From e83c0111297d76daa5885f1da2aab8434ca1fa0a Mon Sep 17 00:00:00 2001
From: yuchen202 <103028470+yuchen202@users.noreply.github.com>
Date: Thu, 28 Sep 2023 23:45:30 +0800
Subject: [PATCH] 0928

---
 python/paddle/distribution/bernoulli.py   |  8 ++++++
 python/paddle/distribution/categorical.py |  8 +++++-
 python/paddle/distribution/gumbel.py      |  5 ++--
 python/paddle/hapi/dynamic_flops.py       |  6 ++--
 python/paddle/hapi/model.py               | 34 +++++++++++------------
 python/paddle/hapi/model_summary.py       |  2 +-
 6 files changed, 39 insertions(+), 24 deletions(-)

diff --git a/python/paddle/distribution/bernoulli.py b/python/paddle/distribution/bernoulli.py
index 7d4849fab48e7..4048641a5c827 100644
--- a/python/paddle/distribution/bernoulli.py
+++ b/python/paddle/distribution/bernoulli.py
@@ -72,6 +72,7 @@ class Bernoulli(exponential_family.ExponentialFamily):
 
         .. code-block:: python
 
+            >>> # doctest: +REQUIRES(env:DISTRIBUTED)
             >>> import paddle
             >>> from paddle.distribution import Bernoulli
 
@@ -156,6 +157,7 @@ def sample(self, shape):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -211,6 +213,7 @@ def rsample(self, shape, temperature=1.0):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -308,6 +311,7 @@ def cdf(self, value):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -346,6 +350,7 @@ def log_prob(self, value):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -385,6 +390,7 @@ def prob(self, value):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -415,6 +421,7 @@ def entropy(self):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
@@ -448,6 +455,7 @@ def kl_divergence(self, other):
 
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Bernoulli
 
diff --git a/python/paddle/distribution/categorical.py b/python/paddle/distribution/categorical.py
index b6484e3f21d56..c7be49e50b471 100644
--- a/python/paddle/distribution/categorical.py
+++ b/python/paddle/distribution/categorical.py
@@ -46,6 +46,7 @@ class Categorical(distribution.Distribution):
     Examples:
         .. code-block:: python
 
+            >>> # doctest: +REQUIRES(env:DISTRIBUTED)
             >>> import paddle
             >>> from paddle.distribution import Categorical
 
@@ -64,7 +65,7 @@ class Categorical(distribution.Distribution):
             >>> cat = Categorical(x)
             >>> cat2 = Categorical(y)
 
-            >>> # doctest: +SKIP
+            >>> # doctest: +SKIP('`paddle.distribution` can not run in xdoctest')
             >>> paddle.seed(1000) # on CPU device
             >>> print(cat.sample([2,3]))
             Tensor(shape=[2, 3], dtype=int64, place=Place(cpu), stop_gradient=True,
@@ -134,6 +135,7 @@ def sample(self, shape):
         Examples:
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Categorical
 
@@ -191,6 +193,7 @@ def kl_divergence(self, other):
         Examples:
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Categorical
 
@@ -245,6 +248,7 @@ def entropy(self):
         Examples:
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Categorical
 
@@ -289,6 +293,7 @@ def probs(self, value):
         Examples:
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Categorical
 
@@ -336,6 +341,7 @@ def log_prob(self, value):
         Examples:
             .. code-block:: python
 
+                >>> # doctest: +REQUIRES(env:DISTRIBUTED)
                 >>> import paddle
                 >>> from paddle.distribution import Categorical
 
diff --git a/python/paddle/distribution/gumbel.py b/python/paddle/distribution/gumbel.py
index 005801ae6b7cc..e42edff8bd446 100644
--- a/python/paddle/distribution/gumbel.py
+++ b/python/paddle/distribution/gumbel.py
@@ -46,13 +46,14 @@ class Gumbel(TransformedDistribution):
     Examples:
         .. code-block:: python
 
+            >>> # doctest: +REQUIRES(env:DISTRIBUTED)
             >>> import paddle
             >>> from paddle.distribution.gumbel import Gumbel
 
             >>> # Gumbel distributed with loc=0, scale=1
             >>> dist = Gumbel(paddle.full([1], 0.0), paddle.full([1], 1.0))
 
-            >>> # doctest: +SKIP
+            >>> # doctest: +SKIP('`paddle.distribution` can not run in xdoctest')
             >>> print(dist.sample([2]))
             Tensor(shape=[2, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
             [[0.40484068],
@@ -63,7 +64,7 @@ class Gumbel(TransformedDistribution):
             [[-0.95093185],
             [ 0.32422572]])
 
-            >>> # doctest: -SKIP
+            >>> # doctest: -SKIP('`paddle.distribution` can not run in xdoctest')
             >>> value = paddle.full([1], 0.5)
             >>> print(dist.prob(value))
             Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
diff --git a/python/paddle/hapi/dynamic_flops.py b/python/paddle/hapi/dynamic_flops.py
index fcae6e4120ac8..89bad05438b32 100644
--- a/python/paddle/hapi/dynamic_flops.py
+++ b/python/paddle/hapi/dynamic_flops.py
@@ -59,7 +59,7 @@ def flops(net, input_size, custom_ops=None, print_detail=False):
             ...             nn.Conv2D(6, 16, 5, stride=1, padding=0),
             ...             nn.ReLU(),
             ...             nn.MaxPool2D(2, 2))
-            ...
+
             ...         if num_classes > 0:
             ...             self.fc = nn.Sequential(
             ...                 nn.Linear(400, 120),
@@ -73,14 +73,14 @@ def flops(net, input_size, custom_ops=None, print_detail=False):
             ...             x = paddle.flatten(x, 1)
             ...             x = self.fc(x)
             ...         return x
-            ...
+
             >>> lenet = LeNet()
             >>> # m is the instance of nn.Layer, x is the intput of layer, y is the output of layer.
             >>> def count_leaky_relu(m, x, y):
             ...     x = x[0]
             ...     nelements = x.numel()
             ...     m.total_ops += int(nelements)
-            ...
+
             >>> FLOPs = paddle.flops(lenet,
             ...                      [1, 1, 28, 28],
             ...                      custom_ops= {nn.LeakyReLU: count_leaky_relu},
diff --git a/python/paddle/hapi/model.py b/python/paddle/hapi/model.py
index 8ca5712a3036c..524637a105edb 100644
--- a/python/paddle/hapi/model.py
+++ b/python/paddle/hapi/model.py
@@ -1140,7 +1140,7 @@ class Model:
             ...
             ...     model = paddle.Model(net)
             ...     optim = paddle.optimizer.SGD(learning_rate=1e-3, parameters=model.parameters())
-            ...
+
             ...     amp_configs = {
             ...         "level": "O1",
             ...         "custom_white_list": {'conv2d'},
@@ -1150,7 +1150,7 @@ class Model:
             ...         paddle.nn.CrossEntropyLoss(),
             ...         paddle.metric.Accuracy(),
             ...         amp_configs=amp_configs)
-            ...
+
             ...     transform = T.Compose([T.Transpose(), T.Normalize([127.5], [127.5])])
             ...     data = paddle.vision.datasets.MNIST(mode='train', transform=transform)
             ...     model.fit(data, epochs=2, batch_size=32, verbose=1)
@@ -1158,7 +1158,7 @@ class Model:
             >>> # mixed precision training is only supported on GPU now.
             >>> if paddle.is_compiled_with_cuda():
             ...     run_example_code()
-            ...
+
     """
 
     def __init__(self, network, inputs=None, labels=None):
@@ -1228,7 +1228,7 @@ def train_batch(self, inputs, labels=None, update=True):
                 ...     nn.Linear(784, 200),
                 ...     nn.Tanh(),
                 ...     nn.Linear(200, 10))
-                ...
+
                 >>> input = InputSpec([None, 784], 'float32', 'x')
                 >>> label = InputSpec([None, 1], 'int64', 'label')
                 >>> model = paddle.Model(net, input, label)
@@ -1282,7 +1282,7 @@ def eval_batch(self, inputs, labels=None):
                 ...     nn.Linear(784, 200),
                 ...     nn.Tanh(),
                 ...     nn.Linear(200, 10))
-                ...
+
                 >>> input = InputSpec([None, 784], 'float32', 'x')
                 >>> label = InputSpec([None, 1], 'int64', 'label')
                 >>> model = paddle.Model(net, input, label)
@@ -1337,7 +1337,7 @@ def predict_batch(self, inputs):
                 ...     nn.Tanh(),
                 ...     nn.Linear(200, 10),
                 ...     nn.Softmax())
-                ...
+
                 >>> model = paddle.Model(net, input, label)
                 >>> model.prepare()
                 >>> data = paddle.rand((1, 784), dtype="float32")
@@ -1467,7 +1467,7 @@ def load(self, path, skip_mismatch=False, reset_optimizer=False):
                 ...     nn.Tanh(),
                 ...     nn.Linear(200, 10),
                 ...     nn.Softmax()), input)
-                ...
+
                 >>> model.save('checkpoint/test')
                 >>> model.load('checkpoint/test')
 
@@ -1558,7 +1558,7 @@ def parameters(self, *args, **kwargs):
                 ...     nn.Linear(784, 200),
                 ...     nn.Tanh(),
                 ...     nn.Linear(200, 10)), input)
-                ...
+
                 >>> params = model.parameters()
                 >>> print(params)
                 [Parameter containing:
@@ -1835,7 +1835,7 @@ def fit(
                 >>> dynamic = True
                 >>> if not dynamic:
                 ...     paddle.enable_static()
-                ...
+
                 >>> transform = T.Compose([T.Transpose(),
                 ...                        T.Normalize([127.5], [127.5])])
                 >>> train_dataset = MNIST(mode='train', transform=transform)
@@ -1858,7 +1858,7 @@ def fit(
                 ...             epochs=2,
                 ...             batch_size=64,
                 ...             save_dir='mnist_checkpoint')
-                ...
+
             2. An example use DataLoader, batch size and shuffle is set in
                DataLoader.
 
@@ -1873,7 +1873,7 @@ def fit(
                 >>> dynamic = True
                 >>> if not dynamic:
                 ...     paddle.enable_static()
-                ...
+
                 >>> transform = T.Compose([T.Transpose(),
                 ...                        T.Normalize([127.5], [127.5])])
                 >>> train_dataset = MNIST(mode='train', transform=transform)
@@ -1882,7 +1882,7 @@ def fit(
                 >>> val_dataset = MNIST(mode='test', transform=transform)
                 >>> val_loader = paddle.io.DataLoader(val_dataset,
                 ...     batch_size=64)
-                ...
+
                 >>> input = InputSpec([None, 1, 28, 28], 'float32', 'image')
                 >>> label = InputSpec([None, 1], 'int64', 'label')
 
@@ -1898,7 +1898,7 @@ def fit(
                 ...             val_loader,
                 ...             epochs=2,
                 ...             save_dir='mnist_checkpoint')
-                ...
+
         """
         assert train_data is not None, "train_data must be given!"
 
@@ -2154,16 +2154,16 @@ def predict(
                 ...     def __init__(self, mode, return_label=True):
                 ...         super().__init__(mode=mode)
                 ...         self.return_label = return_label
-                ...
+
                 ...     def __getitem__(self, idx):
                 ...         img = np.reshape(self.images[idx], [1, 28, 28])
                 ...         if self.return_label:
                 ...             return img, np.array(self.labels[idx]).astype('int64')
                 ...         return img
-                ...
+
                 ...     def __len__(self):
                 ...         return len(self.images)
-                ...
+
                 >>> test_dataset = MnistDataset(mode='test', return_label=False)
 
                 >>> # imperative mode
@@ -2399,7 +2399,7 @@ def summary(self, input_size=None, dtype=None):
                 >>> optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())
                 >>> model.prepare(optim, paddle.nn.CrossEntropyLoss())
                 >>> params_info = model.summary()
-                >>> # doctest: +SKIP
+                >>> # doctest: +SKIP('`paddle.static` can not run in xdoctest')
                 >>> print(params_info)
                 ---------------------------------------------------------------------------
                 Layer (type)       Input Shape          Output Shape         Param #
diff --git a/python/paddle/hapi/model_summary.py b/python/paddle/hapi/model_summary.py
index df5791a5fd70d..99cf123aaff34 100644
--- a/python/paddle/hapi/model_summary.py
+++ b/python/paddle/hapi/model_summary.py
@@ -60,7 +60,7 @@ def summary(net, input_size=None, dtypes=None, input=None):
             ...             nn.Conv2D(6, 16, 5, stride=1, padding=0),
             ...             nn.ReLU(),
             ...             nn.MaxPool2D(2, 2))
-            ...
+
             ...         if num_classes > 0:
             ...             self.fc = nn.Sequential(
             ...                 nn.Linear(400, 120),