[xdoctest] No.44-47 and No.50-59 doc style

python/paddle/distribution/independent.py

@@ -31,21 +31,21 @@ class Independent(distribution.Distribution):
 
         .. code-block:: python
 
-            import paddle
-            from paddle.distribution import independent
-
-            beta = paddle.distribution.Beta(paddle.to_tensor([0.5, 0.5]), paddle.to_tensor([0.5, 0.5]))
-            print(beta.batch_shape, beta.event_shape)
-            # (2,) ()
-            print(beta.log_prob(paddle.to_tensor(0.2)))
-            # Tensor(shape=[2], dtype=float32, place=Place(gpu:0), stop_gradient=True,
-            #        [-0.22843921, -0.22843921])
-            reinterpreted_beta = independent.Independent(beta, 1)
-            print(reinterpreted_beta.batch_shape, reinterpreted_beta.event_shape)
+            >>> import paddle
+            >>> from paddle.distribution import independent
+
+            >>> beta = paddle.distribution.Beta(paddle.to_tensor([0.5, 0.5]), paddle.to_tensor([0.5, 0.5]))
+            >>> print(beta.batch_shape, beta.event_shape)
+            (2,) ()
+            >>> print(beta.log_prob(paddle.to_tensor(0.2)))
+            Tensor(shape=[2], dtype=float32, place=Place(gpu:0), stop_gradient=True,
+                    [-0.22843921, -0.22843921])
+            >>> reinterpreted_beta = independent.Independent(beta, 1)
+            >>> print(reinterpreted_beta.batch_shape, reinterpreted_beta.event_shape)
             # () (2,)
-            print(reinterpreted_beta.log_prob(paddle.to_tensor([0.2,  0.2])))
-            # Tensor(shape=[], dtype=float32, place=Place(gpu:0), stop_gradient=True,
-            #        -0.45687842)
+            >>> print(reinterpreted_beta.log_prob(paddle.to_tensor([0.2,  0.2])))
+            Tensor(shape=[], dtype=float32, place=Place(gpu:0), stop_gradient=True,
+                    -0.45687842)
     """
 
     def __init__(self, base, reinterpreted_batch_rank):

python/paddle/distribution/kl.py

@@ -53,14 +53,14 @@ def kl_divergence(p, q):
 
         .. code-block:: python
 
-            import paddle
+            >>> import paddle
 
-            p = paddle.distribution.Beta(alpha=0.5, beta=0.5)
-            q = paddle.distribution.Beta(alpha=0.3, beta=0.7)
+            >>> p = paddle.distribution.Beta(alpha=0.5, beta=0.5)
+            >>> q = paddle.distribution.Beta(alpha=0.3, beta=0.7)
 
-            print(paddle.distribution.kl_divergence(p, q))
-            # Tensor(shape=[], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
-            #        0.21193528)
+            >>> print(paddle.distribution.kl_divergence(p, q))
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                0.21193528)
 
     """
     return _dispatch(type(p), type(q))(p, q)
@@ -82,11 +82,11 @@ def register_kl(cls_p, cls_q):
     Examples:
         .. code-block:: python
 
-            import paddle
+            >>> import paddle
 
-            @paddle.distribution.register_kl(paddle.distribution.Beta, paddle.distribution.Beta)
-            def kl_beta_beta():
-                pass # insert implementation here
+            >>> @paddle.distribution.register_kl(paddle.distribution.Beta, paddle.distribution.Beta)
+            >>> def kl_beta_beta():
+            ...     pass # insert implementation here
     """
     if not issubclass(cls_p, Distribution) or not issubclass(
         cls_q, Distribution

python/paddle/distribution/laplace.py

@@ -44,12 +44,12 @@ class Laplace(distribution.Distribution):
     Examples:
         .. code-block:: python
 
-            import paddle
+            >>> import paddle
 
-            m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-            m.sample()  # Laplace distributed with loc=0, scale=1
-            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-            #        3.68546247)
+            >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+            >>> m.sample()  # Laplace distributed with loc=0, scale=1
+            Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                    3.68546247)
 
     """
 
@@ -173,13 +173,13 @@ def log_prob(self, value):
         Examples:
             .. code-block:: python
 
-                import paddle
+                >>> import paddle
 
-                m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-                value = paddle.to_tensor(0.1)
-                m.log_prob(value)
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        -0.79314721)
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+                >>> value = paddle.to_tensor(0.1)
+                >>> m.log_prob(value)
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        -0.79314721)
 
         """
         loc, scale, value = self._validate_value(value)
@@ -205,12 +205,12 @@ def entropy(self):
         Examples:
             .. code-block:: python
 
-                import paddle
+                >>> import paddle
 
-                m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-                m.entropy()
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        1.69314718)
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+                >>> m.entropy()
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        1.69314718)
         """
         return 1 + paddle.log(2 * self.scale)
 
@@ -236,13 +236,13 @@ def cdf(self, value):
         Examples:
             .. code-block:: python
 
-                import paddle
+                >>> import paddle
 
-                m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-                value = paddle.to_tensor(0.1)
-                m.cdf(value)
-                # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                #        0.54758132)
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+                >>> value = paddle.to_tensor(0.1)
+                >>> m.cdf(value)
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        0.54758132)
         """
         loc, scale, value = self._validate_value(value)
         iterm = (
@@ -275,13 +275,12 @@ def icdf(self, value):
         Examples:
             .. code-block:: python
 
-                            import paddle
-
-                            m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-                            value = paddle.to_tensor(0.1)
-                            m.icdf(value)
-                            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                            #        -1.60943794)
+                >>> import paddle
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+                >>> value = paddle.to_tensor(0.1)
+                >>> m.icdf(value)
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        -1.60943794)
         """
         loc, scale, value = self._validate_value(value)
         term = value - 0.5
@@ -300,12 +299,11 @@ def sample(self, shape=()):
         Examples:
             .. code-block:: python
 
-                            import paddle
-
-                            m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
-                            m.sample()  # Laplace distributed with loc=0, scale=1
-                            # Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
-                            #        3.68546247)
+                >>> import paddle
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor(0.0), paddle.to_tensor(1.0))
+                >>> m.sample()  # Laplace distributed with loc=0, scale=1
+                Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        3.68546247)
         """
         shape = shape if isinstance(shape, tuple) else tuple(shape)
         with paddle.no_grad():
@@ -323,12 +321,11 @@ def rsample(self, shape):
         Examples:
             .. code-block:: python
 
-                            import paddle
-
-                            m = paddle.distribution.Laplace(paddle.to_tensor([0.0]), paddle.to_tensor([1.0]))
-                            m.rsample((1,))  # Laplace distributed with loc=0, scale=1
-                            # Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                            # [[0.04337667]])
+                >>> import paddle
+                >>> m = paddle.distribution.Laplace(paddle.to_tensor([0.0]), paddle.to_tensor([1.0]))
+                >>> m.rsample((1,))  # Laplace distributed with loc=0, scale=1
+                Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        [[0.04337667]])
         """
 
         eps = self._get_eps()
@@ -395,13 +392,13 @@ def kl_divergence(self, other):
         Examples:
             .. code-block:: python
 
-                import paddle
+                >>> import paddle
 
-                m1 = paddle.distribution.Laplace(paddle.to_tensor([0.0]), paddle.to_tensor([1.0]))
-                m2 = paddle.distribution.Laplace(paddle.to_tensor([1.0]), paddle.to_tensor([0.5]))
-                m1.kl_divergence(m2)
-                # Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
-                # [1.04261160])
+                >>> m1 = paddle.distribution.Laplace(paddle.to_tensor([0.0]), paddle.to_tensor([1.0]))
+                >>> m2 = paddle.distribution.Laplace(paddle.to_tensor([1.0]), paddle.to_tensor([0.5]))
+                >>> m1.kl_divergence(m2)
+                Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
+                        [1.04261160])
         """
 
         var_ratio = other.scale / self.scale

python/paddle/distribution/lognormal.py

@@ -49,36 +49,36 @@ class LogNormal(TransformedDistribution):
     Examples:
         .. code-block:: python
 
-          import paddle
-          from paddle.distribution import LogNormal
-
-          # Define a single scalar LogNormal distribution.
-          dist = LogNormal(loc=0., scale=3.)
-          # Define a batch of two scalar valued LogNormals.
-          # The underlying Normal of first has mean 1 and standard deviation 11, the underlying Normal of second 2 and 22.
-          dist = LogNormal(loc=[1., 2.], scale=[11., 22.])
-          # Get 3 samples, returning a 3 x 2 tensor.
-          dist.sample((3, ))
-
-          # Define a batch of two scalar valued LogNormals.
-          # Their underlying Normal have mean 1, but different standard deviations.
-          dist = LogNormal(loc=1., scale=[11., 22.])
-
-          # Complete example
-          value_tensor = paddle.to_tensor([0.8], dtype="float32")
-
-          lognormal_a = LogNormal([0.], [1.])
-          lognormal_b = LogNormal([0.5], [2.])
-          sample = lognormal_a.sample((2, ))
-          # a random tensor created by lognormal distribution with shape: [2, 1]
-          entropy = lognormal_a.entropy()
-          # [1.4189385] with shape: [1]
-          lp = lognormal_a.log_prob(value_tensor)
-          # [-0.72069150] with shape: [1]
-          p = lognormal_a.probs(value_tensor)
-          # [0.48641577] with shape: [1]
-          kl = lognormal_a.kl_divergence(lognormal_b)
-          # [0.34939718] with shape: [1]
+            >>> import paddle
+            >>> from paddle.distribution import LogNormal
+
+            >>> # Define a single scalar LogNormal distribution.
+            >>> dist = LogNormal(loc=0., scale=3.)
+            >>> # Define a batch of two scalar valued LogNormals.
+            >>> # The underlying Normal of first has mean 1 and standard deviation 11, the underlying Normal of second 2 and 22.
+            >>> dist = LogNormal(loc=[1., 2.], scale=[11., 22.])
+            >>> # Get 3 samples, returning a 3 x 2 tensor.
+            >>> dist.sample((3, ))
+
+            >>> # Define a batch of two scalar valued LogNormals.
+            >>> # Their underlying Normal have mean 1, but different standard deviations.
+            >>> dist = LogNormal(loc=1., scale=[11., 22.])
+
+            >>> # Complete example
+            >>> value_tensor = paddle.to_tensor([0.8], dtype="float32")
+
+            >>> lognormal_a = LogNormal([0.], [1.])
+            >>> lognormal_b = LogNormal([0.5], [2.])
+            >>> sample = lognormal_a.sample((2, ))
+            >>> # a random tensor created by lognormal distribution with shape: [2, 1]
+            >>> entropy = lognormal_a.entropy()
+            >>> # [1.4189385] with shape: [1]
+            >>> lp = lognormal_a.log_prob(value_tensor)
+            >>> # [-0.72069150] with shape: [1]
+            >>> p = lognormal_a.probs(value_tensor)
+            >>> # [0.48641577] with shape: [1]
+            >>> kl = lognormal_a.kl_divergence(lognormal_b)
+            >>> # [0.34939718] with shape: [1]
     """
 
     def __init__(self, loc, scale):

python/paddle/distribution/multinomial.py

@@ -53,18 +53,18 @@ class Multinomial(distribution.Distribution):
 
     .. code-block:: python
 
-        import paddle
-
-        multinomial = paddle.distribution.Multinomial(10, paddle.to_tensor([0.2, 0.3, 0.5]))
-        print(multinomial.sample((2, 3)))
-        # Tensor(shape=[2, 3, 3], dtype=float32, place=Place(gpu:0), stop_gradient=True,
-        #        [[[1., 4., 5.],
-        #          [0., 2., 8.],
-        #          [2., 4., 4.]],
-
-        #         [[1., 6., 3.],
-        #          [3., 3., 4.],
-        #          [3., 4., 3.]]])
+        >>> import paddle
+
+        >>> multinomial = paddle.distribution.Multinomial(10, paddle.to_tensor([0.2, 0.3, 0.5]))
+        >>> print(multinomial.sample((2, 3)))
+        Tensor(shape=[2, 3, 3], dtype=float32, place=Place(cpu), stop_gradient=True,
+                [[[1., 4., 5.],
+                [0., 2., 8.],
+                [2., 4., 4.]],
+
+                [[1., 6., 3.],
+                [3., 3., 4.],
+                [3., 4., 3.]]])
     """
 
     def __init__(self, total_count, probs):

python/paddle/distribution/normal.py

@@ -54,36 +54,36 @@ class Normal(distribution.Distribution):
     Examples:
         .. code-block:: python
 
-            import paddle
-            from paddle.distribution import Normal
-
-            # Define a single scalar Normal distribution.
-            dist = Normal(loc=0., scale=3.)
-            # Define a batch of two scalar valued Normals.
-            # The first has mean 1 and standard deviation 11, the second 2 and 22.
-            dist = Normal(loc=[1., 2.], scale=[11., 22.])
-            # Get 3 samples, returning a 3 x 2 tensor.
-            dist.sample([3])
-
-            # Define a batch of two scalar valued Normals.
-            # Both have mean 1, but different standard deviations.
-            dist = Normal(loc=1., scale=[11., 22.])
-
-            # Complete example
-            value_tensor = paddle.to_tensor([0.8], dtype="float32")
-
-            normal_a = Normal([0.], [1.])
-            normal_b = Normal([0.5], [2.])
-            sample = normal_a.sample([2])
-            # a random tensor created by normal distribution with shape: [2, 1]
-            entropy = normal_a.entropy()
-            # [1.4189385] with shape: [1]
-            lp = normal_a.log_prob(value_tensor)
-            # [-1.2389386] with shape: [1]
-            p = normal_a.probs(value_tensor)
-            # [0.28969154] with shape: [1]
-            kl = normal_a.kl_divergence(normal_b)
-            # [0.34939718] with shape: [1]
+            >>> import paddle
+            >>> from paddle.distribution import Normal
+
+            >>> # Define a single scalar Normal distribution.
+            >>> dist = Normal(loc=0., scale=3.)
+            >>> # Define a batch of two scalar valued Normals.
+            >>> # The first has mean 1 and standard deviation 11, the second 2 and 22.
+            >>> dist = Normal(loc=[1., 2.], scale=[11., 22.])
+            >>> # Get 3 samples, returning a 3 x 2 tensor.
+            >>> dist.sample([3])
+
+            >>> # Define a batch of two scalar valued Normals.
+            >>> # Both have mean 1, but different standard deviations.
+            >>> dist = Normal(loc=1., scale=[11., 22.])
+
+            >>> # Complete example
+            >>> value_tensor = paddle.to_tensor([0.8], dtype="float32")
+
+            >>> normal_a = Normal([0.], [1.])
+            >>> normal_b = Normal([0.5], [2.])
+            >>> sample = normal_a.sample([2])
+            >>> # a random tensor created by normal distribution with shape: [2, 1]
+            >>> entropy = normal_a.entropy()
+            >>> # [1.4189385] with shape: [1]
+            >>> lp = normal_a.log_prob(value_tensor)
+            >>> # [-1.2389386] with shape: [1]
+            >>> p = normal_a.probs(value_tensor)
+            >>> # [0.28969154] with shape: [1]
+            >>> kl = normal_a.kl_divergence(normal_b)
+            >>> # [0.34939718] with shape: [1]
     """
 
     def __init__(self, loc, scale, name=None):