[paddle v2.0.0rc1: API fixs] assign/conv2d/conv2d_transpose/cast/ParamAttr (#29397)

* fix bug,test=develop

* fix DLTP-15151, paddle.ParamAttr API

* fix DLTP-15083/DLTP-15274, paddle.nn.functionl.assign paddle.cast API

* fix DLTP-15431/DLTP-15432, paddle.static.nn.conv2d paddle.static.nn.conv2d_transpose API

* fix DLTP-15083, paddle.nn.functionl.assign API

* fix DLTP-15431/DLTP-15432, paddle.static.nn.conv2d paddle.static.nn.conv2d_transpose API

* support in_dygraph_mode for cast op, test=develop

* fix bug,test=develop

* fix doc

* fix DLTP-15431/DLTP-15432, paddle.static.nn.conv2d paddle.static.nn.conv2d_transpose API, test=document_fix

python/paddle/fluid/layers/nn.py

@@ -1403,7 +1403,7 @@ def conv2d(input,
             W_{out}&= \\frac{(W_{in} + 2 * paddings[1] - (dilations[1] * (W_f - 1) + 1))}{strides[1]} + 1
 
     Args:
-        input (Variable): The input is 4-D Tensor with shape [N, C, H, W], the data type
+        input (Tensor): The input is 4-D Tensor with shape [N, C, H, W], the data type
             of input is float16 or float32 or float64.
         num_filters(int): The number of filter. It is as same as the output
             image channel.
@@ -1456,9 +1456,9 @@ def conv2d(input,
             `[batch_size, input_channels, input_height, input_width]`.
 
     Returns:
-        A Variable holding Tensor representing the conv2d, whose data type is the
-        same with input. If act is None, the tensor variable storing the convolution
-        result, and if act is not None, the tensor variable storing convolution
+        A Tensor representing the conv2d, whose data type is the
+        same with input. If act is None, the tensor storing the convolution
+        result, and if act is not None, the tensor storing convolution
         and non-linearity activation result.
 
     Raises:
@@ -1477,12 +1477,12 @@ def conv2d(input,
     Examples:
         .. code-block:: python
 
-          import paddle.fluid as fluid
           import paddle
           paddle.enable_static()
           
-          data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
-          conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3, act="relu")
+          data = paddle.static.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
+          conv2d = paddle.static.nn.conv2d(input=data, num_filters=2, filter_size=3, act="relu")
+          print(conv2d.shape) # [-1, 2, 30, 30]
     """
 
     check_variable_and_dtype(input, 'input', ['float16', 'float32', 'float64'],
@@ -3805,7 +3805,7 @@ def conv2d_transpose(input,
           conv2d_transpose can compute the kernel size automatically.
 
     Args:
-        input(Variable): 4-D Tensor with [N, C, H, W] or [N, H, W, C] format,
+        input(Tensor): 4-D Tensor with [N, C, H, W] or [N, H, W, C] format,
                          its data type is float32 or float64.
         num_filters(int): The number of the filter. It is as same as the output
             image channel.
@@ -3823,15 +3823,14 @@ def conv2d_transpose(input,
         stride(int|tuple, optional): The stride size. It means the stride in transposed convolution.
             If stride is a tuple, it must contain two integers, (stride_height, stride_width).
             Otherwise, stride_height = stride_width = stride. Default: stride = 1.
-        padding(int|list|str|tuple, optional): The padding size. The padding argument effectively adds
-             `dilation * (kernel - 1)` amount of zero-padding on both sides of input. If `padding` is a
-             string, either 'VALID' or 'SAME' supported, which is the padding algorithm.
-             If `padding` is a tuple or list, it could be in three forms:
-             `[pad_height, pad_width]` or
-            `[pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`, and
-            when `data_format` is `'NCHW'`,
-            `padding` can be in the form `[[0,0], [0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right]]`.
-            when `data_format` is `'NHWC'`, `padding` can be in the form
+        padding(str|int|list|tuple, optional): The padding size. It means the number of zero-paddings 
+            on both sides for each dimension. If `padding` is a string, either 'VALID' or 
+            'SAME' which is the padding algorithm. If `padding` is a tuple or list,
+            it could be in three forms: `[pad_height, pad_width]` or 
+            `[pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`,
+            and when `data_format` is `"NCHW"`, `padding` can be in the form 
+            `[[0,0], [0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right]]`.
+            when `data_format` is `"NHWC"`, `padding` can be in the form 
             `[[0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`.
             Default: padding = 0.
         dilation(int|tuple, optional): The dilation size. It means the spacing between the kernel points.
@@ -3869,11 +3868,11 @@ def conv2d_transpose(input,
             `[batch_size, input_channels, input_height, input_width]`.
 
     Returns:
-        A Variable holding Tensor representing the conv2d_transpose, whose
+        A Tensor representing the conv2d_transpose, whose
         data type is the same with input and shape is (num_batches, channels, out_h,
-        out_w) or (num_batches, out_h, out_w, channels). If act is None, the tensor variable
+        out_w) or (num_batches, out_h, out_w, channels). If act is None, the tensor 
         storing the transposed convolution result, and if act is not None, the
-        tensor variable storing transposed convolution and non-linearity activation
+        tensor storing transposed convolution and non-linearity activation
         result.
 
     Raises:
@@ -3892,11 +3891,12 @@ def conv2d_transpose(input,
     Examples:
        .. code-block:: python
 
-          import paddle.fluid as fluid
           import paddle
           paddle.enable_static()
-          data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
-          conv2d_transpose = fluid.layers.conv2d_transpose(input=data, num_filters=2, filter_size=3)
+
+          data = paddle.static.data(name='data', shape=[None, 3, 32, 32], dtype='float32')
+          conv2d_transpose = paddle.static.nn.conv2d_transpose(input=data, num_filters=2, filter_size=3)
+          print(conv2d_transpose.shape) # [-1, 2, 34, 34]
     """
     assert param_attr is not False, "param_attr should not be False in conv2d_transpose."
     if data_format not in ['NCHW', 'NHWC']:

python/paddle/fluid/layers/tensor.py

@@ -203,7 +203,7 @@ def create_global_var(shape,
 def cast(x, dtype):
     """
 
-    This OP takes in the Variable :attr:`x` with :attr:`x.dtype` and casts it
+    This OP takes in the Tensor :attr:`x` with :attr:`x.dtype` and casts it
     to the output with :attr:`dtype`. It's meaningless if the output dtype
     equals the input dtype, but it's fine if you do so.
 
@@ -539,20 +539,20 @@ def assign(input, output=None):
     The OP copies the :attr:`input` to the :attr:`output`.
 
     Parameters:
-        input (Variable|numpy.ndarray): A tensor or numpy ndarray, its data type supports
+        input (Tensor|numpy.ndarray): A tensor or numpy ndarray, its data type supports
             float16, float32, float64, int32 and int64.
-        output (Variable, optional): A tensor. If :attr:`output` is None, a new tensor will
+        output (Tensor, optional): A tensor. If :attr:`output` is None, a new tensor will
             be created as :attr:`output`. Default: None.
 
     Returns:
-        Variable: A tensor with the same shape, data type and value as :attr:`input`.
+        Tensor: A tensor with the same shape, data type and value as :attr:`input`.
 
     Examples:
         .. code-block:: python
 
           import paddle
           import numpy as np
-          data = paddle.fill_constant(shape=[3, 2], value=2.5, dtype='float64') # [[2.5, 2.5], [2.5, 2.5], [2.5, 2.5]]
+          data = paddle.full(shape=[3, 2], fill_value=2.5, dtype='float64') # [[2.5, 2.5], [2.5, 2.5], [2.5, 2.5]]
           array = np.array([[1, 1],
                             [3, 4],
                             [1, 3]]).astype(np.int64)

python/paddle/fluid/param_attr.py

@@ -37,8 +37,8 @@ class ParamAttr(object):
     Note:
         ``gradient_clip`` of ``ParamAttr`` HAS BEEN DEPRECATED since 2.0. 
         Please use ``need_clip`` in ``ParamAttr`` to speficiy the clip scope.
-        There are three clipping strategies: :ref:`api_paddle_nn_GradientClipByGlobalNorm` , 
-        :ref:`api_fluid_clip_GradientClipByNorm` , :ref:`api_fluid_clip_GradientClipByValue` .
+        There are three clipping strategies: :ref:`api_paddle_nn_ClipGradByGlobalNorm` , 
+        :ref:`api_paddle_nn_ClipGradByNorm` , :ref:`api_paddle_nn_ClipGradByValue` .
 
     Parameters:
         name (str, optional): The parameter's name. Default None, meaning that the name
@@ -50,8 +50,8 @@ class ParamAttr(object):
                 optimize is the global learning rates times the parameter's learning rate times
                 the factor of learning rate scheduler. Default 1.0.
         regularizer (WeightDecayRegularizer, optional): Regularization strategy. There are two method: 
-                :ref:`api_fluid_regularizer_L1Decay` , :ref:`api_fluid_regularizer_L2Decay` . If 
-                regularizer is also set in ``optimizer`` (such as :ref:`api_fluid_optimizer_SGDOptimizer` ), 
+                :ref:`api_paddle_regularizer_L1Decay` , :ref:`api_paddle_regularizer_L2Decay` . If 
+                regularizer is also set in ``optimizer`` (such as :ref:`api_paddle_optimizer_SGD` ), 
                 that regularizer setting in optimizer will be ignored. Default None, meaning there is 
                 no regularization.
         trainable (bool): Whether this parameter is trainable. Default True.
@@ -63,7 +63,6 @@ class ParamAttr(object):
         .. code-block:: python
 
             import paddle
-            paddle.enable_static()
 
             weight_attr = paddle.ParamAttr(name="weight",
                                            learning_rate=0.5,