Python tensor.as_tensor_variable函数代码示例

def test_downsample():
    shps = [
        (1, 1, 1, 12),
        (1, 1, 2, 2),
        (1, 1, 1, 1),
        (1, 1, 4, 4),
        (1, 1, 10, 11),
        (1, 2, 2, 2),
        (3, 5, 4, 4),
        (25, 1, 7, 7),
        (1, 1, 12, 12),
        (1, 1, 2, 14),
        (1, 1, 12, 14),
        (1, 1, 14, 14),
        (1, 1, 16, 16),
        (1, 1, 18, 18),
        (1, 1, 24, 24),
        (1, 6, 24, 24),
        (10, 1, 24, 24),
        (10, 6, 24, 24),
        (30, 6, 12, 12),
        (30, 2, 24, 24),
        (30, 6, 24, 24),
        (10, 10, 10, 11),
        (1, 1, 10, 1025),
        (1, 1, 10, 1023),
        (1, 1, 1025, 10),
        (1, 1, 1023, 10),
    ]

    numpy.random.RandomState(unittest_tools.fetch_seed()).shuffle(shps)

    for shp in shps:
        for ds in (2, 2), (3, 2), (1, 1):
            if ds[0] > shp[2]:
                continue
            if ds[1] > shp[3]:
                continue
            # GpuDownsampleFactorMax doesn't like having more than 512 columns
            # in the output tensor.
            if float(shp[3]) / ds[1] > 512:
                continue
            for ignore_border in (True, False):
                print "test_downsample", shp, ds, ignore_border
                ds_op = DownsampleFactorMax(ds, ignore_border=ignore_border)

                a = tcn.shared_constructor(my_rand(*shp), "a")
                f = pfunc([], ds_op(tensor.as_tensor_variable(a)), mode=mode_with_gpu)
                f2 = pfunc([], ds_op(tensor.as_tensor_variable(a)), mode=mode_without_gpu)
                assert any([isinstance(node.op, tcn.blas.GpuDownsampleFactorMax) for node in f.maker.env.toposort()])
                assert any([isinstance(node.op, DownsampleFactorMax) for node in f2.maker.env.toposort()])
                assert numpy.allclose(f(), f2())

                g = pfunc([], tensor.grad(ds_op(tensor.as_tensor_variable(a)).sum(), a), mode=mode_with_gpu)
                g2 = pfunc([], tensor.grad(ds_op(tensor.as_tensor_variable(a)).sum(), a), mode=mode_without_gpu)
                assert any(
                    [isinstance(node.op, tcn.blas.GpuDownsampleFactorMaxGrad) for node in g.maker.env.toposort()]
                )
                assert any([isinstance(node.op, DownsampleFactorMaxGrad) for node in g2.maker.env.toposort()])
                assert numpy.allclose(g(), g2())

 def make_node(self, a, n, axis):
     a = tensor.as_tensor_variable(a)
     if a.ndim < 1:
         raise TypeError('%s: input must be an array, not a scalar' %
                         self.__class__.__name__)
     if axis is None:
         axis = a.ndim - 1
         axis = tensor.as_tensor_variable(axis)
     else:
         axis = tensor.as_tensor_variable(axis)
         if (not axis.dtype.startswith('int')) and \
            (not axis.dtype.startswith('uint')):
             raise TypeError('%s: index of the transformed axis must be'
                             ' of type integer' % self.__class__.__name__)
         elif axis.ndim != 0 or (isinstance(axis, tensor.TensorConstant) and
                                 (axis.data < 0 or axis.data > a.ndim - 1)):
             raise TypeError('%s: index of the transformed axis must be'
                             ' a scalar not smaller than 0 and smaller than'
                             ' dimension of array' % self.__class__.__name__)
     if n is None:
         n = a.shape[axis]
         n = tensor.as_tensor_variable(n)
     else:
         n = tensor.as_tensor_variable(n)
         if (not n.dtype.startswith('int')) and \
            (not n.dtype.startswith('uint')):
             raise TypeError('%s: length of the transformed axis must be'
                             ' of type integer' % self.__class__.__name__)
         elif n.ndim != 0 or (isinstance(n, tensor.TensorConstant) and
                              n.data < 1):
             raise TypeError('%s: length of the transformed axis must be a'
                             ' strictly positive scalar'
                             % self.__class__.__name__)
     return gof.Apply(self, [a, n, axis], [tensor.TensorType('complex128',
                      a.type.broadcastable)()])

    def __init__(self, distribution, lower, upper, transform="infer", *args, **kwargs):
        dtype = kwargs.get("dtype", theano.config.floatX)

        if lower is not None:
            lower = tt.as_tensor_variable(lower).astype(dtype)
        if upper is not None:
            upper = tt.as_tensor_variable(upper).astype(dtype)

        if transform == "infer":
            if lower is None and upper is None:
                transform = None
                default = None
            elif lower is not None and upper is not None:
                transform = transforms.interval(lower, upper)
                default = 0.5 * (lower + upper)
            elif upper is not None:
                transform = transforms.upperbound(upper)
                default = upper - 1
            else:
                transform = transforms.lowerbound(lower)
                default = lower + 1
        else:
            default = None

        super().__init__(
            distribution, lower, upper, default, *args, transform=transform, **kwargs
        )

def quantized_lognormal_sampler(
    rstream, mu=0.0, sigma=1.0, step=1, draw_shape=None, ndim=None, dtype=theano.config.floatX
):
    """
    Sample from a quantized log-normal distribution centered on avg with
    the specified standard deviation (std).

    If the size argument is ambiguous on the number of dimensions, ndim
    may be a plain integer to supplement the missing information.

    If size is None, the output shape will be determined by the shapes
    of avg and std.

    If dtype is not specified, it will be inferred from the dtype of
    avg and std, but will be at least as precise as floatX.
    """

    mu = tensor.as_tensor_variable(mu)
    sigma = tensor.as_tensor_variable(sigma)
    step = tensor.as_tensor_variable(step)

    if dtype == None:
        dtype = tensor.scal.upcast(theano.config.floatX, mu.dtype, sigma.dtype, step.dtype)
    rstate = rstream.new_shared_rstate()
    ndim, draw_shape, bcast = tensor.raw_random._infer_ndim_bcast(ndim, draw_shape, mu, sigma)
    op = QuantizedLognormal(otype=tensor.TensorType(dtype=dtype, broadcastable=bcast))
    new_rstate, out = op(rstate, draw_shape, mu, sigma, step)
    rstream.add_default_update(out, rstate, new_rstate)
    return out

    def make_node(self, activations, labels, input_lengths):
        t_activations = T.as_tensor_variable(activations)
        # Ensure activations array is C-contiguous
        t_activations = cpu_contiguous(t_activations)

        t_labels = T.as_tensor_variable(labels)
        t_input_lengths = T.as_tensor_variable(input_lengths)

        if t_activations.type.dtype != 'float32':
            raise TypeError('activations must use the float32 type!')

        if t_activations.ndim != 3:
            raise ValueError('activations must have 3 dimensions.')

        if t_labels.type.dtype != 'int32':
            raise TypeError('labels must use the int32 type!')

        if t_labels.ndim != 2:
            raise ValueError('labels must have 2 dimensions.')

        if t_input_lengths.type.dtype != 'int32':
            raise TypeError('input_lengths must use the int32 type!')

        if t_input_lengths.ndim != 1:
            raise ValueError('input_lengths must have 1 dimension.')

        costs = T.fvector(name="ctc_cost")
        outputs = [costs]
        if self.compute_grad:
            gradients = T.ftensor3(name="ctc_grad")
            outputs += [gradients]

        return gof.Apply(self, inputs=[t_activations, t_labels, t_input_lengths],
                         outputs=outputs)

 def make_node(self,x,y):
     if x.type.ndim != y.type.ndim:
         raise TypeError()
     # TODO: consider restricting the dtype?
     x = tensor.as_tensor_variable(x)
     y = tensor.as_tensor_variable(y)
     return gof.Apply(self, [x,y], [])

    def test_neibs_bad_shape_wrap_centered(self):
        shape = (2, 3, 10, 10)

        for dtype in self.dtypes:
            images = shared(numpy.arange(
                numpy.prod(shape), dtype=dtype
                ).reshape(shape))

            for neib_shape in [(3, 2), (2, 3)]:
                neib_shape = T.as_tensor_variable(neib_shape)

                f = function([], images2neibs(images, neib_shape,
                                              mode="wrap_centered"),
                             mode=self.mode)
                self.assertRaises(TypeError, f)

            for shape in [(2, 3, 2, 3), (2, 3, 3, 2)]:
                images = shared(numpy.arange(numpy.prod(shape)).reshape(shape))
                neib_shape = T.as_tensor_variable((3, 3))
                f = function([], images2neibs(images, neib_shape,
                                              mode="wrap_centered"),
                             mode=self.mode)
                self.assertRaises(TypeError, f)

            # Test a valid shapes
            shape = (2, 3, 3, 3)
            images = shared(numpy.arange(numpy.prod(shape)).reshape(shape))
            neib_shape = T.as_tensor_variable((3, 3))

            f = function([],
                         images2neibs(images, neib_shape, mode="wrap_centered"),
                         mode=self.mode)
            f()

 def make_node(self, x, scale, shift):
     if x.type.ndim != 4:
         raise TypeError()
     x = tensor.as_tensor_variable(x)
     scale = tensor.as_tensor_variable(scale)
     shift = tensor.as_tensor_variable(shift)
     return gof.Apply(self, [x, scale, shift], [x.type()])

    def __init__(self, distribution, lower, upper,
                 transform='infer', *args, **kwargs):
        dtype = kwargs.get('dtype', theano.config.floatX)

        if lower is not None:
            lower = tt.as_tensor_variable(lower).astype(dtype)
        if upper is not None:
            upper = tt.as_tensor_variable(upper).astype(dtype)

        if transform == 'infer':
            if lower is None and upper is None:
                transform = None
                default = None
            elif lower is not None and upper is not None:
                transform = transforms.interval(lower, upper)
                default = 0.5 * (lower + upper)
            elif upper is not None:
                transform = transforms.upperbound(upper)
                default = upper - 1
            else:
                transform = transforms.lowerbound(lower)
                default = lower + 1
        else:
            default = None

        super(_ContinuousBounded, self).__init__(
            distribution=distribution, lower=lower, upper=upper,
            transform=transform, default=default, *args, **kwargs)

    def _traverse(node):
        """ TODO: writeme """
        if node is None:
            return None
        else:
            op = node.op
            inputs = node.inputs

            # Compute the evaluation points corresponding to each of the
            # inputs of the node
            local_eval_points = []
            for inp in inputs:
                if inp in wrt:
                    local_eval_points.append(eval_points[wrt.index(inp)])
                elif inp.owner is None:
                    local_eval_points.append(inp.zeros_like())
                elif inp.owner in seen_nodes:

                    local_eval_points.append(seen_nodes[inp.owner][inp.owner.outputs.index(inp)])

                else:
                    # We actually need to compute the R_op for this node

                    _traverse(inp.owner)
                    local_eval_points.append(seen_nodes[inp.owner][inp.owner.outputs.index(inp)])
            for x, y in zip(inputs, local_eval_points):
                if y is not None:
                    assert as_tensor_variable(x).type == as_tensor_variable(y).type

            seen_nodes[node] = op.R_op(node.inputs, local_eval_points)
            return None

    def make_node(self, kern, topgrad, shape=None):
        kern = as_tensor_variable(kern)
        topgrad = as_tensor_variable(topgrad)
        kern, topgrad = self.as_common_dtype(kern, topgrad)
        if kern.type.ndim != 5:
            raise TypeError('kern must be 5D tensor')
        if topgrad.type.ndim != 5:
            raise TypeError('topgrad must be 5D tensor')
        if shape is None:
            if self.subsample != (1, 1, 1):
                raise ValueError('shape must be given if subsample != (1, 1, 1)')
            height_width_depth = []
        else:
            height_width_depth = [as_tensor_variable(shape[0]).astype('int64'),
                                  as_tensor_variable(shape[1]).astype('int64'),
                                  as_tensor_variable(shape[2]).astype('int64')]

        if self.num_groups > 1:
            broadcastable = [topgrad.type.broadcastable[0], False,
                             False, False, False]
        else:
            broadcastable = [topgrad.type.broadcastable[0], kern.type.broadcastable[1],
                             False, False, False]
        dtype = kern.type.dtype
        return Apply(self, [kern, topgrad] + height_width_depth,
                     [TensorType(dtype, broadcastable)()])

def choice(random_state, size=None, a=2, replace=True, p=None, ndim=None,
           dtype='int64'):
    """
    Choose values from `a` with or without replacement. `a` can be a 1-D array
    or a positive scalar. If `a` is a scalar, the samples are drawn from the
    range 0,...,a-1.

    If the size argument is ambiguous on the number of dimensions, ndim
    may be a plain integer to supplement the missing information.

    If size is None, a scalar will be returned.

    """
    # numpy.random.choice is only available for numpy versions >= 1.7
    major, minor, _ = numpy.version.short_version.split('.')
    if (int(major), int(minor)) < (1, 7):
        raise ImportError('choice requires at NumPy version >= 1.7 '
                          '(%s)' % numpy.__version__)
    a = tensor.as_tensor_variable(a)
    if isinstance(replace, bool):
        replace = tensor.constant(replace, dtype='int8')
    else:
        replace = tensor.as_tensor_variable(replace)
    # encode p=None as an empty vector
    p = tensor.as_tensor_variable(p or [])
    ndim, size, bcast = _infer_ndim_bcast(ndim, size)
    op = RandomFunction(choice_helper, tensor.TensorType(dtype=dtype,
                                                         broadcastable=bcast))
    return op(random_state, size, a, replace, p)

 def make_node(self, A, b):
     A = as_tensor_variable(A)
     b = as_tensor_variable(b)
     otype = tensor.tensor(
             broadcastable=b.broadcastable,
             dtype = (A*b).dtype)
     return Apply(self, [A,b], [otype])

    def __init__(self, q, beta, *args, **kwargs):
        super().__init__(*args, defaults=('median',), **kwargs)

        self.q = q = tt.as_tensor_variable(q)
        self.beta = beta = tt.as_tensor_variable(beta)

        self.median = self._ppf(0.5)

 def __init__(self, w, mu, *args, **kwargs):
     _, sd = get_tau_sd(tau=kwargs.pop('tau', None),
                        sd=kwargs.pop('sd', None))
     self.mu = mu = tt.as_tensor_variable(mu)
     self.sd = sd = tt.as_tensor_variable(sd)
     super(NormalMixture, self).__init__(w, Normal.dist(mu, sd=sd),
                                         *args, **kwargs)