update the shape [1] instruction to 0D tensor (#62875)

ooooo-create · web-flow · commit 0422de022cc5 · 2024-03-25T16:46:26.000+08:00
diff --git a/python/paddle/device/cuda/__init__.py b/python/paddle/device/cuda/__init__.py
@@ -222,7 +222,7 @@ def max_memory_allocated(device=None):
 
     Note:
         The size of GPU memory allocated to tensor is 256-byte aligned in Paddle, which may larger than the memory size that tensor actually need.
-        For instance, a float32 tensor with shape [1] in GPU will take up 256 bytes memory, even though storing a float32 data requires only 4 bytes.
+        For instance, a float32 0-D Tensor with shape [] in GPU will take up 256 bytes memory, even though storing a float32 data requires only 4 bytes.
 
     Args:
         device(paddle.CUDAPlace or int or str, optional): The device, the id of the device or
@@ -290,7 +290,7 @@ def memory_allocated(device=None):
 
     Note:
         The size of GPU memory allocated to tensor is 256-byte aligned in Paddle, which may be larger than the memory size that tensor actually need.
-        For instance, a float32 tensor with shape [1] in GPU will take up 256 bytes memory, even though storing a float32 data requires only 4 bytes.
+        For instance, a float32 0-D Tensor with shape [] in GPU will take up 256 bytes memory, even though storing a float32 data requires only 4 bytes.
 
     Args:
         device(paddle.CUDAPlace or int or str, optional): The device, the id of the device or
diff --git a/python/paddle/incubate/layers/nn.py b/python/paddle/incubate/layers/nn.py
@@ -1317,8 +1317,8 @@ def fused_bn_add_act(
         y (Tensor): The rank of input tensor can be 2, 3, 4, 5. The data type
             is float16.
         momentum (float|Tensor, optional): The value used for the moving_mean and
-            moving_var computation. This should be a float number or a tensor with
-            shape [1] and data type as float32. The updated formula is:
+            moving_var computation. This should be a float number or a 0-D Tensor with
+            shape [] and data type as float32. The updated formula is:
             :math:`moving\_mean = moving\_mean * momentum + new\_mean * (1. - momentum)`
             :math:`moving\_var = moving\_var * momentum + new\_var * (1. - momentum)`
             Default is 0.9.
diff --git a/python/paddle/incubate/xpu/resnet_block.py b/python/paddle/incubate/xpu/resnet_block.py
@@ -346,8 +346,8 @@ class ResNetBasicBlock(Layer):
         act (str, optional): Activation type, if it is set to None, activation is not appended.
             Default: None
         momentum (float, optional): The value used for the moving_mean and
-            moving_var computation. This should be a float number or a Tensor with
-            shape [1] and data type as float32. The updated formula is:
+            moving_var computation. This should be a float number or a 0-D Tensor with
+            shape [] and data type as float32. The updated formula is:
             :math:`moving\_mean = moving\_mean * momentum + new\_mean * (1. - momentum)`
             :math:`moving\_var = moving\_var * momentum + new\_var * (1. - momentum)`
             Default is 0.9.
diff --git a/python/paddle/optimizer/adam.py b/python/paddle/optimizer/adam.py
@@ -63,13 +63,13 @@ class Adam(Optimizer):
         learning_rate (float|LRScheduler, optional): The learning rate used to update ``Parameter``.
             It can be a float value or a LRScheduler. The default value is 0.001.
         beta1 (float|Tensor, optional): The exponential decay rate for the 1st moment estimates.
-            It should be a float number or a Tensor with shape [1] and data type as float32.
+            It should be a float number or a 0-D Tensor with shape [] and data type as float32.
             The default value is 0.9.
         beta2 (float|Tensor, optional): The exponential decay rate for the 2nd moment estimates.
-            It should be a float number or a Tensor with shape [1] and data type as float32.
+            It should be a float number or a 0-D Tensor with shape [] and data type as float32.
             The default value is 0.999.
         epsilon (float|Tensor, optional): A small float value for numerical stability.
-            It should be a float number or a Tensor with shape [1] and data type as float32.
+            It should be a float number or a 0-D Tensor with shape [] and data type as float32.
             The default value is 1e-08.
         parameters (list|tuple, optional): List/Tuple of ``Tensor`` to update to minimize ``loss``.
             This parameter is required in dygraph mode. And you can specify different options for
diff --git a/python/paddle/optimizer/adamw.py b/python/paddle/optimizer/adamw.py
@@ -67,10 +67,10 @@ class AdamW(Optimizer):
             represents the scale of base learning_rate.
             The default value is None in static graph mode, at this time all parameters will be updated.
         beta1 (float|Tensor, optional): The exponential decay rate for the 1st moment estimates.
-            It should be a float number or a Tensor with shape [1] and data type as float32.
+            It should be a float number or a 0-D Tensor with shape [] and data type as float32.
             The default value is 0.9.
         beta2 (float|Tensor, optional): The exponential decay rate for the 2nd moment estimates.
-            It should be a float number or a Tensor with shape [1] and data type as float32.
+            It should be a float number or a 0-D Tensor with shape [] and data type as float32.
             The default value is 0.999.
         epsilon (float, optional): A small float value for numerical stability.
             The default value is 1e-08.
diff --git a/python/paddle/optimizer/lr.py b/python/paddle/optimizer/lr.py
@@ -2615,7 +2615,7 @@ def noam_decay(d_model, warmup_steps, learning_rate=1.0):
         d_model(Variable): The dimensionality of input and output of model.
         warmup_steps(Variable): A super parameter.
         learning_rate(Variable|float|int): The initial learning rate. If the type
-            is Variable, it's a tensor with shape [1], the data type can be
+            is Variable, it's a 0-D Tensor with shape [], the data type can be
             float32 or float64. It also can be set to python int number. Default 1.0
 
     Returns:
diff --git a/python/paddle/sparse/unary.py b/python/paddle/sparse/unary.py
@@ -960,13 +960,13 @@ def slice(x, axes, starts, ends, name=None):
     Args:
         x (Tensor): The input Tensor (``SparseCooTensor`` or ``SparseCsrTensor``), it's data type should be ``float16``, ``float32``, ``float64``, ``int32``, ``int64``.
         axes (list|tuple|Tensor): The data type is ``int32``.If ``axes`` is a list or tuple, the elements of
-                it should be integers or Tensors with shape [1]. If ``axes`` is a Tensor, it should be a 1-D Tensor.
+                it should be integers or a 0-D Tensor with shape []. If ``axes`` is a Tensor, it should be a 1-D Tensor.
                 Axes that `starts` and `ends` apply to.
         starts (list|tuple|Tensor): The data type is ``int32``. If ``starts`` is a list or tuple, the elements of
-                it should be integers or Tensors with shape [1]. If ``starts`` is a Tensor, it should be a 1-D Tensor.
+                it should be integers or a 0-D Tensor with shape []. If ``starts`` is a Tensor, it should be a 1-D Tensor.
                 It represents starting indices of corresponding axis in ``axes``.
         ends (list|tuple|Tensor): The data type is ``int32``. If ``ends`` is a list or tuple, the elements of
-                it should be integers or Tensors with shape [1]. If ``ends`` is a Tensor, it should be a 1-D Tensor.
+                it should be integers or a 0-D Tensor with shape []. If ``ends`` is a Tensor, it should be a 1-D Tensor.
                 It represents ending indices of corresponding axis in ``axes``.
 
     Returns:
diff --git a/python/paddle/static/nn/common.py b/python/paddle/static/nn/common.py
@@ -2700,8 +2700,8 @@ def batch_norm(
         is_test (bool, Default False): A flag indicating whether it is in
             test phrase or not.
         momentum(float|Tensor, Default 0.9): The value used for the moving_mean and
-            moving_var computation. This should be a float number or a Tensor with
-            shape [1] and data type as float32. The updated formula is:
+            moving_var computation. This should be a float number or a 0-D Tensor with
+            shape [] and data type as float32. The updated formula is:
             :math:`moving\_mean = moving\_mean * momentum + new\_mean * (1. - momentum)`
             :math:`moving\_var = moving\_var * momentum + new\_var * (1. - momentum)`
             Default is 0.9.
diff --git a/python/paddle/tensor/array.py b/python/paddle/tensor/array.py
@@ -32,7 +32,7 @@ def array_length(array):
         array (list|Tensor): The input array that will be used to compute the length. In dynamic mode, ``array`` is a Python list. But in static graph mode, array is a Tensor whose VarType is LOD_TENSOR_ARRAY.
 
     Returns:
-        Tensor: 1-D Tensor with shape [1], which is the length of array.
+        Tensor: 0-D Tensor with shape [], which is the length of array.
 
     Examples:
         .. code-block:: python
@@ -169,7 +169,7 @@ def array_write(x, i, array=None):
     Args:
         x (Tensor): The input data to be written into array. It's multi-dimensional
             Tensor or LoDTensor. Data type: float32, float64, int32, int64 and bool.
-        i (Tensor): 1-D Tensor with shape [1], which represents the position into which
+        i (Tensor): 0-D Tensor with shape [], which represents the position into which
             ``x`` is written.
         array (list|Tensor, optional): The array into which ``x`` is written. The default value is None,
             when a new array will be created and returned as a result. In dynamic mode, ``array`` is a Python list.
diff --git a/python/paddle/tensor/manipulation.py b/python/paddle/tensor/manipulation.py
@@ -3617,7 +3617,7 @@ def unbind(input, axis=0):
 
     Args:
         input (Tensor): The input variable which is an N-D Tensor, data type being bool, float16, float32, float64, int32, int64, complex64 or complex128.
-        axis (int32|int64, optional): A scalar with type ``int32|int64`` shape [1]. The dimension along which to unbind.
+        axis (int32|int64, optional): A 0-D Tensor with shape [] and type is ``int32|int64``. The dimension along which to unbind.
             If :math:`axis < 0`, the dimension to unbind along is :math:`rank(input) + axis`. Default is 0.
     Returns:
         list(Tensor), The list of segmented Tensor variables.
