)
        f = pfunc([], reg)

        assert f() == np.sum(w_init * w_init)
        # Change the value of w and ensure the output changes accordingly.
        w.set_value(w.get_value(borrow=True) + 1.0, borrow=True)
        assert f() == np.sum((w_init + 1) ** 2)
Ejemplo n.º 41
0
    def test_default_updates(self):
        x = shared(0)
        x.default_update = x + 1

        f = pfunc([], [x])
        f()
        assert x.get_value() == 1

        del x.default_update
        f()
        assert x.get_value() == 2

        g = pfunc([], [x])
        g()
        assert x.get_value() == 2
Ejemplo n.º 42
0
    def test_default_updates(self):
        x = shared(0)
        x.default_update = x + 1

        f = pfunc([], [x])
        f()
        assert x.get_value() == 1

        del x.default_update
        f()
        assert x.get_value() == 2

        g = pfunc([], [x])
        g()
        assert x.get_value() == 2
Ejemplo n.º 43
0
    def test_update_same(self):
        # There was a bug in CVM, triggered when a shared variable
        # was its own update expression.
        a = shared(1., 'a')
        b = shared(numpy.ones((2, 3)), 'b')

        # The order of the variables is not determined, so we try
        # both shared variables.
        # TODO: explain the above comment. By "not determined" does
        # this mean "not deterministic"?
        # This test originally wrote the updates using dictionaries,
        # and iterating over the dictionary was not deterministic.
        # Is that all the comment above meant, or is the CVM intended
        # to add extra non-determinism? Or is the CVM meant to
        # deterministically but arbitrarily pick an order for the updates?
        f = theano.function([], [], updates=[(a, a), (b, (2 * b))])
        g = theano.function([], [], updates=[(a, (a * 2)), (b, b)])

        f()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
        g()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
Ejemplo n.º 44
0
    def test_update_same(self):
        # There was a bug in CVM, triggered when a shared variable
        # was its own update expression.
        a = shared(1.0, "a")
        b = shared(np.ones((2, 3)), "b")

        # The order of the variables is not determined, so we try
        # both shared variables.
        # TODO: explain the above comment. By "not determined" does
        # this mean "not deterministic"?
        # This test originally wrote the updates using dictionaries,
        # and iterating over the dictionary was not deterministic.
        # Is that all the comment above meant, or is the CVM intended
        # to add extra non-determinism? Or is the CVM meant to
        # deterministically but arbitrarily pick an order for the updates?
        f = theano.function([], [], updates=[(a, a), (b, (2 * b))])
        g = theano.function([], [], updates=[(a, (a * 2)), (b, b)])

        f()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
        g()
        assert a.get_value(borrow=True).shape == (), a.get_value()
        assert b.get_value(borrow=True).shape == (2, 3), b.get_value()
Ejemplo n.º 45
0
    def test_givens(self):
        x = shared(0)
        assign = pfunc([], x, givens={x: 3})
        assert assign() == 3
        assert x.get_value(borrow=True) == 0

        y = tensor.ivector()
        f = pfunc([y], (y * x), givens={x: 6})
        assert np.all(f([1, 1, 1]) == [6, 6, 6])
        assert x.get_value() == 0

        z = tensor.ivector()
        c = z * y
        f = pfunc([y], (c + 7), givens={z: theano._asarray([4, 4, 4], dtype="int32")})
        assert np.all(f([1, 1, 1]) == [11, 11, 11])
        assert x.get_value() == 0
Ejemplo n.º 46
0
    def __init__(self, window_size, vocab_size, embedding_size, hidden_size, seed, initial_embeddings, two_hidden_layers):
        """
        Initialize L{Model} parameters.
        """

        self.vocab_size     = vocab_size
        self.window_size    = window_size
        self.embedding_size = embedding_size
        self.two_hidden_layers = two_hidden_layers
        if LBL:
            self.hidden_size    = hidden_size
            self.output_size    = self.embedding_size
        else:
            self.hidden_size    = hidden_size
            self.output_size    = 1

        import numpy
        import hyperparameters

        numpy.random.seed(seed)
        if initial_embeddings is None:
            self.embeddings = numpy.asarray((numpy.random.rand(self.vocab_size, HYPERPARAMETERS["EMBEDDING_SIZE"]) - 0.5)*2 * HYPERPARAMETERS["INITIAL_EMBEDDING_RANGE"], dtype=floatX)
        else:
            assert initial_embeddings.shape == (self.vocab_size, HYPERPARAMETERS["EMBEDDING_SIZE"])
            self.embeddings = copy.copy(initial_embeddings)
        if HYPERPARAMETERS["NORMALIZE_EMBEDDINGS"]: self.normalize(range(self.vocab_size))
        if LBL:
            self.output_weights = shared(numpy.asarray(random_weights(self.input_size, self.output_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]), dtype=floatX))
            self.output_biases = shared(numpy.asarray(numpy.zeros((1, self.output_size)), dtype=floatX))
            self.score_biases = shared(numpy.asarray(numpy.zeros(self.vocab_size), dtype=floatX))
            assert not self.two_hidden_layers
        else:
            self.hidden_weights = shared(numpy.asarray(random_weights(self.input_size, self.hidden_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]), dtype=floatX))
            self.hidden_biases = shared(numpy.asarray(numpy.zeros((self.hidden_size,)), dtype=floatX))
            if self.two_hidden_layers:
                self.hidden2_weights = shared(numpy.asarray(random_weights(self.hidden_size, self.hidden_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]), dtype=floatX))
                self.hidden2_biases = shared(numpy.asarray(numpy.zeros((self.hidden_size,)), dtype=floatX))
            self.output_weights = shared(numpy.asarray(random_weights(self.hidden_size, self.output_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]), dtype=floatX))
            self.output_biases = shared(numpy.asarray(numpy.zeros((self.output_size,)), dtype=floatX))
Ejemplo n.º 47
0
    def test_givens(self):
        x = shared(0)
        assign = pfunc([], x, givens={x: 3})
        assert assign() == 3
        assert x.get_value(borrow=True) == 0

        y = tensor.ivector()
        f = pfunc([y], (y * x), givens={x: 6})
        assert numpy.all(f([1, 1, 1]) == [6, 6, 6])
        assert x.get_value() == 0

        z = tensor.ivector()
        c = z * y
        f = pfunc([y], (c + 7),
                  givens={z: theano._asarray([4, 4, 4], dtype='int32')})
        assert numpy.all(f([1, 1, 1]) == [11, 11, 11])
        assert x.get_value() == 0
Ejemplo n.º 48
0
    def test_param_strict(self):

        a = tensor.dvector()
        b = shared(7)
        out = a + b

        f = pfunc([In(a, strict=False)], [out])
        # works, rand generates float64 by default
        f(numpy.random.rand(8))
        # works, casting is allowed
        f(numpy.array([1, 2, 3, 4], dtype='int32'))

        f = pfunc([In(a, strict=True)], [out])
        try:
            # fails, f expects float64
            f(numpy.array([1, 2, 3, 4], dtype='int32'))
        except TypeError:
            pass
Ejemplo n.º 49
0
    def test_param_strict(self):

        a = tensor.dvector()
        b = shared(7)
        out = a + b

        f = pfunc([In(a, strict=False)], [out])
        # works, rand generates float64 by default
        f(np.random.rand(8))
        # works, casting is allowed
        f(np.array([1, 2, 3, 4], dtype="int32"))

        f = pfunc([In(a, strict=True)], [out])
        try:
            # fails, f expects float64
            f(np.array([1, 2, 3, 4], dtype="int32"))
        except TypeError:
            pass
Ejemplo n.º 50
0
def _shared_uniform(rng, low, high, size, dtype, name=None):
    return shared(theano._asarray(rng.uniform(low=low, high=high, size=size), dtype=dtype), name)
Ejemplo n.º 51
0
def _shared_uniform(rng, low, high, size, dtype, name=None):
    return shared(
        theano._asarray(rng.uniform(low=low, high=high, size=size),
                        dtype=dtype), name)
Ejemplo n.º 52
0
    def __init__(self, window_size, vocab_size, embedding_size, hidden_size,
                 seed, initial_embeddings, two_hidden_layers):
        """
        Initialize L{Model} parameters.
        """

        self.vocab_size = vocab_size
        self.window_size = window_size
        self.embedding_size = embedding_size
        self.two_hidden_layers = two_hidden_layers
        if LBL:
            self.hidden_size = hidden_size
            self.output_size = self.embedding_size
        else:
            self.hidden_size = hidden_size
            self.output_size = 1

        import numpy
        import hyperparameters

        numpy.random.seed(seed)
        if initial_embeddings is None:
            self.embeddings = numpy.asarray(
                (numpy.random.rand(self.vocab_size,
                                   HYPERPARAMETERS["EMBEDDING_SIZE"]) - 0.5) *
                2 * HYPERPARAMETERS["INITIAL_EMBEDDING_RANGE"],
                dtype=floatX)
        else:
            assert initial_embeddings.shape == (
                self.vocab_size, HYPERPARAMETERS["EMBEDDING_SIZE"])
            self.embeddings = copy.copy(initial_embeddings)
        if HYPERPARAMETERS["NORMALIZE_EMBEDDINGS"]:
            self.normalize(range(self.vocab_size))
        if LBL:
            self.output_weights = shared(
                numpy.asarray(random_weights(
                    self.input_size,
                    self.output_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.output_biases = shared(
                numpy.asarray(numpy.zeros((1, self.output_size)),
                              dtype=floatX))
            self.score_biases = shared(
                numpy.asarray(numpy.zeros(self.vocab_size), dtype=floatX))
            assert not self.two_hidden_layers
        else:
            self.hidden_weights = shared(
                numpy.asarray(random_weights(
                    self.input_size,
                    self.hidden_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.hidden_biases = shared(
                numpy.asarray(numpy.zeros((self.hidden_size, )), dtype=floatX))
            if self.two_hidden_layers:
                self.hidden2_weights = shared(
                    numpy.asarray(random_weights(
                        self.hidden_size,
                        self.hidden_size,
                        scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                                  dtype=floatX))
                self.hidden2_biases = shared(
                    numpy.asarray(numpy.zeros((self.hidden_size, )),
                                  dtype=floatX))
            self.output_weights = shared(
                numpy.asarray(random_weights(
                    self.hidden_size,
                    self.output_size,
                    scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]),
                              dtype=floatX))
            self.output_biases = shared(
                numpy.asarray(numpy.zeros((self.output_size, )), dtype=floatX))
Ejemplo n.º 53
0
 def test_duplicate_updates(self):
     x, y = dmatrices('x', 'y')
     z = shared(numpy.ones((2, 3)))
     self.assertRaises(ValueError, theano.function, [x, y], [z],
                       updates=[(z, (z + x + y)), (z, (z - x))])
Ejemplo n.º 54
0
 def test_duplicate_updates(self):
     x, y = dmatrices("x", "y")
     z = shared(np.ones((2, 3)))
     with pytest.raises(ValueError):
         theano.function([x, y], [z], updates=[(z, (z + x + y)), (z, (z - x))])
Ejemplo n.º 55
0
    def __init__(
        self,
        window_size=HYPERPARAMETERS["WINDOW_SIZE"],
        vocab_size=vocabulary.wordmap.len,
        embedding_size=HYPERPARAMETERS["EMBEDDING_SIZE"],
        hidden_size=HYPERPARAMETERS["HIDDEN_SIZE"],
        seed=miscglobals.RANDOMSEED,
    ):
        """
        Initialize L{Model} parameters.
        """

        self.vocab_size = vocab_size
        self.window_size = window_size
        self.embedding_size = embedding_size
        if LBL:
            self.hidden_size = hidden_size
            self.output_size = self.embedding_size
        else:
            self.hidden_size = hidden_size
            self.output_size = 1

        import numpy
        import hyperparameters

        numpy.random.seed(seed)
        self.embeddings = numpy.asarray(
            (numpy.random.rand(self.vocab_size, HYPERPARAMETERS["EMBEDDING_SIZE"]) - 0.5)
            * 2
            * HYPERPARAMETERS["INITIAL_EMBEDDING_RANGE"],
            dtype=floatX,
        )
        if HYPERPARAMETERS["NORMALIZE_EMBEDDINGS"]:
            self.normalize(range(self.vocab_size))
        if LBL:
            self.output_weights = shared(
                numpy.asarray(
                    random_weights(
                        self.input_size, self.output_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]
                    ),
                    dtype=floatX,
                )
            )
            self.output_biases = shared(numpy.asarray(numpy.zeros((1, self.output_size)), dtype=floatX))
            self.score_biases = shared(numpy.asarray(numpy.zeros(self.vocab_size), dtype=floatX))
        else:
            self.hidden_weights = shared(
                numpy.asarray(
                    random_weights(
                        self.input_size, self.hidden_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]
                    ),
                    dtype=floatX,
                )
            )
            self.output_weights = shared(
                numpy.asarray(
                    random_weights(
                        self.hidden_size, self.output_size, scale_by=HYPERPARAMETERS["SCALE_INITIAL_WEIGHTS_BY"]
                    ),
                    dtype=floatX,
                )
            )
            self.hidden_biases = shared(numpy.asarray(numpy.zeros((self.hidden_size,)), dtype=floatX))
            self.output_biases = shared(numpy.asarray(numpy.zeros((self.output_size,)), dtype=floatX))