def probs(self, value):
"""Probabilities of the given category (``value``).
If ``logits`` is 2-D or higher dimension, the last dimension will be regarded as
category, and the others represents the different distributions.
At the same time, if ``vlaue`` is 1-D Tensor, ``value`` will be broadcast to the
same number of distributions as ``logits``.
If ``value`` is not 1-D Tensor, ``value`` should have the same number distributions
with ``logits. That is, ``value[:-1] = logits[:-1]``.
Args:
value (Tensor): The input tensor represents the selected category index.
Returns:
Tensor: probability according to the category index.
Examples:
.. code-block:: python
import paddle
from paddle.distribution import Categorical
paddle.seed(100) # on CPU device
x = paddle.rand([6])
print(x)
# [0.5535528 0.20714243 0.01162981
# 0.51577556 0.36369765 0.2609165 ]
cat = Categorical(x)
value = paddle.to_tensor([2,1,3])
cat.probs(value)
# [0.00608027 0.108298 0.269656]
"""
name = self.name + '_probs'
if len(self._prob.shape) == 1: # batch_shape is empty
return paddle.gather(self._prob,
value.reshape([-1], name=name),
name=name).reshape(value.shape, name=name)
else:
if len(value.shape) == 1:
return paddle.take_along_axis(
self._prob,
paddle.reshape(value,
(len(self._prob.shape) - 1) * [1] + [-1],
name=name),
axis=-1)
else:
return paddle.take_along_axis(self._prob, value, axis=-1)
def test_api_dygraph(self):
paddle.disable_static(self.place[0])
x_tensor = paddle.to_tensor(self.x_np)
self.index = paddle.to_tensor(self.index_np)
out = paddle.take_along_axis(x_tensor, self.index, self.axis)
out_ref = np.array(
np.take_along_axis(self.x_np, self.index_np, self.axis))
self.assertEqual(np.allclose(out.numpy(), out_ref, rtol=1e-03), True)
paddle.enable_static()
def test_api_static(self):
paddle.enable_static()
with paddle.static.program_guard(paddle.static.Program()):
x = paddle.fluid.data('X', self.shape)
index = paddle.fluid.data('Index', self.index_shape, "int64")
out = paddle.take_along_axis(x, index, self.axis)
exe = paddle.static.Executor(self.place)
res = exe.run(feed={'X': self.x_np,
'Index': self.index_np},
fetch_list=[out])
out_ref = np.array(
np.take_along_axis(self.x_np, self.index_np, self.axis))
for out in res:
self.assertEqual(np.allclose(out, out_ref, rtol=1e-03), True)
def _compute_quantile(x, q, axis=None, keepdim=False, ignore_nan=False):
"""
Compute the quantile of the input along the specified axis.
Args:
Args:
x (Tensor): The input Tensor, it's data type can be float32, float64.
q (int|float|list): The q for calculate quantile, which should be in range [0, 1]. If q is a list,
each q will be calculated and the first dimension of output is same to the number of ``q`` .
axis (int|list, optional): The axis along which to calculate quantile. ``axis`` should be int or list of int.
``axis`` should be in range [-D, D), where D is the dimensions of ``x`` .
If ``axis`` is less than 0, it works the same way as :math:`axis + D`.
If ``axis`` is a list, quantile is calculated over all elements of given axises.
If ``axis`` is None, quantile is calculated over all elements of ``x``. Default is None.
keepdim (bool, optional): Whether to reserve the reduced dimension(s)
in the output Tensor. If ``keepdim`` is True, the dimensions of
the output Tensor is the same as ``x`` except in the reduced
dimensions(it is of size 1 in this case). Otherwise, the shape of
the output Tensor is squeezed in ``axis`` . Default is False.
ignore_nan: (bool, optional): Whether to ignore NaN of input Tensor.
If ``ignore_nan`` is True, it will calculate nanquantile.
Otherwise it will calculate quantile. Default is False.
Returns:
Tensor, results of quantile along ``axis`` of ``x``.
In order to obtain higher precision, data type of results will be float64.
"""
# Validate x
if not isinstance(x, Variable):
raise TypeError("input x should be a Tensor.")
# Validate q
if isinstance(q, (int, float)):
q = [q]
elif isinstance(q, (list, tuple)):
if len(q) <= 0:
raise ValueError("q should not be empty")
else:
raise TypeError("Type of q should be int, float, list or tuple.")
# Validate axis
dims = len(x.shape)
out_shape = list(x.shape)
if axis is None:
x = paddle.flatten(x)
axis = 0
out_shape = [1] * dims
else:
if isinstance(axis, list):
if len(axis) <= 0:
raise ValueError("axis should not be empty")
axis_src, axis_dst = [], []
for axis_single in axis:
if not isinstance(axis_single, int) or not (
axis_single < dims and axis_single >= -dims):
raise ValueError(
"Axis should be None, int, or a list, element should in range [-rank(x), rank(x))."
)
if axis_single < 0:
axis_single = axis_single + dims
axis_src.append(axis_single)
out_shape[axis_single] = 1
axis_dst = list(range(-len(axis), 0))
x = paddle.moveaxis(x, axis_src, axis_dst)
x = paddle.flatten(x, axis_dst[0], axis_dst[-1])
axis = axis_dst[0]
else:
if not isinstance(axis, int) or not (axis < dims and axis >= -dims):
raise ValueError(
"Axis should be None, int, or a list, element should in range [-rank(x), rank(x))."
)
if axis < 0:
axis += dims
out_shape[axis] = 1
mask = x.isnan()
valid_counts = mask.logical_not().sum(axis=axis,
keepdim=True,
dtype='float64')
indices = []
for q_num in q:
if q_num < 0 or q_num > 1:
raise ValueError("q should be in range [0, 1]")
if paddle.in_dynamic_mode():
q_num = paddle.to_tensor(q_num, dtype='float64')
if ignore_nan:
indices.append(q_num * (valid_counts - 1))
else:
# TODO(Asthestarsfalll): Use paddle.index_fill instead of where
index = q_num * (valid_counts - 1)
last_index = x.shape[axis] - 1
nums = paddle.full_like(index, fill_value=last_index)
index = paddle.where(mask.any(axis=axis, keepdim=True), nums, index)
indices.append(index)
sorted_tensor = paddle.sort(x, axis)
outputs = []
# TODO(chenjianye): replace the for-loop to directly take elements.
for index in indices:
indices_below = paddle.floor(index).astype(paddle.int32)
indices_upper = paddle.ceil(index).astype(paddle.int32)
tensor_upper = paddle.take_along_axis(
sorted_tensor, indices_upper, axis=axis)
tensor_below = paddle.take_along_axis(
sorted_tensor, indices_below, axis=axis)
weights = (index - indices_below.astype('float64'))
out = paddle.lerp(
tensor_below.astype('float64'),
tensor_upper.astype('float64'), weights)
if not keepdim:
out = paddle.squeeze(out, axis=axis)
else:
out = out.reshape(out_shape)
outputs.append(out)
if len(q) > 1:
outputs = paddle.stack(outputs, 0)
else:
outputs = outputs[0]
return outputs
def quantile(x, q, axis=None, keepdim=False):
"""
Compute the quantile of the input along the specified axis.
Args:
x (Tensor): The input Tensor, it's data type can be float32, float64.
q (int|float|list): The q for calculate quantile, which should be in range [0, 1]. If q is a list,
each q will be calculated and the first dimension of output is same to the number of ``q`` .
axis (int|list, optional): The axis along which to calculate quantile. ``axis`` should be int or list of int.
``axis`` should be in range [-D, D), where D is the dimensions of ``x`` .
If ``axis`` is less than 0, it works the same way as :math:`axis + D`.
If ``axis`` is a list, quantile is calculated over all elements of given axises.
If ``axis`` is None, quantile is calculated over all elements of ``x``. Default is None.
keepdim (bool, optional): Whether to reserve the reduced dimension(s)
in the output Tensor. If ``keepdim`` is True, the dimensions of
the output Tensor is the same as ``x`` except in the reduced
dimensions(it is of size 1 in this case). Otherwise, the shape of
the output Tensor is squeezed in ``axis`` . Default is False.
name (str, optional): Name for the operation (optional, default is None).
For more information, please refer to :ref:`api_guide_Name`.
Returns:
Tensor, results of quantile along ``axis`` of ``x``. If data type of ``x`` is float64, data type of results will be float64, otherwise data type will be float32.
Examples:
.. code-block:: python
import paddle
x = paddle.randn((2,3))
#[[-1.28740597, 0.49533170, -1.00698614],
# [-1.11656201, -1.01010525, -2.23457789]])
y1 = paddle.quantile(x, q=0.5, axis=[0, 1])
# y1 = -1.06333363
y2 = paddle.quantile(x, q=0.5, axis=1)
# y2 = [-1.00698614, -1.11656201]
y3 = paddle.quantile(x, q=[0.3, 0.5], axis=1)
# y3 =[[-1.11915410, -1.56376839],
# [-1.00698614, -1.11656201]]
y4 = paddle.quantile(x, q=0.8, axis=1, keepdim=True)
# y4 = [[-0.10559537],
# [-1.05268800]])
"""
if not isinstance(x, Variable):
raise TypeError("input x should be a Tensor.")
dims = len(x.shape)
out_shape = x.shape
if axis is None:
x = paddle.flatten(x)
axis = 0
out_shape = [1] * dims
else:
if isinstance(axis, list):
if (len(axis) <= 0):
raise ValueError("axis should not be empty")
axis_src, axis_dst = [], []
for axis_single in axis:
if not isinstance(axis_single, int) or not (
axis_single < dims and axis_single >= -dims):
raise ValueError(
"Axis should be None, int, or a list, element should in range [-rank(x), rank(x))."
)
if axis_single < 0:
axis_single = axis_single + dims
axis_src.append(axis_single)
out_shape[axis_single] = 1
axis_dst = list(range(-len(axis), 0))
x = paddle.moveaxis(x, axis_src, axis_dst)
x = paddle.flatten(x, axis_dst[0], axis_dst[-1])
axis = axis_dst[0]
else:
if not isinstance(axis, int) or not (axis < dims and axis >= -dims):
raise ValueError(
"Axis should be None, int, or a list, element should in range [-rank(x), rank(x))."
)
if axis < 0:
axis += dims
out_shape[axis] = 1
indices = []
if isinstance(q, (int, float)):
if q < 0 or q > 1:
raise ValueError("q should be in range [0, 1]")
indices.append(q * (x.shape[axis] - 1))
elif isinstance(q, (list, tuple)):
if len(q) <= 0:
raise ValueError("q should not be empty")
for q_num in q:
if q_num < 0 or q_num > 1:
raise ValueError("q should be in range [0, 1]")
indices.append(q_num * (x.shape[axis] - 1))
else:
raise TypeError("Type of q should be int, float, list or tuple.")
indices = paddle.to_tensor(indices).astype(paddle.float32)
sorted_tensor = paddle.sort(x, axis)
indices_below = paddle.floor(indices).astype(paddle.int32)
indices_upper = paddle.ceil(indices).astype(paddle.int32)
outputs = []
# TODO(chenjianye): replace the for-loop to directly take elements.
for i in range(len(indices)):
if (indices_upper[i] != indices_below[i]):
tensor_below = paddle.take_along_axis(sorted_tensor,
indices_below[i], axis)
tensor_upper = paddle.take_along_axis(sorted_tensor,
indices_upper[i], axis)
weights = (indices[i] - indices_below[i]).astype(x.dtype)
out = paddle.lerp(tensor_below, tensor_upper, weights)
else:
out = paddle.take_along_axis(sorted_tensor, indices_below[i], axis)
if not keepdim:
out = paddle.squeeze(out, axis=axis)
else:
out = out.reshape(out_shape)
outputs.append(out)
if isinstance(q, (list, tuple)):
return paddle.stack(outputs, 0)
else:
return outputs[0]