Python theano.tensor.constant() Examples

def test_mixin_sklearn_params():
    # get_params
    p = Normal(mu=0.0, sigma=1.0)
    params = p.get_params()
    assert len(params) == 2
    assert "mu" in params
    assert "sigma" in params

    # for parameters, set_params should change the value contained
    old_mu = p.get_params()["mu"]
    p.set_params(mu=42.0)
    new_mu = p.get_params()["mu"]
    assert old_mu is new_mu
    assert new_mu.get_value() == 42.0

    # check errors
    p = Normal(mu=T.constant(0.0), sigma=1.0)
    assert_raises(ValueError, p.set_params, mu=1.0) 

def test_csm_unsorted(self):
        """
        Test support for gradients of unsorted inputs.
        """
        sp_types = {'csc': sp.csc_matrix,
                    'csr': sp.csr_matrix}

        for format in ['csr', 'csc', ]:
            for dtype in ['float32', 'float64']:
                x = tensor.tensor(dtype=dtype, broadcastable=(False,))
                y = tensor.ivector()
                z = tensor.ivector()
                s = tensor.ivector()
                # Sparse advanced indexing produces unsorted sparse matrices
                a = sparse_random_inputs(format, (4, 3), out_dtype=dtype,
                                         unsorted_indices=True)[1][0]
                # Make sure it's unsorted
                assert not a.has_sorted_indices
                def my_op(x):
                    y = tensor.constant(a.indices)
                    z = tensor.constant(a.indptr)
                    s = tensor.constant(a.shape)
                    return tensor.sum(
                        dense_from_sparse(CSM(format)(x, y, z, s) * a))
                verify_grad_sparse(my_op, [a.data]) 

def huber_loss(mx, Sx, target, Q, width=1.0, *args, **kwargs):
    '''
        Huber loss
    '''
    if Sx is None:
        # deterministic case
        if mx.ndim == 1:
            mx = mx[None, :]
        delta = mx-target
        Q = tt.constant(Q) if isinstance(Q, np.ndarray) else Q
        deltaQ = delta.dot(Q)
        abs_deltaQ = abs(deltaQ)
        cost = tt.switch(
            abs_deltaQ <= width,
            0.5*deltaQ**2,
            width*(abs_deltaQ - width/2)).sum(-1)
        return cost
    else:
        # stochastic case (moment matching)
        raise NotImplementedError 

def test_fit():
    p1 = Normal(mu=T.constant(0.0), sigma=T.constant(2.0))
    p2 = Normal(mu=T.constant(3.0), sigma=T.constant(2.0))
    p3 = Exponential(inverse_scale=T.constant(0.5))
    g = theano.shared(0.5)
    m = Mixture(components=[p1, p2, p3], weights=[g, g*g])

    X = np.concatenate([st.norm(loc=0.0, scale=2.0).rvs(300, random_state=0),
                        st.norm(loc=3.0, scale=2.0).rvs(100, random_state=1),
                        st.expon(scale=1. / 0.5).rvs(500, random_state=2)])
    X = X.reshape(-1, 1)
    s0 = m.score(X)

    m.fit(X)
    assert np.abs(g.eval() - 1. / 3.) < 0.05
    assert m.score(X) >= s0 

def sample_noise(self, input):
        # get noise_shape
        noise_shape = self.input_shape
        if any(s is None for s in noise_shape):
            noise_shape = input.shape

        # respect shared axes
        if self.shared_axes:
            shared_axes = tuple(a if a >= 0 else a + input.ndim
                                for a in self.shared_axes)
            noise_shape = tuple(1 if a in shared_axes else s
                                for a, s in enumerate(noise_shape))

        one = tt.constant(1)
        retain_prob = one - self.p
        noise = self._srng.binomial(noise_shape, p=retain_prob,
                                    dtype=floatX)

        if self.shared_axes:
            bcast = tuple(bool(s == 1) for s in noise_shape)
            noise = tt.patternbroadcast(noise, bcast)

        return noise 

def print_graph_linker(print_prog=True):
    if 1:
        imap = {None:'-'}
        def blah(i, node, thunk):
            imap[node] = str(i)
            if print_prog:# and node.op.__class__ is T.DimShuffle:
                if False and  node.op == T.DimShuffle((), ['x', 'x'], inplace = True):
                    print(node.op == T.DimShuffle((), ['x', 'x'],
                                                  inplace=True), end=' ')
                    print(node.inputs[0], type(node.inputs[0]), end=' ')
                    print(node.inputs[0].equals(T.constant(2)), end=' ')
                outputs = node.outputs
                inputs = theano.gof.graph.inputs(outputs)
                print('node ', i, node, end=' ')
                print(':'.join([imap[inp.owner] for inp in node.inputs]))
                #print theano.sandbox.pprint.pp.process_graph(inputs, outputs)
        return theano.sandbox.wraplinker.WrapLinkerMany(
                [theano.gof.OpWiseCLinker()],
                [theano.sandbox.wraplinker.run_all
                    ,blah
                    #,theano.sandbox.wraplinker.numpy_notall_isfinite
                    ])
    else:
        return theano.gof.OpWiseCLinker() 

def get_size(self, shape_info):
        # The size is the data, that have constant size.
        state = numpy.random.RandomState().get_state()
        size = 0
        for elem in state:
            if isinstance(elem, str):
                size += len(elem)
            elif isinstance(elem, numpy.ndarray):
                size += elem.size * elem.itemsize
            elif isinstance(elem, int):
                size += numpy.dtype("int").itemsize
            elif isinstance(elem, float):
                size += numpy.dtype("float").itemsize
            else:
                raise NotImplementedError()
        return size 

def stop_gradient(variables):
    """Returns `variables` but with zero gradient w.r.t. every other variable.

    # Arguments
        variables: tensor or list of tensors to consider constant with respect
            to any other variable.

    # Returns
        A single tensor or a list of tensors (depending on the passed argument)
            that has constant gradient with respect to any other variable.
    """
    if isinstance(variables, (list, tuple)):
        return map(theano.gradient.disconnected_grad, variables)
    else:
        return theano.gradient.disconnected_grad(variables)


# CONTROL FLOW 

def infer_shape(self, node, i_shapes):
        r, shp = node.inputs[0:2]

        # if shp is a constant array of len 0, then it means 'automatic shape'
        unknown_shape = len(getattr(shp, 'data', [0, 1, 2])) == 0

        # if ndim_added == 0 and shape != () then shape
        if self.ndim_added == 0 and not unknown_shape:
            sample_shp = shp
        else:
            # if shape == () then it will depend on args
            # if ndim_added != 0 and shape != () then it will depend on args
            # Use the default infer_shape implementation.
            raise tensor.ShapeError()

        return [None, [sample_shp[i] for i in xrange(node.outputs[1].ndim)]] 

def make_node(self, x, index):
        assert isinstance(x.type, TypedListType)
        if not isinstance(index, Variable):
            if isinstance(index, slice):
                index = Constant(SliceType(), index)
                return Apply(self, [x, index], [x.type()])
            else:
                index = T.constant(index, ndim=0, dtype='int64')
                return Apply(self, [x, index], [x.ttype()])
        if isinstance(index.type, SliceType):
            return Apply(self, [x, index], [x.type()])
        elif isinstance(index, T.TensorVariable) and index.ndim == 0:
            assert index.dtype == 'int64'
            return Apply(self, [x, index], [x.ttype()])
        else:
            raise TypeError('Expected scalar or slice as index.') 

def test_constant(self):
        orig_compute_test_value = theano.config.compute_test_value
        try:
            theano.config.compute_test_value = 'raise'

            x = T.constant(numpy.random.rand(2, 3), dtype=config.floatX)
            y = theano.shared(numpy.random.rand(3, 6).astype(config.floatX),
                              'y')

            # should work
            z = T.dot(x, y)
            assert hasattr(z.tag, 'test_value')
            f = theano.function([], z)
            assert _allclose(f(), z.tag.test_value)

            # this test should fail
            x = T.constant(numpy.random.rand(2, 4), dtype=config.floatX)
            self.assertRaises(ValueError, T.dot, x, y)
        finally:
            theano.config.compute_test_value = orig_compute_test_value 

def test_gpualloc():
    '''
    This tests tries to catch the scenario when, due to infer_shape,
    the input of the alloc changes from tensor scalar to a constant
    1. In this case the original constracted broadcastable pattern will
    have a False for that dimension, but the new broadcastable pattern
    that will be inserted by gpualloc will have  a True since it knows the
    dimension is 1 and therefore broadcastable.
    '''

    x = theano.shared(numpy.ones(3, dtype='float32'), 'x')
    m = (x).dimshuffle(['x', 0])
    v = tensor.alloc(1., *m.shape)
    f = theano.function([], v + x,
                        mode=mode_with_gpu.excluding("local_elemwise_alloc"))
    l = f.maker.fgraph.toposort()
    assert numpy.any([isinstance(x.op, cuda.GpuAlloc) for x in l]) 

def test_gpualloc():
    '''
    This tests tries to catch the scenario when, due to infer_shape,
    the input of the alloc changes from tensor scalar to a constant
    1. In this case the original constracted broadcastable pattern will
    have a False for that dimension, but the new broadcastable pattern
    that will be inserted by gpualloc will have  a True since it knows the
    dimension is 1 and therefore broadcastable.
    '''

    x = theano.shared(numpy.ones(3, dtype='float32'), 'x')
    m = (x).dimshuffle(['x', 0])
    v = tensor.alloc(1., *m.shape)
    f = theano.function([], v + x,
                        mode=mode_with_gpu.excluding("local_elemwise_alloc"))
    l = f.maker.fgraph.toposort()
    assert numpy.any([isinstance(x.op, cuda.GpuAlloc) for x in l]) 

def make_node(self, x, index):
        assert isinstance(x.type, TypedListType)
        if not isinstance(index, Variable):
            if isinstance(index, slice):
                index = Constant(SliceType(), index)
                return Apply(self, [x, index], [x.type()])
            else:
                index = T.constant(index, ndim=0, dtype='int64')
                return Apply(self, [x, index], [x.ttype()])
        if isinstance(index.type, SliceType):
            return Apply(self, [x, index], [x.type()])
        elif isinstance(index, T.TensorVariable) and index.ndim == 0:
            assert index.dtype == 'int64'
            return Apply(self, [x, index], [x.ttype()])
        else:
            raise TypeError('Expected scalar or slice as index.') 

def get_size(self, shape_info):
        # The size is the data, that have constant size.
        state = numpy.random.RandomState().get_state()
        size = 0
        for elem in state:
            if isinstance(elem, str):
                size += len(elem)
            elif isinstance(elem, numpy.ndarray):
                size += elem.size * elem.itemsize
            elif isinstance(elem, int):
                size += numpy.dtype("int").itemsize
            elif isinstance(elem, float):
                size += numpy.dtype("float").itemsize
            else:
                raise NotImplementedError()
        return size 

def get_output_for(self, input, deterministic=False, **kwargs):
        """
        Parameters
        ----------
        input : tensor
            output from the previous layer
        deterministic : bool
            If true dropout and scaling is disabled, see notes
        """
        if deterministic or self.p == 0:
            return input
        else:
            # Using theano constant to prevent upcasting
            one = T.constant(1)

            retain_prob = one - self.p
            if self.rescale:
                input /= retain_prob

            mask = _srng.binomial(input.shape[:2], p=retain_prob,
                                      dtype=theano.config.floatX)
            axes = [0, 1] + (['x'] * (input.ndim - 2))
            mask = mask.dimshuffle(*axes)

            return input * mask 

def test_csm_unsorted(self):
        """
        Test support for gradients of unsorted inputs.
        """
        sp_types = {'csc': sp.csc_matrix,
                    'csr': sp.csr_matrix}

        for format in ['csr', 'csc', ]:
            for dtype in ['float32', 'float64']:
                x = tensor.tensor(dtype=dtype, broadcastable=(False,))
                y = tensor.ivector()
                z = tensor.ivector()
                s = tensor.ivector()
                # Sparse advanced indexing produces unsorted sparse matrices
                a = sparse_random_inputs(format, (4, 3), out_dtype=dtype,
                                         unsorted_indices=True)[1][0]
                # Make sure it's unsorted
                assert not a.has_sorted_indices
                def my_op(x):
                    y = tensor.constant(a.indices)
                    z = tensor.constant(a.indptr)
                    s = tensor.constant(a.shape)
                    return tensor.sum(
                        dense_from_sparse(CSM(format)(x, y, z, s) * a))
                verify_grad_sparse(my_op, [a.data]) 

def stop_gradient(variables):
    """Returns `variables` but with zero gradient w.r.t. every other variable.

    # Arguments
        variables: tensor or list of tensors to consider constant with respect
            to any other variable.

    # Returns
        A single tensor or a list of tensors (depending on the passed argument)
            that has constant gradient with respect to any other variable.
    """
    if isinstance(variables, (list, tuple)):
        return map(theano.gradient.disconnected_grad, variables)
    else:
        return theano.gradient.disconnected_grad(variables)


# CONTROL FLOW 

def print_graph_linker(print_prog=True):
    if 1:
        imap = {None:'-'}
        def blah(i, node, thunk):
            imap[node] = str(i)
            if print_prog:# and node.op.__class__ is T.DimShuffle:
                if False and  node.op == T.DimShuffle((), ['x', 'x'], inplace = True):
                    print(node.op == T.DimShuffle((), ['x', 'x'],
                                                  inplace=True), end=' ')
                    print(node.inputs[0], type(node.inputs[0]), end=' ')
                    print(node.inputs[0].equals(T.constant(2)), end=' ')
                outputs = node.outputs
                inputs = theano.gof.graph.inputs(outputs)
                print('node ', i, node, end=' ')
                print(':'.join([imap[inp.owner] for inp in node.inputs]))
                #print theano.sandbox.pprint.pp.process_graph(inputs, outputs)
        return theano.sandbox.wraplinker.WrapLinkerMany(
                [theano.gof.OpWiseCLinker()],
                [theano.sandbox.wraplinker.run_all
                    ,blah
                    #,theano.sandbox.wraplinker.numpy_notall_isfinite
                    ])
    else:
        return theano.gof.OpWiseCLinker() 

def test_mixin_constants():
    # Check with constants
    mu = T.constant(0.0)
    sigma = T.constant(1.0)
    p = Normal(mu=mu, sigma=sigma)
    assert len(p.parameters_) == 0
    assert len(p.constants_) == 2
    assert mu in p.constants_
    assert sigma in p.constants_ 

def __init__(self, x, y, args):
        self.params_theta = []
        self.params_lambda = []
        self.params_weight = []
        if args.dataset == 'mnist':
            input_size = (None, 1, 28, 28)
        elif args.dataset == 'cifar10':
            input_size = (None, 3, 32, 32)
        else:
            raise AssertionError
        layers = [ll.InputLayer(input_size)]
        self.penalty = theano.shared(np.array(0.))

        #conv1
        layers.append(Conv2DLayerWithReg(args, layers[-1], 20, 5))
        self.add_params_to_self(args, layers[-1])
        layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2))
        #conv1
        layers.append(Conv2DLayerWithReg(args, layers[-1], 50, 5))
        self.add_params_to_self(args, layers[-1])
        layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2))
        #fc1
        layers.append(DenseLayerWithReg(args, layers[-1], num_units=500))
        self.add_params_to_self(args, layers[-1])
        #softmax
        layers.append(DenseLayerWithReg(args, layers[-1], num_units=10, nonlinearity=nonlinearities.softmax))
        self.add_params_to_self(args, layers[-1])

        self.layers = layers
        self.y = ll.get_output(layers[-1], x, deterministic=False)
        self.prediction = T.argmax(self.y, axis=1)
        # self.penalty = penalty if penalty != 0. else T.constant(0.)
        print(self.params_lambda)
        # time.sleep(20)
        # cost function
        self.loss = T.mean(categorical_crossentropy(self.y, y))
        self.lossWithPenalty = T.add(self.loss, self.penalty)
        print "loss and losswithpenalty", type(self.loss), type(self.lossWithPenalty) 

def test_dtype_normal_uniform_687(self):
        # Regression test for #687.
        rng_R = random_state_type()
        assert uniform(rng_R, low=tensor.constant(0, dtype='float64'),
                       dtype='float32')[1].dtype == 'float32'

        assert normal(rng_R, avg=tensor.constant(0, dtype='float64'),
                      dtype='float32')[1].dtype == 'float32' 

def test_inplace(self):
        A = self.shared(numpy.random.rand(4, 5).astype(self.dtype))
        f = self.function([self.x, self.y], [],
                          updates=[(A, A + T.constant(0.1, dtype=self.dtype) *
                                   T.outer(self.x, self.y))])
        self.assertFunctionContains(f, self.ger_destructive)
        f(numpy.random.rand(4).astype(self.dtype),
          numpy.random.rand(5).astype(self.dtype))

        A.set_value(
            A.get_value(borrow=True, return_internal_type=True)[::-1, ::-1],
            borrow=True)
        f(numpy.random.rand(4).astype(self.dtype),
          numpy.random.rand(5).astype(self.dtype)) 

def test1(self):
        """Test that it fails on nonscalar constants"""
        a = T.constant(numpy.ones(5))
        self.assertTrue(None == _as_scalar(a))
        self.assertTrue(None == _as_scalar(T.DimShuffle([False], [0, 'x'])(a))) 

def test_destroy_map4(self):
        """test that dot args can be aliased"""
        Z = shared(self.rand(2, 2), name='Z')
        A = shared(self.rand(2, 2), name='A')
        one = T.constant(1.0).astype(Z.dtype)
        f = inplace_func([], gemm_inplace(Z, one, A, A, one))
        f()
        f = inplace_func([], gemm_inplace(Z, one, A, A.T, one))
        f() 

def test_factorised_scalar(self):
        a = T.matrix()
        b = T.matrix()
        c = T.matrix()
        s = theano.shared(numpy.zeros((5, 5)).astype(config.floatX))

        lr1 = T.constant(0.01).astype(config.floatX)
        lr2 = T.constant(2).astype(config.floatX)
        l2_reg = T.constant(0.0001).astype(config.floatX)

        # test constant merge with gemm
        f = theano.function([a, b], updates=[(s, lr1 * T.dot(a, b) +
                                                l2_reg * lr2 * s)],
                            mode=mode_not_fast_compile).maker.fgraph.toposort()
        #[Gemm{inplace}(<TensorType(float64, matrix)>, 0.01,
        # <TensorType(float64, matrix)>, <TensorType(float64, matrix)>,
        # 2e-06)]
        assert len(f) == 1
        assert f[0].op == gemm_inplace

        # test factored scalar with merge
        f = theano.function([a, b], updates=[(s, lr1 * (T.dot(a, b) -
                                                        l2_reg * s))],
                            mode=mode_not_fast_compile).maker.fgraph.toposort()
        #[Gemm{inplace}(<TensorType(float64, matrix)>, 0.01,
        # <TensorType(float64, matrix)>, <TensorType(float64, matrix)>,
        # -2e-06)]
        assert len(f) == 1
        assert f[0].op == gemm_inplace

        # test factored scalar with merge and neg
        f = theano.function([a, b],
                            updates=[(s, s - lr1 * (s * .0002 + T.dot(a, b)))],
                            mode=mode_not_fast_compile).maker.fgraph.toposort()
        #[Gemm{inplace}(<TensorType(float64, matrix)>, -0.01,
        # <TensorType(float64, matrix)>, <TensorType(float64, matrix)>,
        # 0.999998)]
        assert len(f) == 1
        assert f[0].op == gemm_inplace 

def setUp(self):
        super(AddSSDataTester, self).setUp()
        self.op_class = AddSSData

        for format in sparse.sparse_formats:
            variable = getattr(theano.sparse, format + '_matrix')

            rand = numpy.array(
                numpy.random.random_integers(3, size=(3, 4)) - 1,
                dtype=theano.config.floatX)
            constant = as_sparse_format(rand, format)

            self.x[format] = [variable() for t in range(2)]
            self.a[format] = [constant for t in range(2)] 

def constant(value, dtype=None, shape=None, name=None):
    if dtype is None:
        dtype = floatx()
    if shape is None:
        shape = ()
    np_value = value * np.ones(shape)
    const = T.constant(np_value,
                       dtype=dtype,
                       name=_prepare_name(name, 'constant'))
    const._keras_shape = shape
    const._uses_learning_phase = False
    return const 

def const(value):
    return TT.constant(numpy.asarray(value, dtype=theano.config.floatX)) 

def test_opfromgraph(self):
        # as with the scan tests above, insert foreign inputs into the
        # inner graph.
        outer = tensor.scalar("outer")
        shared = theano.shared(
            numpy.array(1., dtype=theano.config.floatX),
            name="shared")
        constant = tensor.constant(1., name="constant")
        z = outer * (shared + constant)

        # construct the inner graph
        a = tensor.scalar()
        b = tensor.scalar()
        r = a + b
        r.tag.replacement = z * (a - b)

        # construct the outer graph
        c = tensor.scalar()
        d = tensor.scalar()
        u = theano.OpFromGraph([a, b], [r])(c, d)
        t = z * u
        v, = map_variables(self.replacer, [t])
        t2 = z * v

        f = theano.function([c, d, outer], [t, t2])
        for m, n in itertools.combinations(range(10), 2):
            assert f(m, n, outer=0.5) == [m + n, m - n]

        # test that the unsupported case of replacement with a shared
        # variable with updates crashes
        shared.update = shared + 1
        self.assertRaises(NotImplementedError,
                          map_variables, self.replacer, [t])