[Typing] 修改一些示例代码中的类型错误 part 1 (#65461)

megemini · web-flow · commit 6cee769d744b · 2024-06-28T10:02:55.000+08:00
diff --git a/python/paddle/amp/debugging.py b/python/paddle/amp/debugging.py
@@ -88,7 +88,7 @@ def check_layer_numerics(func):
             ...         return x @ self._w + self._b
             ...
             >>> dtype = 'float32'
-            >>> x = paddle.rand([10, 2, 2], dtype=dtype)
+            >>> x = paddle.rand([10, 2, 2], dtype=dtype) # type: ignore
             >>> model = MyLayer(dtype)
             >>> x[0] = float(0)
             >>> loss = model(x)
diff --git a/python/paddle/autograd/saved_tensors_hooks.py b/python/paddle/autograd/saved_tensors_hooks.py
@@ -44,59 +44,63 @@ class saved_tensors_hooks:
 
     Examples:
         .. code-block:: python
+            :name: code-example1
 
-        >>> # Example1
-        >>> import paddle
-
-        >>> def pack_hook(x):
-        ...     print("Packing", x)
-        ...     return x.numpy()
-
-        >>> def unpack_hook(x):
-        ...     print("UnPacking", x)
-        ...     return paddle.to_tensor(x)
-
-        >>> a = paddle.ones([3,3])
-        >>> b = paddle.ones([3,3]) * 2
-        >>> a.stop_gradient = False
-        >>> b.stop_gradient = False
-        >>> with paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook):
-        ...     y = paddle.multiply(a, b)
-        >>> y.sum().backward()
-
-        >>> # Example2
-        >>> import paddle
-        >>> from paddle.autograd import PyLayer
-
-        >>> class cus_multiply(PyLayer):
-        ...     @staticmethod
-        ...     def forward(ctx, a, b):
-        ...         y = paddle.multiply(a, b)
-        ...         ctx.save_for_backward(a, b)
-        ...         return y
-        ...
-        ...     @staticmethod
-        ...     def backward(ctx, dy):
-        ...         a,b = ctx.saved_tensor()
-        ...         grad_a = dy * a
-        ...         grad_b = dy * b
-        ...         return grad_a, grad_b
-
-        >>> def pack_hook(x):
-        ...     print("Packing", x)
-        ...     return x.numpy()
-
-        >>> def unpack_hook(x):
-        ...     print("UnPacking", x)
-        ...     return paddle.to_tensor(x)
-
-        >>> a = paddle.ones([3,3])
-        >>> b = paddle.ones([3,3]) * 2
-        >>> a.stop_gradient = False
-        >>> b.stop_gradient = False
-        >>> with paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook):
-        ...     y = cus_multiply.apply(a, b)
-        >>> y.sum().backward()
+            >>> # Example1
+            >>> import paddle
+
+            >>> def pack_hook(x):
+            ...     print("Packing", x)
+            ...     return x.numpy()
+
+            >>> def unpack_hook(x):
+            ...     print("UnPacking", x)
+            ...     return paddle.to_tensor(x)
+
+            >>> a = paddle.ones([3,3])
+            >>> b = paddle.ones([3,3]) * 2
+            >>> a.stop_gradient = False
+            >>> b.stop_gradient = False
+            >>> with paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook):
+            ...     y = paddle.multiply(a, b)
+            >>> y.sum().backward()
+
+        .. code-block:: python
+            :name: code-example2
+
+            >>> # Example2
+            >>> import paddle
+            >>> from paddle.autograd import PyLayer
+
+            >>> class cus_multiply(PyLayer):
+            ...     @staticmethod
+            ...     def forward(ctx, a, b):
+            ...         y = paddle.multiply(a, b)
+            ...         ctx.save_for_backward(a, b)
+            ...         return y
+            ...
+            ...     @staticmethod
+            ...     def backward(ctx, dy):
+            ...         a,b = ctx.saved_tensor()
+            ...         grad_a = dy * a
+            ...         grad_b = dy * b
+            ...         return grad_a, grad_b
+
+            >>> def pack_hook(x):
+            ...     print("Packing", x)
+            ...     return x.numpy()
+
+            >>> def unpack_hook(x):
+            ...     print("UnPacking", x)
+            ...     return paddle.to_tensor(x)
+
+            >>> a = paddle.ones([3,3])
+            >>> b = paddle.ones([3,3]) * 2
+            >>> a.stop_gradient = False
+            >>> b.stop_gradient = False
+            >>> with paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook):
+            ...     y = cus_multiply.apply(a, b)
+            >>> y.sum().backward()
     """
 
     def __init__(self, pack_hook, unpack_hook):
diff --git a/python/paddle/base/framework.py b/python/paddle/base/framework.py
@@ -2868,7 +2868,7 @@ def size(self):
                 >>> x = paddle.static.data(name='x', shape=[3, 2, 1])
 
                 >>> # get the number of elements of the Variable
-                >>> y = x.size()
+                >>> y = x.size() # type: ignore
 
         """
 
diff --git a/python/paddle/distributed/communication/all_gather.py b/python/paddle/distributed/communication/all_gather.py
@@ -56,7 +56,7 @@ def all_gather(tensor_list, tensor, group=None, sync_op=True):
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> tensor_list = []
+            >>> tensor_list = [] # type: ignore
             >>> if dist.get_rank() == 0:
             ...     data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
             >>> else:
@@ -92,7 +92,7 @@ def all_gather_object(object_list, obj, group=None):
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> object_list = []
+            >>> object_list = [] # type: ignore
             >>> if dist.get_rank() == 0:
             ...     obj = {"foo": [1, 2, 3]}
             >>> else:
diff --git a/python/paddle/distributed/communication/all_to_all.py b/python/paddle/distributed/communication/all_to_all.py
@@ -45,7 +45,7 @@ def alltoall(in_tensor_list, out_tensor_list, group=None, sync_op=True):
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> out_tensor_list = []
+            >>> out_tensor_list = [] # type: ignore
             >>> if dist.get_rank() == 0:
             ...     data1 = paddle.to_tensor([[1, 2, 3], [4, 5, 6]])
             ...     data2 = paddle.to_tensor([[7, 8, 9], [10, 11, 12]])
diff --git a/python/paddle/distributed/communication/gather.py b/python/paddle/distributed/communication/gather.py
@@ -43,13 +43,13 @@ def gather(tensor, gather_list=None, dst=0, group=None, sync_op=True):
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> gather_list = []
+            >>> gather_list = [] # type: ignore
             >>> if dist.get_rank() == 0:
             ...     data = paddle.to_tensor([1, 2, 3])
             ...     dist.gather(data, gather_list, dst=0)
             >>> else:
             ...     data = paddle.to_tensor([4, 5, 6])
-            ...     dist.gather(data1, gather_list, dst=0)
+            ...     dist.gather(data, gather_list, dst=0)
             >>> print(gather_list)
             >>> # [[1, 2, 3], [4, 5, 6]] (2 GPUs, out for rank 0)
             >>> # [] (2 GPUs, out for rank 1)
diff --git a/python/paddle/distributed/communication/scatter.py b/python/paddle/distributed/communication/scatter.py
@@ -97,7 +97,7 @@ def scatter_object_list(
             >>> import paddle.distributed as dist
 
             >>> dist.init_parallel_env()
-            >>> out_object_list = []
+            >>> out_object_list = [] # type: ignore
             >>> if dist.get_rank() == 0:
             ...     in_object_list = [{'foo': [1, 2, 3]}, {'foo': [4, 5, 6]}]
             >>> else:
diff --git a/python/paddle/distributed/communication/stream/all_gather.py b/python/paddle/distributed/communication/stream/all_gather.py
@@ -155,7 +155,7 @@ def all_gather(
 
             >>> dist.init_parallel_env()
             >>> local_rank = dist.get_rank()
-            >>> tensor_list = []
+            >>> tensor_list = [] # type: ignore
             >>> if local_rank == 0:
             ...     data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
             >>> else:
diff --git a/python/paddle/distributed/parallel_with_gloo.py b/python/paddle/distributed/parallel_with_gloo.py
@@ -58,7 +58,7 @@ def gloo_init_parallel_env(rank_id, rank_num, server_endpoint):
             >>> from contextlib import closing
             >>> import socket
 
-            >>> port_set = set()
+            >>> port_set = set() # type: ignore
 
             >>> def find_free_port():
             ...     def _free_port():
@@ -153,7 +153,7 @@ def gloo_barrier():
             >>> from contextlib import closing
             >>> import socket
 
-            >>> port_set = set()
+            >>> port_set = set() # type: ignore
 
             >>> def find_free_port():
             ...     def _free_port():
@@ -211,7 +211,7 @@ def gloo_release():
             >>> from contextlib import closing
             >>> import socket
 
-            >>> port_set = set()
+            >>> port_set = set() # type: ignore
 
             >>> def find_free_port():
             ...     def _free_port():
