(fluid清理)remove reshape in nn.py under fluid (#47967)

* remove reshape in nn.py under fluid

* remove reshape reference

* fix test case

* fix test case in distribution.uniform

* remove fluid reshape reference

python/paddle/distribution/normal.py

@@ -184,7 +184,7 @@ class Normal(distribution.Distribution):
             zero_tmp = tensor.fill_constant_batch_size_like(
                 self.loc + self.scale, batch_shape + shape, self.dtype, 0.0
             )
-            zero_tmp_reshape = nn.reshape(zero_tmp, output_shape)
+            zero_tmp_reshape = paddle.reshape(zero_tmp, output_shape)
             zero_tmp_shape = nn.shape(zero_tmp_reshape)
             normal_random_tmp = nn.gaussian_random(
                 zero_tmp_shape, mean=0.0, std=1.0, seed=seed, dtype=self.dtype
@@ -199,7 +199,7 @@ class Normal(distribution.Distribution):
             ) * (tensor.zeros(output_shape, dtype=self.dtype) + self.scale)
             output = elementwise_add(output, self.loc, name=name)
             if self.all_arg_is_float:
-                return nn.reshape(output, shape, name=name)
+                return paddle.reshape(output, shape, name=name)
             else:
                 return output
 

python/paddle/distribution/uniform.py

@@ -28,6 +28,7 @@ from paddle.fluid.layers import (
     nn,
     tensor,
 )
+import paddle
 
 
 class Uniform(distribution.Distribution):
@@ -174,8 +175,8 @@ class Uniform(distribution.Distribution):
                 max=1.0,
                 seed=seed,
             )
-            zero_tmp_reshape = nn.reshape(zero_tmp, output_shape)
-            uniform_random_tmp_reshape = nn.reshape(
+            zero_tmp_reshape = paddle.reshape(zero_tmp, output_shape)
+            uniform_random_tmp_reshape = paddle.reshape(
                 uniform_random_tmp, output_shape
             )
             output = uniform_random_tmp_reshape * (
@@ -193,7 +194,7 @@ class Uniform(distribution.Distribution):
             )
             output = elementwise_add(output, self.low, name=name)
             if self.all_arg_is_float:
-                return nn.reshape(output, shape, name=name)
+                return paddle.reshape(output, shape, name=name)
             else:
                 return output
 

python/paddle/fluid/contrib/layers/nn.py

@@ -36,7 +36,8 @@ from paddle.fluid import core
 from paddle.fluid.param_attr import ParamAttr
 
 from paddle.fluid.framework import Variable, convert_np_dtype_to_dtype_
-from paddle.fluid.layers import slice, reshape
+from paddle.fluid.layers import slice
+import paddle
 import warnings
 from paddle import _C_ops, _legacy_C_ops
 
@@ -1549,17 +1550,17 @@ def tdm_sampler(
                 mask, axes=[1], starts=[start_offset], ends=[end_offset]
             )
 
-            layer_samples = reshape(
+            layer_samples = paddle.reshape(
                 layer_samples, [-1, layer_sample_num + positive_flag, 1]
             )
             layer_samples.stop_gradient = True
 
-            layer_labels = reshape(
+            layer_labels = paddle.reshape(
                 layer_labels, [-1, layer_sample_num + positive_flag, 1]
             )
             layer_labels.stop_gradient = True
 
-            layer_mask = reshape(
+            layer_mask = paddle.reshape(
                 layer_mask, [-1, layer_sample_num + positive_flag, 1]
             )
             layer_mask.stop_gradient = True

python/paddle/fluid/contrib/layers/rnn_impl.py

@@ -19,6 +19,7 @@ from paddle.fluid import layers, unique_name
 from paddle.fluid.dygraph import Layer
 from paddle.fluid.dygraph.layer_object_helper import LayerObjectHelper
 from paddle.fluid.layers.control_flow import StaticRNN
+import paddle
 
 __all__ = ['BasicGRUUnit', 'basic_gru', 'BasicLSTMUnit', 'basic_lstm']
 
@@ -339,7 +340,7 @@ def basic_gru(
     if bidirectional:
         direc_num = 2
     if init_hidden:
-        init_hidden = layers.reshape(
+        init_hidden = paddle.reshape(
             init_hidden, shape=[num_layers, direc_num, -1, hidden_size]
         )
 
@@ -394,7 +395,7 @@ def basic_gru(
             last_hidden_array.append(last_hidden)
 
         last_hidden_output = layers.concat(last_hidden_array, axis=0)
-        last_hidden_output = layers.reshape(
+        last_hidden_output = paddle.reshape(
             last_hidden_output, shape=[num_layers, -1, hidden_size]
         )
 
@@ -419,7 +420,7 @@ def basic_gru(
         rnn_out = layers.concat([fw_rnn_out, bw_rnn_out], axis=2)
         last_hidden = layers.concat([fw_last_hidden, bw_last_hidden], axis=1)
 
-        last_hidden = layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[num_layers * direc_num, -1, hidden_size]
         )
 
@@ -625,10 +626,10 @@ def basic_lstm(
         direc_num = 2
         # convert to [num_layers, 2, batch_size, hidden_size]
     if init_hidden:
-        init_hidden = layers.reshape(
+        init_hidden = paddle.reshape(
             init_hidden, shape=[num_layers, direc_num, -1, hidden_size]
         )
-        init_cell = layers.reshape(
+        init_cell = paddle.reshape(
             init_cell, shape=[num_layers, direc_num, -1, hidden_size]
         )
 
@@ -701,11 +702,11 @@ def basic_lstm(
             last_cell_array.append(last_cell)
 
         last_hidden_output = layers.concat(last_hidden_array, axis=0)
-        last_hidden_output = layers.reshape(
+        last_hidden_output = paddle.reshape(
             last_hidden_output, shape=[num_layers, -1, hidden_size]
         )
         last_cell_output = layers.concat(last_cell_array, axis=0)
-        last_cell_output = layers.reshape(
+        last_cell_output = paddle.reshape(
             last_cell_output, shape=[num_layers, -1, hidden_size]
         )
 
@@ -729,12 +730,12 @@ def basic_lstm(
 
         rnn_out = layers.concat([fw_rnn_out, bw_rnn_out], axis=2)
         last_hidden = layers.concat([fw_last_hidden, bw_last_hidden], axis=1)
-        last_hidden = layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[num_layers * direc_num, -1, hidden_size]
         )
 
         last_cell = layers.concat([fw_last_cell, bw_last_cell], axis=1)
-        last_cell = layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[num_layers * direc_num, -1, hidden_size]
         )
 

python/paddle/fluid/contrib/tests/test_model_cast_to_bf16.py

@@ -107,17 +107,17 @@ class TestModelCastBF16(unittest.TestCase):
 
             ret = layers.elementwise_add(t, tt)
             ret = layers.elementwise_mul(ret, t)
-            ret = layers.reshape(ret, [0, 0])
+            ret = paddle.reshape(ret, [0, 0])
 
             with amp.bf16.bf16_guard():
                 ret_bf16 = layers.elementwise_add(t_bf16, tt_bf16)
                 ret_bf16 = layers.elementwise_mul(ret_bf16, t_bf16)
-                ret_bf16 = layers.reshape(ret_bf16, [0, 0])
+                ret_bf16 = paddle.reshape(ret_bf16, [0, 0])
 
             with amp.bf16.bf16_guard():
                 ret_fp32bf16 = layers.elementwise_add(t, tt)
                 ret_fp32bf16 = layers.elementwise_mul(ret_fp32bf16, t)
-                ret_fp32bf16 = layers.reshape(ret_fp32bf16, [0, 0])
+                ret_fp32bf16 = paddle.reshape(ret_fp32bf16, [0, 0])
 
             (
                 static_ret_bf16,
@@ -148,7 +148,8 @@ class TestModelCastBF16(unittest.TestCase):
 
             with amp.bf16.bf16_guard():
                 ret = layers.elementwise_add(t, tt)
-                ret = layers.reshape(ret, [0, 0], act='elu')
+                ret = paddle.reshape(ret, [0, 0])
+                ret = paddle.nn.functional.elu(ret)
                 ret = layers.elementwise_mul(ret, t)
             ret = layers.elementwise_add(ret, tt)
 

python/paddle/fluid/dygraph/parallel.py

@@ -320,7 +320,7 @@ def _coalesce_tensors(var_groups):
         for g_var in grad_vars:
             g_var_shapes.append(g_var.shape)
             flattened_vars.append(
-                nn.reshape(x=g_var, shape=[np.prod(g_var.shape)])
+                paddle.reshape(x=g_var, shape=[np.prod(g_var.shape)])
             )
         coalesced_grad = nn.concat(flattened_vars)
         coalesced_grads_and_grad_vars.append(

python/paddle/fluid/layer_helper_base.py

@@ -14,6 +14,7 @@
 
 import copy
 import numpy as np
+import paddle
 
 from .framework import (
     Variable,
@@ -114,7 +115,7 @@ class LayerHelperBase:
             )
 
     def _create_weight_normalize(self, attr, shape, dtype):
-        from .layers import elementwise_mul, elementwise_div, reshape
+        from .layers import elementwise_mul, elementwise_div
 
         # Remove these ops when LayerHelper and layers support indicating
         # program and block.
@@ -275,7 +276,7 @@ class LayerHelperBase:
                 x=v,
                 y=scale
                 if dim is None
-                else reshape(x=scale, shape=[v.shape[dim]]),
+                else paddle.reshape(x=scale, shape=[v.shape[dim]]),
                 axis=-1 if dim is None else dim,
             )
             # To serialize the original parameter for inference, maybe a

python/paddle/fluid/layers/detection.py

@@ -328,8 +328,8 @@ def retinanet_target_assign(
     bbox_inside_weight.stop_gradient = True
     fg_num.stop_gradient = True
 
-    cls_logits = nn.reshape(x=cls_logits, shape=(-1, num_classes))
-    bbox_pred = nn.reshape(x=bbox_pred, shape=(-1, 4))
+    cls_logits = paddle.reshape(x=cls_logits, shape=(-1, num_classes))
+    bbox_pred = paddle.reshape(x=bbox_pred, shape=(-1, 4))
     predicted_cls_logits = paddle.gather(cls_logits, score_index)
     predicted_bbox_pred = paddle.gather(bbox_pred, loc_index)
 
@@ -510,8 +510,8 @@ def rpn_target_assign(
     target_bbox.stop_gradient = True
     bbox_inside_weight.stop_gradient = True
 
-    cls_logits = nn.reshape(x=cls_logits, shape=(-1, 1))
-    bbox_pred = nn.reshape(x=bbox_pred, shape=(-1, 4))
+    cls_logits = paddle.reshape(x=cls_logits, shape=(-1, 1))
+    bbox_pred = paddle.reshape(x=bbox_pred, shape=(-1, 4))
     predicted_cls_logits = paddle.gather(cls_logits, score_index)
     predicted_bbox_pred = paddle.gather(bbox_pred, loc_index)
 
@@ -1750,7 +1750,7 @@ def ssd_loss(
 
     # 2. Compute confidence for mining hard examples
     # 2.1. Get the target label based on matched indices
-    gt_label = nn.reshape(
+    gt_label = paddle.reshape(
         x=gt_label, shape=(len(gt_label.shape) - 1) * (0,) + (-1, 1)
     )
     gt_label.stop_gradient = True
@@ -1769,9 +1769,7 @@ def ssd_loss(
     actual_shape.stop_gradient = True
     # shape=(-1, 0) is set for compile-time, the correct shape is set by
     # actual_shape in runtime.
-    conf_loss = nn.reshape(
-        x=conf_loss, shape=(-1, 0), actual_shape=actual_shape
-    )
+    conf_loss = paddle.reshape(x=conf_loss, shape=actual_shape)
     conf_loss.stop_gradient = True
     neg_indices = helper.create_variable_for_type_inference(dtype='int32')
     dtype = matched_indices.dtype
@@ -1848,7 +1846,7 @@ def ssd_loss(
     # reshape to [N, Np], N is the batch size and Np is the prior box number.
     # shape=(-1, 0) is set for compile-time, the correct shape is set by
     # actual_shape in runtime.
-    loss = nn.reshape(x=loss, shape=(-1, 0), actual_shape=actual_shape)
+    loss = paddle.reshape(x=loss, shape=actual_shape)
     loss = nn.reduce_sum(loss, dim=1, keep_dim=True)
     if normalize:
         normalizer = nn.reduce_sum(target_loc_weight)
@@ -2477,9 +2475,9 @@ def multi_box_head(
         box = tensor.concat(reshaped_boxes)
         var = tensor.concat(reshaped_vars)
         mbox_locs_concat = tensor.concat(mbox_locs, axis=1)
-        mbox_locs_concat = nn.reshape(mbox_locs_concat, shape=[0, -1, 4])
+        mbox_locs_concat = paddle.reshape(mbox_locs_concat, shape=[0, -1, 4])
         mbox_confs_concat = tensor.concat(mbox_confs, axis=1)
-        mbox_confs_concat = nn.reshape(
+        mbox_confs_concat = paddle.reshape(
             mbox_confs_concat, shape=[0, -1, num_classes]
         )
 

python/paddle/fluid/layers/distributions.py

@@ -228,7 +228,7 @@ class Uniform(Distribution):
                 uniform_random_tmp * (zero_tmp + self.high - self.low)
                 + self.low
             )
-            return nn.reshape(output, output_shape)
+            return paddle.reshape(output, output_shape)
         else:
             output_shape = shape + batch_shape
             output = (
@@ -240,7 +240,7 @@ class Uniform(Distribution):
                 + self.low
             )
             if self.all_arg_is_float:
-                return nn.reshape(output, shape)
+                return paddle.reshape(output, shape)
             else:
                 return output
 
@@ -382,7 +382,7 @@ class Normal(Distribution):
                 zero_tmp_shape, mean=0.0, std=1.0, seed=seed
             )
             output = normal_random_tmp * (zero_tmp + self.scale) + self.loc
-            return nn.reshape(output, output_shape)
+            return paddle.reshape(output, output_shape)
         else:
             output_shape = shape + batch_shape
             output = (
@@ -394,7 +394,7 @@ class Normal(Distribution):
                 + self.loc
             )
             if self.all_arg_is_float:
-                return nn.reshape(output, shape)
+                return paddle.reshape(output, shape)
             else:
                 return output
 

python/paddle/fluid/layers/nn.py

@@ -101,7 +101,6 @@ __all__ = [
     'smooth_l1',
     'one_hot',
     'autoincreased_step_counter',
-    'reshape',
     'squeeze',
     'unsqueeze',
     'lod_reset',
@@ -6234,240 +6233,6 @@ def autoincreased_step_counter(counter_name=None, begin=1, step=1):
     return counter
 
 
-def reshape(x, shape, actual_shape=None, act=None, inplace=False, name=None):
-    r"""
-    :alias_main: paddle.reshape
-	:alias: paddle.reshape,paddle.tensor.reshape,paddle.tensor.manipulation.reshape
-
-    This operator changes the shape of ``x`` without changing its data.
-
-    The target shape can be given by ``shape`` or ``actual_shape``.
-    When ``shape`` and ``actual_shape`` are set at the same time,
-    ``actual_shape`` has a higher priority than ``shape``
-    but at this time ``shape`` can only be an integer list or tuple, and ``shape`` still should be set correctly to
-    guarantee shape inference in compile-time.
-
-    Some tricks exist when specifying the target shape.
-
-    1. -1 means the value of this dimension is inferred from the total element
-    number of x and remaining dimensions. Thus one and only one dimension can
-    be set -1.
-
-    2. 0 means the actual dimension value is going to be copied from the
-    corresponding dimension of x. The index of 0s in shape can not exceed
-    the dimension of x.
-
-    Here are some examples to explain it.
-
-    1. Given a 3-D tensor x with a shape [2, 4, 6], and the target shape
-    is [6, 8], the reshape operator will transform x into a 2-D tensor with
-    shape [6, 8] and leaving x's data unchanged.
-
-    2. Given a 3-D tensor x with a shape [2, 4, 6], and the target shape
-    specified is [2, 3, -1, 2], the reshape operator will transform x into a
-    4-D tensor with shape [2, 3, 4, 2] and leaving x's data unchanged. In this
-    case, one dimension of the target shape is set to -1, the value of this
-    dimension is inferred from the total element number of x and remaining
-    dimensions.
-
-    3. Given a 3-D tensor x with a shape [2, 4, 6], and the target shape
-    is [-1, 0, 3, 2], the reshape operator will transform x into a 4-D tensor
-    with shape [2, 4, 3, 2] and leaving x's data unchanged. In this case,
-    besides -1, 0 means the actual dimension value is going to be copied from
-    the corresponding dimension of x.
-
-    **Note**:
-        The parameter ``actual_shape`` will be deprecated in the future and only use ``shape`` instead to represent the target shape.
-
-    Args:
-        x(Tensor): An N-D Tensor. The data type is ``float32``, ``float64``, ``int32`` or ``int64``.
-        shape(list|tuple|Tensor): Define the target shape. At most one dimension of the target shape can be -1.
-                        The data type is ``int32`` . If ``shape`` is a list or tuple, the elements of it should be integers or Tensors with shape [1].
-                        If ``shape`` is an Tensor, it should be an 1-D Tensor .
-        actual_shape(variable, optional): An 1-D ``Tensor`` or ``LoDTensor`` . The data type is ``int32`` . If provided, reshape
-                                according to this given shape rather than ``shape`` specifying shape.
-                                That is to say ``actual_shape`` has a higher priority
-                                than ``shape(list|tuple)`` but not ``shape(Tensor)``. \
-                                This argument ``actual_shape`` will be removed in a future version. \
-                                Instructions for updating: ``actual_shape`` will be removed in future versions and replaced by ``shape``.
-        act (str, optional): The non-linear activation to be applied to the reshaped input. Default None.
-        inplace(bool, optional): If ``inplace`` is True, the input and output of ``layers.reshape``
-                       are the same variable. Otherwise, the input and output of
-                       ``layers.reshape`` are different variable. Default False. Note that if ``x``
-                       is more than one OPs' input, ``inplace`` must be False.
-        name(str, optional): The default value is None. Normally there is no need for user to set this property.
-                            For more information, please refer to :ref:`api_guide_Name` .
-
-    Returns:
-        Tensor: A reshaped Tensor with the same data type as ``x``. It is a new tensor variable if ``inplace`` is ``False``, otherwise it is ``x``. If ``act`` is None, return the reshaped tensor variable, otherwise return the activated tensor variable.
-
-
-    Examples:
-        .. code-block:: python
-
-            import paddle
-            import paddle.fluid as fluid
-            paddle.enable_static()
-
-            # example 1:
-            # attr shape is a list which doesn't contain Tensors.
-            data_1 = fluid.data(
-              name='data_1', shape=[2, 4, 6], dtype='float32')
-            reshaped_1 = fluid.layers.reshape(
-              x=data_1, shape=[-1, 0, 3, 2])
-            # the shape of reshaped_1 is [2,4,3,2].
-
-            # example 2:
-            # attr shape is a list which contains Tensors.
-            data_2 = fluid.layers.fill_constant([2,25], "int32", 3)
-            dim = fluid.layers.fill_constant([1], "int32", 5)
-            reshaped_2 = fluid.layers.reshape(data_2, shape=[dim, 10])
-            # the shape of reshaped_2 is [5,10].
-
-            # example 3:
-            data_3 = fluid.data(
-              name="data_3", shape=[2,4,6], dtype='float32')
-            reshaped_3 = fluid.layers.reshape(x=data_3, shape=[6,8])
-            # the shape of reshaped_3 is [6,8].
-    """
-    if in_dygraph_mode():
-        tmp_tensor_type = core.eager.Tensor
-        # TODO(zhiqiu): enable inplace in dygraph mode.
-        if inplace:
-            warnings.warn(
-                "Inplace on reshape is not allowed and will be discarded in dygraph mode currently."
-            )
-        if isinstance(shape, (list, tuple)):
-            shape = [
-                item.numpy().item(0) if isinstance(item, Variable) else item
-                for item in shape
-            ]
-            out = _C_ops.reshape(x, shape)
-        elif isinstance(shape, tmp_tensor_type):
-            # TODO: Tensor shape in reshape has not been tested
-            shape.stop_gradient = True
-            out = _C_ops.reshape(x, shape)
-        else:
-            raise ValueError(
-                "shape must be an instance of `list`, `tuple` or `Variable`,"
-                " got '{}.'".format(type(shape))
-            )
-
-        return dygraph_utils._append_activation_in_dygraph(out, act)
-    else:
-        if _in_legacy_dygraph():
-            tmp_tensor_type = Variable
-            if inplace:
-                warnings.warn(
-                    "Inplace on reshape is not allowed and will be discarded in dygraph mode currently."
-                )
-            if isinstance(shape, (list, tuple)):
-                shape = [
-                    item.numpy().item(0) if isinstance(item, Variable) else item
-                    for item in shape
-                ]
-                out, _ = _legacy_C_ops.reshape2(x, None, 'shape', shape)
-            elif isinstance(shape, tmp_tensor_type):
-                shape.stop_gradient = True
-                out, _ = _legacy_C_ops.reshape2(x, shape)
-            else:
-                raise ValueError(
-                    "shape must be an instance of `list`, `tuple` or `Variable`,"
-                    " got '{}.'".format(type(shape))
-                )
-
-            return dygraph_utils._append_activation_in_dygraph(out, act)
-
-    check_variable_and_dtype(
-        x,
-        'x',
-        [
-            'float16',
-            'float32',
-            'float64',
-            'int16',
-            'int32',
-            'int64',
-            'bool',
-            'uint16',
-        ],
-        'reshape',
-    )
-    check_type(shape, 'shape', (list, tuple, Variable), 'reshape')
-    check_type(actual_shape, 'actual_shape', (Variable, type(None)), 'reshape')
-
-    helper = LayerHelper("reshape2", **locals())
-
-    def get_attr_shape(list_shape):
-        unk_dim_idx = -1
-        attrs_shape = []
-        for dim_idx, dim_size in enumerate(list_shape):
-            if isinstance(dim_size, Variable):
-                attrs_shape.append(-1)
-            else:
-                attrs_shape.append(dim_size)
-                if dim_size == -1:
-                    assert unk_dim_idx == -1, (
-                        "Only one dimension value of 'shape' in reshape can "
-                        "be -1. But received shape[%d] is also -1.\n"
-                        "\n\t# N = x.shape()[2]\t\t# N is an int. "
-                        "(NOT recommend under @to_static)\n\tN = paddle.shape(x)[2]\t\t"
-                        "# N is a Tensor. (Recommend)\n\tz = paddle.reshape([N, -1, 4])"
-                        "\t# z.shape is [-1, -1, 4]\n\n"
-                        "    If your target shape in Reshape represents dynamic shape, "
-                        "please turn it into a Tensor under @to_static. See above example for details."
-                        % dim_idx
-                    )
-                    unk_dim_idx = dim_idx
-                elif dim_size == 0:
-                    assert dim_idx < len(x.shape), (
-                        "The index of 0 in `shape` must be less than "
-                        "the input tensor X's dimensions. "
-                        "But received shape[%d] = 0, X's dimensions = %d."
-                        % (dim_idx, len(x.shape))
-                    )
-                else:
-                    assert dim_size > 0, (
-                        "Each dimension value of 'shape' in reshape must not "
-                        "be negative except one unknown dimension. "
-                        "But received shape[%d] = %s."
-                        % (dim_idx, str(dim_size))
-                    )
-        return attrs_shape
-
-    inputs = {"X": x}
-    attrs = {}
-    if isinstance(shape, Variable):
-        shape.stop_gradient = True
-        inputs["Shape"] = shape
-    elif isinstance(shape, (list, tuple)):
-        assert len(shape) > 0, (
-            "The size of 'shape' in reshape can't be zero, "
-            "but received %s." % len(shape)
-        )
-        attrs["shape"] = get_attr_shape(shape)
-        if utils._contain_var(shape):
-            inputs['ShapeTensor'] = utils._convert_to_tensor_list(shape)
-        elif isinstance(actual_shape, Variable):
-            actual_shape.stop_gradient = True
-            inputs["Shape"] = actual_shape
-
-    out = (
-        x
-        if inplace
-        else helper.create_variable_for_type_inference(dtype=x.dtype)
-    )
-    x_shape = helper.create_variable_for_type_inference(dtype=x.dtype)
-    helper.append_op(
-        type="reshape2",
-        inputs=inputs,
-        attrs=attrs,
-        outputs={"Out": out, "XShape": x_shape},
-    )
-
-    return helper.append_activation(out)
-
-
 def squeeze(input, axes, name=None):
     """
     This OP will squeeze single-dimensional entries of input tensor's shape. If axes is provided, will

python/paddle/fluid/layers/rnn.py

@@ -1036,7 +1036,7 @@ class BeamSearchDecoder(Decoder):
             x, list(range(2, len(x.shape))) + [0, 1]
         )  # [..., batch_size, beam_size]
         # use 0 to copy to avoid wrong shape
-        x = nn.reshape(
+        x = paddle.reshape(
             x, shape=[0] * (len(x.shape) - 2) + [-1]
         )  # [..., batch_size * beam_size]
         x = nn.transpose(
@@ -1059,7 +1059,7 @@ class BeamSearchDecoder(Decoder):
         """
         check_type(x, 'x', (Variable), 'BeamSearchDecoder._split_batch_beams')
         # TODO: avoid fake shape in compile-time like tile_beam_merge_with_batch
-        return nn.reshape(x, shape=[-1, self.beam_size] + list(x.shape[1:]))
+        return paddle.reshape(x, shape=[-1, self.beam_size] + list(x.shape[1:]))
 
     def _merge_batch_beams(self, x):
         r"""
@@ -1076,7 +1076,7 @@ class BeamSearchDecoder(Decoder):
         """
         check_type(x, 'x', (Variable), 'BeamSearchDecoder._merge_batch_beams')
         # TODO: avoid fake shape in compile-time like tile_beam_merge_with_batch
-        return nn.reshape(x, shape=[-1] + list(x.shape[2:]))
+        return paddle.reshape(x, shape=[-1] + list(x.shape[2:]))
 
     def _expand_to_beam_size(self, x):
         r"""
@@ -1311,13 +1311,13 @@ class BeamSearchDecoder(Decoder):
         )
         # TODO: length penalty
         scores = log_probs
-        scores = nn.reshape(scores, [-1, self.beam_size * self.vocab_size])
+        scores = paddle.reshape(scores, [-1, self.beam_size * self.vocab_size])
         # TODO: add grad for topk then this beam search can be used to train
         topk_scores, topk_indices = paddle.topk(x=scores, k=self.beam_size)
         beam_indices = paddle.floor_divide(topk_indices, self.vocab_size_tensor)
         token_indices = paddle.remainder(topk_indices, self.vocab_size_tensor)
         next_log_probs = self._gather(
-            nn.reshape(log_probs, [-1, self.beam_size * self.vocab_size]),
+            paddle.reshape(log_probs, [-1, self.beam_size * self.vocab_size]),
             topk_indices,
             self.batch_size,
         )

python/paddle/fluid/layers/tensor.py

@@ -1948,7 +1948,8 @@ def eye(
             if batch_val <= 0:
                 raise TypeError("batch_shape should be a positive int list")
 
-        from .nn import reshape, expand
+        from .nn import expand
+        from paddle import reshape
 
         out = reshape(x=out, shape=re_shape)
         out = expand(x=out, expand_times=expand_times)

python/paddle/fluid/nets.py

@@ -16,6 +16,7 @@ import paddle
 from . import layers
 from .data_feeder import check_variable_and_dtype, convert_dtype
 from ..utils import deprecated
+import paddle
 
 __all__ = [
     "simple_img_conv_pool",
@@ -569,7 +570,7 @@ def scaled_dot_product_attention(
         # reshape the 3-D input: [batch_size, max_sequence_length, hidden_dim]
         # into a 4-D output:
         # [batch_size, max_sequence_length, num_heads, hidden_size_per_head].
-        reshaped = layers.reshape(
+        reshaped = paddle.reshape(
             x=x,
             shape=list(x.shape[:-1]) + [num_heads, hidden_size // num_heads],
         )
@@ -598,7 +599,7 @@ def scaled_dot_product_attention(
             raise ValueError("Input(x) should be a 4-D Tensor.")
 
         trans_x = layers.transpose(x, perm=[0, 2, 1, 3])
-        return layers.reshape(
+        return paddle.reshape(
             x=trans_x,
             shape=list(
                 map(
@@ -622,12 +623,10 @@ def scaled_dot_product_attention(
     scaled_q = layers.scale(x=q, scale=key_dim_per_head**-0.5)
     product = layers.matmul(x=scaled_q, y=k, transpose_y=True)
 
-    weights = layers.reshape(
-        x=layers.reshape(
-            x=product, shape=[-1, product.shape[-1]], act="softmax"
-        ),
-        shape=product.shape,
-    )
+    x = paddle.reshape(x=product, shape=[-1, product.shape[-1]])
+    x = paddle.nn.functional.softmax(x)
+    weights = paddle.reshape(x=x, shape=product.shape)
+
     if dropout_rate:
         weights = layers.dropout(
             weights, dropout_prob=dropout_rate, is_test=False

python/paddle/fluid/tests/book/test_machine_translation.py

@@ -140,7 +140,9 @@ def decoder_decode(context, is_sparse):
         topk_scores, topk_indices = pd.topk(current_score, k=beam_size)
         # calculate accumulated scores after topk to reduce computation cost
         accu_scores = pd.elementwise_add(
-            x=pd.log(topk_scores), y=pd.reshape(pre_score, shape=[-1]), axis=0
+            x=pd.log(topk_scores),
+            y=paddle.reshape(pre_score, shape=[-1]),
+            axis=0,
         )
         selected_ids, selected_scores = pd.beam_search(
             pre_ids,

python/paddle/fluid/tests/unittests/collective/fleet/hybrid_parallel_pp_embedding.py

@@ -55,7 +55,7 @@ class SimpleNet(Layer):
         x_emb = self.word_embeddings(x1)
         fc = fluid.layers.matmul(x_emb, self.softmax_weight)
         fc = fluid.layers.elementwise_add(fc, self.softmax_bias)
-        projection = fluid.layers.reshape(fc, shape=[-1, vocab_size])
+        projection = paddle.reshape(fc, shape=[-1, vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=y1, soft_label=False
         )
@@ -95,7 +95,7 @@ class BiasNet(Layer):
     def forward(self, args):
         fc, x2 = args
         fc = fluid.layers.elementwise_add(fc, self.softmax_bias)
-        projection = fluid.layers.reshape(fc, shape=[-1, vocab_size])
+        projection = paddle.reshape(fc, shape=[-1, vocab_size])
         return projection, x2
 
 

python/paddle/fluid/tests/unittests/collective/fleet/hybrid_parallel_shared_weight.py

@@ -59,7 +59,7 @@ class SimpleNet(Layer):
         x_emb = self.word_embeddings(x1)
         fc = fluid.layers.matmul(x_emb, self.softmax_weight)
         fc = fluid.layers.elementwise_add(fc, self.softmax_bias)
-        projection = fluid.layers.reshape(fc, shape=[-1, vocab_size])
+        projection = paddle.reshape(fc, shape=[-1, vocab_size])
 
         projection = paddle.matmul(projection, self.word_embeddings.weight)
 
@@ -106,7 +106,7 @@ class BiasNet(Layer):
     def forward(self, args):
         fc, x2 = args
         fc = fluid.layers.elementwise_add(fc, self.softmax_bias)
-        projection = fluid.layers.reshape(fc, shape=[-1, vocab_size])
+        projection = paddle.reshape(fc, shape=[-1, vocab_size])
         return projection, x2
 
 

python/paddle/fluid/tests/unittests/collective/fleet/parallel_dygraph_se_resnext.py

@@ -135,7 +135,7 @@ class SqueezeExcitation(fluid.dygraph.Layer):
 
     def forward(self, input):
         y = self._pool(input)
-        y = fluid.layers.reshape(y, shape=[-1, self._num_channels])
+        y = paddle.reshape(y, shape=[-1, self._num_channels])
         y = self._squeeze(y)
         y = self._excitation(y)
         y = fluid.layers.elementwise_mul(x=input, y=y, axis=0)
@@ -326,7 +326,7 @@ class SeResNeXt(fluid.dygraph.Layer):
         for bottleneck_block in self.bottleneck_block_list:
             y = bottleneck_block(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_output])
         y = self.out(y)
         return y
 

python/paddle/fluid/tests/unittests/collective/fleet/parallel_dygraph_transformer.py

@@ -325,16 +325,16 @@ class MultiHeadAttentionLayer(Layer):
         v = self._v_fc(values)
 
         # split head
-        reshaped_q = fluid.layers.reshape(
-            x=q, shape=[0, 0, self._n_head, self._d_key], inplace=False
+        reshaped_q = paddle.reshape(
+            x=q, shape=[0, 0, self._n_head, self._d_key]
         )
         transpose_q = fluid.layers.transpose(x=reshaped_q, perm=[0, 2, 1, 3])
-        reshaped_k = fluid.layers.reshape(
-            x=k, shape=[0, 0, self._n_head, self._d_key], inplace=False
+        reshaped_k = paddle.reshape(
+            x=k, shape=[0, 0, self._n_head, self._d_key]
         )
         transpose_k = fluid.layers.transpose(x=reshaped_k, perm=[0, 2, 1, 3])
-        reshaped_v = fluid.layers.reshape(
-            x=v, shape=[0, 0, self._n_head, self._d_value], inplace=False
+        reshaped_v = paddle.reshape(
+            x=v, shape=[0, 0, self._n_head, self._d_value]
         )
         transpose_v = fluid.layers.transpose(x=reshaped_v, perm=[0, 2, 1, 3])
 
@@ -363,10 +363,9 @@ class MultiHeadAttentionLayer(Layer):
         if len(out.shape) != 4:
             raise ValueError("Input(x) should be a 4-D Tensor.")
         trans_x = fluid.layers.transpose(out, perm=[0, 2, 1, 3])
-        final_out = fluid.layers.reshape(
+        final_out = paddle.reshape(
             x=trans_x,
             shape=[0, 0, trans_x.shape[2] * trans_x.shape[3]],
-            inplace=False,
         )
 
         # fc to output
@@ -839,8 +838,8 @@ class WrapDecoderLayer(Layer):
             dec_input, enc_output, trg_slf_attn_bias, trg_src_attn_bias
         )
 
-        dec_output_reshape = fluid.layers.reshape(
-            dec_output, shape=[-1, dec_output.shape[-1]], inplace=False
+        dec_output_reshape = paddle.reshape(
+            dec_output, shape=[-1, dec_output.shape[-1]]
         )
 
         if self._weight_sharing:

python/paddle/fluid/tests/unittests/dist_fleet_simnet_bow.py

@@ -127,7 +127,7 @@ def train_network(
         ),
         is_sparse=is_sparse,
     )
-    q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+    q_emb = paddle.reshape(q_emb, [-1, emb_dim])
     # vsum
     q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
     q_ss = paddle.nn.functional.softsign(q_sum)
@@ -154,7 +154,7 @@ def train_network(
         ),
         is_sparse=is_sparse,
     )
-    pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+    pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
     # vsum
     pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
     pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -178,7 +178,7 @@ def train_network(
         ),
         is_sparse=is_sparse,
     )
-    nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+    nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
     # vsum
     nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
     nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/dist_transformer.py

@@ -1142,7 +1142,7 @@ def multi_head_attention(
         hidden_size = x.shape[-1]
         # The value 0 in shape attr means copying the corresponding dimension
         # size of the input as the output dimension size.
-        reshaped = layers.reshape(
+        reshaped = paddle.reshape(
             x=x, shape=[0, 0, n_head, hidden_size // n_head]
         )
 
@@ -1163,7 +1163,7 @@ def multi_head_attention(
         trans_x = layers.transpose(x, perm=[0, 2, 1, 3])
         # The value 0 in shape attr means copying the corresponding dimension
         # size of the input as the output dimension size.
-        return layers.reshape(
+        return paddle.reshape(
             x=trans_x,
             shape=list(map(int, [0, 0, trans_x.shape[2] * trans_x.shape[3]])),
         )
@@ -1585,7 +1585,7 @@ def transformer(
         )
 
     cost = layers.softmax_with_cross_entropy(
-        logits=layers.reshape(predict, shape=[-1, trg_vocab_size]),
+        logits=paddle.reshape(predict, shape=[-1, trg_vocab_size]),
         label=label,
         soft_label=True if label_smooth_eps else False,
     )
@@ -1765,7 +1765,7 @@ def fast_decode(
         while_op = layers.While(cond)
         # array states will be stored for each step.
         ids = layers.array_write(
-            layers.reshape(start_tokens, (-1, 1)), step_idx
+            paddle.reshape(start_tokens, (-1, 1)), step_idx
         )
         scores = layers.array_write(init_scores, step_idx)
         # cell states will be overwrited at each step.
@@ -1790,7 +1790,7 @@ def fast_decode(
         ]
         with while_op.block():
             pre_ids = layers.array_read(array=ids, i=step_idx)
-            pre_ids = layers.reshape(pre_ids, (-1, 1, 1))
+            pre_ids = paddle.reshape(pre_ids, (-1, 1, 1))
             pre_scores = layers.array_read(array=scores, i=step_idx)
             # sequence_expand can gather sequences according to lod thus can be
             # used in beam search to sift states corresponding to selected ids.
@@ -1830,14 +1830,14 @@ def fast_decode(
                 enc_output=pre_enc_output,
                 caches=pre_caches,
             )
-            logits = layers.reshape(logits, (-1, trg_vocab_size))
+            logits = paddle.reshape(logits, (-1, trg_vocab_size))
 
             topk_scores, topk_indices = layers.topk(
                 input=layers.softmax(logits), k=beam_size
             )
             accu_scores = layers.elementwise_add(
                 x=layers.log(topk_scores),
-                y=layers.reshape(pre_scores, shape=[-1]),
+                y=paddle.reshape(pre_scores, shape=[-1]),
                 axis=0,
             )
             # beam_search op uses lod to distinguish branches.

python/paddle/fluid/tests/unittests/dygraph_to_static/bert_dygraph_model.py

@@ -295,7 +295,7 @@ class BertModelLayer(Layer):
             input=enc_output, axes=[1], starts=[0], ends=[1]
         )
         next_sent_feat = self.pooled_fc(next_sent_feat)
-        next_sent_feat = fluid.layers.reshape(
+        next_sent_feat = paddle.reshape(
             next_sent_feat, shape=[-1, self._emb_size]
         )
 
@@ -391,7 +391,7 @@ class PretrainModelLayer(Layer):
         enc_output, next_sent_feat = self.bert_layer(
             src_ids, position_ids, sentence_ids, input_mask
         )
-        reshaped_emb_out = fluid.layers.reshape(
+        reshaped_emb_out = paddle.reshape(
             x=enc_output, shape=[-1, self._emb_size]
         )
 

python/paddle/fluid/tests/unittests/dygraph_to_static/ifelse_simple_func.py

@@ -173,7 +173,7 @@ def nested_if_else(x_v):
 
 
 def nested_if_else_2(x):
-    y = fluid.layers.reshape(x, [-1, 1])
+    y = paddle.reshape(x, [-1, 1])
     b = 2
     if b < 1:
         # var `z` is not visible for outer scope
@@ -196,7 +196,7 @@ def nested_if_else_2(x):
 
 
 def nested_if_else_3(x):
-    y = fluid.layers.reshape(x, [-1, 1])
+    y = paddle.reshape(x, [-1, 1])
     b = 2
     # var `z` is visible for func.body
     if b < 1:

python/paddle/fluid/tests/unittests/dygraph_to_static/seq2seq_dygraph_model.py

@@ -179,10 +179,10 @@ class BaseModel(fluid.dygraph.Layer):
         return fluid.layers.transpose(x, [1, 0] + list(range(2, len(x.shape))))
 
     def _merge_batch_beams(self, x):
-        return fluid.layers.reshape(x, shape=(-1, x.shape[2]))
+        return paddle.reshape(x, shape=(-1, x.shape[2]))
 
     def _split_batch_beams(self, x):
-        return fluid.layers.reshape(x, shape=(-1, self.beam_size, x.shape[1]))
+        return paddle.reshape(x, shape=(-1, self.beam_size, x.shape[1]))
 
     def _expand_to_beam_size(self, x):
         x = fluid.layers.unsqueeze(x, [1])
@@ -454,7 +454,7 @@ class BaseModel(fluid.dygraph.Layer):
             log_probs = fluid.layers.elementwise_add(
                 x=step_log_probs, y=beam_state_log_probs, axis=0
             )
-            scores = fluid.layers.reshape(
+            scores = paddle.reshape(
                 log_probs, [-1, self.beam_size * self.tar_vocab_size]
             )
             topk_scores, topk_indices = fluid.layers.topk(
@@ -646,7 +646,7 @@ class AttentionModel(fluid.dygraph.Layer):
         return fluid.layers.transpose(x, [1, 0] + list(range(2, len(x.shape))))
 
     def _merge_batch_beams(self, x):
-        return fluid.layers.reshape(x, shape=(-1, x.shape[2]))
+        return paddle.reshape(x, shape=(-1, x.shape[2]))
 
     def tile_beam_merge_with_batch(self, x):
         x = fluid.layers.unsqueeze(x, [1])  # [batch_size, 1, ...]
@@ -657,7 +657,7 @@ class AttentionModel(fluid.dygraph.Layer):
             x, list(range(2, len(x.shape))) + [0, 1]
         )  # [..., batch_size, beam_size]
         # use 0 to copy to avoid wrong shape
-        x = fluid.layers.reshape(
+        x = paddle.reshape(
             x, shape=[0] * (len(x.shape) - 2) + [-1]
         )  # [..., batch_size * beam_size]
         x = fluid.layers.transpose(
@@ -666,7 +666,7 @@ class AttentionModel(fluid.dygraph.Layer):
         return x
 
     def _split_batch_beams(self, x):
-        return fluid.layers.reshape(x, shape=(-1, self.beam_size, x.shape[1]))
+        return paddle.reshape(x, shape=(-1, self.beam_size, x.shape[1]))
 
     def _expand_to_beam_size(self, x):
         x = fluid.layers.unsqueeze(x, [1])

python/paddle/fluid/tests/unittests/dygraph_to_static/simnet_dygraph_model.py

@@ -503,10 +503,10 @@ class BOW(Layer):
         # embedding layer
         left_emb = self.emb_layer(left)
         right_emb = self.emb_layer(right)
-        left_emb = fluid.layers.reshape(
+        left_emb = paddle.reshape(
             left_emb, shape=[-1, self.seq_len, self.bow_dim]
         )
-        right_emb = fluid.layers.reshape(
+        right_emb = paddle.reshape(
             right_emb, shape=[-1, self.seq_len, self.bow_dim]
         )
 

python/paddle/fluid/tests/unittests/dygraph_to_static/test_bmn.py

@@ -284,9 +284,7 @@ class BMN(fluid.dygraph.Layer):
         xp = paddle.nn.functional.relu(self.p_conv1(x))
         # BM layer
         xp = fluid.layers.matmul(xp, self.sample_mask)
-        xp = fluid.layers.reshape(
-            xp, shape=[0, 0, -1, self.dscale, self.tscale]
-        )
+        xp = paddle.reshape(xp, shape=[0, 0, -1, self.dscale, self.tscale])
 
         xp = self.p_conv3d1(xp)
         xp = fluid.layers.squeeze(xp, axes=[2])
@@ -319,12 +317,8 @@ def bmn_loss_func(
 
     def tem_loss_func(pred_start, pred_end, gt_start, gt_end):
         def bi_loss(pred_score, gt_label):
-            pred_score = fluid.layers.reshape(
-                x=pred_score, shape=[-1], inplace=False
-            )
-            gt_label = fluid.layers.reshape(
-                x=gt_label, shape=[-1], inplace=False
-            )
+            pred_score = paddle.reshape(x=pred_score, shape=[-1])
+            gt_label = paddle.reshape(x=gt_label, shape=[-1])
             gt_label.stop_gradient = True
             pmask = fluid.layers.cast(x=(gt_label > 0.5), dtype=DATATYPE)
             num_entries = fluid.layers.cast(

python/paddle/fluid/tests/unittests/dygraph_to_static/test_error.py

@@ -41,7 +41,7 @@ def func_error_in_compile_time(x):
 @paddle.jit.to_static
 def func_error_in_compile_time_2(x):
     x = fluid.dygraph.to_variable(x)
-    x = fluid.layers.reshape(x, shape=[1, 2])
+    x = paddle.reshape(x, shape=[1, 2])
     return x
 
 
@@ -49,7 +49,7 @@ def func_error_in_compile_time_2(x):
 def func_error_in_runtime(x):
     x = fluid.dygraph.to_variable(x)
     two = fluid.layers.fill_constant(shape=[1], value=2, dtype="int32")
-    x = fluid.layers.reshape(x, shape=[1, two])
+    x = paddle.reshape(x, shape=[1, two])
     return x
 
 
@@ -101,7 +101,7 @@ def func_error_in_runtime_with_empty_line(x):
     x = fluid.dygraph.to_variable(x)
     two = fluid.layers.fill_constant(shape=[1], value=2, dtype="int32")
 
-    x = fluid.layers.reshape(x, shape=[1, two])
+    x = paddle.reshape(x, shape=[1, two])
 
     return x
 
@@ -290,7 +290,7 @@ class TestErrorStaticLayerCallInCompiletime_2(
             ),
             'def func_error_in_compile_time_2(x):',
             'x = fluid.dygraph.to_variable(x)',
-            'x = fluid.layers.reshape(x, shape=[1, 2])',
+            'x = paddle.reshape(x, shape=[1, 2])',
             '<--- HERE',
             'return x',
         ]
@@ -340,7 +340,7 @@ class TestErrorStaticLayerCallInRuntime(TestErrorStaticLayerCallInCompiletime):
             ),
             'x = fluid.dygraph.to_variable(x)',
             'two = fluid.layers.fill_constant(shape=[1], value=2, dtype="int32")',
-            'x = fluid.layers.reshape(x, shape=[1, two])',
+            'x = paddle.reshape(x, shape=[1, two])',
             '<--- HERE',
             'return x',
         ]
@@ -356,7 +356,7 @@ class TestErrorStaticLayerCallInRuntime2(TestErrorStaticLayerCallInRuntime):
                 self.filepath
             ),
             'two = fluid.layers.fill_constant(shape=[1], value=2, dtype="int32")',
-            'x = fluid.layers.reshape(x, shape=[1, two])',
+            'x = paddle.reshape(x, shape=[1, two])',
             '<--- HERE',
             'return x',
         ]

python/paddle/fluid/tests/unittests/dygraph_to_static/test_lac.py

@@ -87,13 +87,9 @@ class DynamicGRU(fluid.dygraph.Layer):
             input_ = fluid.layers.slice(
                 inputs, axes=[1], starts=[j], ends=[j + 1]
             )
-            input_ = fluid.layers.reshape(
-                input_, [-1, input_.shape[2]], inplace=False
-            )
+            input_ = paddle.reshape(input_, [-1, input_.shape[2]])
             hidden, reset, gate = self.gru_unit(input_, hidden)
-            hidden_ = fluid.layers.reshape(
-                hidden, [-1, 1, hidden.shape[1]], inplace=False
-            )
+            hidden_ = paddle.reshape(hidden, [-1, 1, hidden.shape[1]])
             res.append(hidden_)
 
         if self.is_reverse:

python/paddle/fluid/tests/unittests/dygraph_to_static/test_mnist.py

@@ -125,7 +125,7 @@ class MNIST(fluid.dygraph.Layer):
     def inference(self, inputs):
         x = self._simple_img_conv_pool_1(inputs)
         x = self._simple_img_conv_pool_2(x)
-        x = fluid.layers.reshape(x, shape=[-1, self.pool_2_shape])
+        x = paddle.reshape(x, shape=[-1, self.pool_2_shape])
         x = self._fc(x)
         return x
 

python/paddle/fluid/tests/unittests/dygraph_to_static/test_mobile_net.py

@@ -271,7 +271,7 @@ class MobileNetV1(fluid.dygraph.Layer):
         for dws in self.dwsl:
             y = dws(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, 1024])
+        y = paddle.reshape(y, shape=[-1, 1024])
         y = self.out(y)
         return y
 
@@ -438,7 +438,7 @@ class MobileNetV2(fluid.dygraph.Layer):
             y = inv(y)
         y = self._conv9(y, if_act=True)
         y = self._pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self._out_c])
+        y = paddle.reshape(y, shape=[-1, self._out_c])
         y = self._fc(y)
         return y
 

python/paddle/fluid/tests/unittests/dygraph_to_static/test_partial_program.py

@@ -186,7 +186,7 @@ class GPT2LMHeadModel(fluid.dygraph.Layer):
 
     @declarative
     def forward(self, x):
-        x = fluid.layers.reshape(x, shape=[-1, 6])
+        x = paddle.reshape(x, shape=[-1, 6])
         x1, x2, x3 = fluid.layers.split(input=x, dim=1, num_or_sections=3)
         return x1
 

python/paddle/fluid/tests/unittests/dygraph_to_static/test_ptb_lm.py

@@ -115,16 +115,16 @@ class SimpleLSTMRNN(fluid.Layer):
                     )
             res.append(step_input)
         real_res = fluid.layers.concat(res, 1)
-        real_res = fluid.layers.reshape(
+        real_res = paddle.reshape(
             real_res, [-1, self._num_steps, self._hidden_size]
         )
         last_hidden = fluid.layers.concat(hidden_array, 1)
-        last_hidden = fluid.layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_hidden = fluid.layers.transpose(x=last_hidden, perm=[1, 0, 2])
         last_cell = fluid.layers.concat(cell_array, 1)
-        last_cell = fluid.layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_cell = fluid.layers.transpose(x=last_cell, perm=[1, 0, 2])
@@ -189,17 +189,17 @@ class PtbModel(fluid.Layer):
     @declarative
     def forward(self, input, label, init_hidden, init_cell):
 
-        init_h = fluid.layers.reshape(
+        init_h = paddle.reshape(
             init_hidden, shape=[self.num_layers, -1, self.hidden_size]
         )
 
-        init_c = fluid.layers.reshape(
+        init_c = paddle.reshape(
             init_cell, shape=[self.num_layers, -1, self.hidden_size]
         )
 
         x_emb = self.embedding(input)
 
-        x_emb = fluid.layers.reshape(
+        x_emb = paddle.reshape(
             x_emb, shape=[-1, self.num_steps, self.hidden_size]
         )
         if self.dropout is not None and self.dropout > 0.0:
@@ -218,7 +218,7 @@ class PtbModel(fluid.Layer):
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/dygraph_to_static/test_reinforcement_learning.py

@@ -41,7 +41,7 @@ class Policy(Layer):
 
     @declarative
     def forward(self, x):
-        x = fluid.layers.reshape(x, shape=[1, 4])
+        x = paddle.reshape(x, shape=[1, 4])
         x = self.affine1(x)
         x = fluid.layers.dropout(x, self.dropout_ratio)
         x = fluid.layers.relu(x)

python/paddle/fluid/tests/unittests/dygraph_to_static/test_resnet.py

@@ -211,7 +211,7 @@ class ResNet(fluid.dygraph.Layer):
         for bottleneck_block in self.bottleneck_block_list:
             y = bottleneck_block(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_output])
         pred = self.out(y)
 
         return pred

python/paddle/fluid/tests/unittests/dygraph_to_static/test_se_resnet.py

@@ -148,7 +148,7 @@ class SqueezeExcitation(fluid.dygraph.Layer):
 
     def forward(self, input):
         y = self._pool(input)
-        y = fluid.layers.reshape(y, shape=[-1, self._num_channels])
+        y = paddle.reshape(y, shape=[-1, self._num_channels])
         y = self._fc(y)
         y = self._excitation(y)
         y = fluid.layers.elementwise_mul(x=input, y=y, axis=0)
@@ -344,7 +344,7 @@ class SeResNeXt(fluid.dygraph.Layer):
 
         y = self.pool2d_avg(y)
         y = fluid.layers.dropout(y, dropout_prob=0.5, seed=100)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_output])
         out = self.out(y)
 
         softmax_out = fluid.layers.softmax(out)

python/paddle/fluid/tests/unittests/dygraph_to_static/test_sentiment.py

@@ -53,7 +53,7 @@ class SimpleConvPool(fluid.dygraph.Layer):
     def forward(self, inputs):
         x = paddle.tanh(self._conv2d(inputs))
         x = fluid.layers.reduce_max(x, dim=-1)
-        x = fluid.layers.reshape(x, shape=[self.batch_size, -1])
+        x = paddle.reshape(x, shape=[self.batch_size, -1])
         return x
 
 
@@ -92,12 +92,12 @@ class CNN(fluid.dygraph.Layer):
     @declarative
     def forward(self, inputs, label=None):
         emb = self.embedding(inputs)
-        o_np_mask = (
-            fluid.layers.reshape(inputs, [-1, 1]) != self.dict_dim
-        ).astype(dtype='float32')
+        o_np_mask = (paddle.reshape(inputs, [-1, 1]) != self.dict_dim).astype(
+            dtype='float32'
+        )
         mask_emb = fluid.layers.expand(o_np_mask, [1, self.hid_dim])
         emb = emb * mask_emb
-        emb = fluid.layers.reshape(
+        emb = paddle.reshape(
             emb, shape=[-1, self.channels, self.seq_len, self.hid_dim]
         )
         conv_3 = self._simple_conv_pool_1(emb)
@@ -138,12 +138,12 @@ class BOW(fluid.dygraph.Layer):
     @declarative
     def forward(self, inputs, label=None):
         emb = self.embedding(inputs)
-        o_np_mask = (
-            fluid.layers.reshape(inputs, [-1, 1]) != self.dict_dim
-        ).astype(dtype='float32')
+        o_np_mask = (paddle.reshape(inputs, [-1, 1]) != self.dict_dim).astype(
+            dtype='float32'
+        )
         mask_emb = fluid.layers.expand(o_np_mask, [1, self.hid_dim])
         emb = emb * mask_emb
-        emb = fluid.layers.reshape(emb, shape=[-1, self.seq_len, self.hid_dim])
+        emb = paddle.reshape(emb, shape=[-1, self.seq_len, self.hid_dim])
         bow_1 = fluid.layers.reduce_sum(emb, dim=1)
         bow_1 = paddle.tanh(bow_1)
         fc_1 = self._fc1(bow_1)
@@ -186,14 +186,12 @@ class GRU(fluid.dygraph.Layer):
     @declarative
     def forward(self, inputs, label=None):
         emb = self.embedding(inputs)
-        o_np_mask = (
-            fluid.layers.reshape(inputs, [-1, 1]) != self.dict_dim
-        ).astype('float32')
+        o_np_mask = (paddle.reshape(inputs, [-1, 1]) != self.dict_dim).astype(
+            'float32'
+        )
         mask_emb = fluid.layers.expand(o_np_mask, [1, self.hid_dim])
         emb = emb * mask_emb
-        emb = fluid.layers.reshape(
-            emb, shape=[self.batch_size, -1, self.hid_dim]
-        )
+        emb = paddle.reshape(emb, shape=[self.batch_size, -1, self.hid_dim])
         fc_1 = self._fc1(emb)
         gru_hidden = self._gru(fc_1)
         gru_hidden = fluid.layers.reduce_max(gru_hidden, dim=1)
@@ -242,14 +240,12 @@ class BiGRU(fluid.dygraph.Layer):
     @declarative
     def forward(self, inputs, label=None):
         emb = self.embedding(inputs)
-        o_np_mask = (
-            fluid.layers.reshape(inputs, [-1, 1]) != self.dict_dim
-        ).astype('float32')
+        o_np_mask = (paddle.reshape(inputs, [-1, 1]) != self.dict_dim).astype(
+            'float32'
+        )
         mask_emb = fluid.layers.expand(o_np_mask, [1, self.hid_dim])
         emb = emb * mask_emb
-        emb = fluid.layers.reshape(
-            emb, shape=[self.batch_size, -1, self.hid_dim]
-        )
+        emb = paddle.reshape(emb, shape=[self.batch_size, -1, self.hid_dim])
         fc_1 = self._fc1(emb)
         gru_forward = self._gru_forward(fc_1)
         gru_backward = self._gru_backward(fc_1)

python/paddle/fluid/tests/unittests/dygraph_to_static/test_simnet.py

@@ -145,9 +145,9 @@ def train(conf_dict, to_static):
         )
 
         for left, pos_right, neg_right in train_loader():
-            left = fluid.layers.reshape(left, shape=[-1, 1])
-            pos_right = fluid.layers.reshape(pos_right, shape=[-1, 1])
-            neg_right = fluid.layers.reshape(neg_right, shape=[-1, 1])
+            left = paddle.reshape(left, shape=[-1, 1])
+            pos_right = paddle.reshape(pos_right, shape=[-1, 1])
+            neg_right = paddle.reshape(neg_right, shape=[-1, 1])
             net.train()
             global_step += 1
             left_feat, pos_score = net(left, pos_right)

python/paddle/fluid/tests/unittests/dygraph_to_static/test_tensor_shape.py

@@ -22,7 +22,7 @@ from paddle.fluid.dygraph.jit import declarative
 
 def dyfunc_tensor_shape_1(x):
     x = fluid.dygraph.to_variable(x)
-    res = fluid.layers.reshape(x, shape=x.shape)
+    res = paddle.reshape(x, shape=x.shape)
     return res
 
 
@@ -38,13 +38,13 @@ def dyfunc_tensor_shape_3(x):
     # Transform y.shape but run y.shape actually because y is not Tensor
     x = fluid.dygraph.to_variable(x)
     y = np.ones(5)
-    res = fluid.layers.reshape(x, shape=y.shape)
+    res = paddle.reshape(x, shape=y.shape)
     return res
 
 
 def dyfunc_tensor_shape_4(x):
     x = fluid.dygraph.to_variable(x)
-    res = fluid.layers.reshape(x, shape=(-1, x.shape[0], len(x.shape)))
+    res = paddle.reshape(x, shape=(-1, x.shape[0], len(x.shape)))
     return res
 
 
@@ -54,7 +54,7 @@ def dyfunc_tensor_shape_5(x):
     #           paddle.jit.dy2static.convert_var_shape(x)[0]))`
     x = fluid.dygraph.to_variable(x)
     s = x.shape[0]
-    res = fluid.layers.reshape(x, shape=(-1, s))
+    res = paddle.reshape(x, shape=(-1, s))
     return res
 
 
@@ -64,7 +64,7 @@ def dyfunc_tensor_shape_6(x):
     #           paddle.jit.dy2static.convert_var_shape(x)[0:]))`
     x = fluid.dygraph.to_variable(x)
     s = x.shape[0:]
-    res = fluid.layers.reshape(x, shape=s)
+    res = paddle.reshape(x, shape=s)
     return res
 
 
@@ -103,7 +103,7 @@ def dyfunc_paddle_shape_api(x):
 
 def dyfunc_with_if_1(x):
     x = fluid.dygraph.to_variable(x)
-    res = fluid.layers.reshape(x, [-1, 1])
+    res = paddle.reshape(x, [-1, 1])
     x_shape_0 = x.shape[0]
     if x_shape_0 < 1:
         # `res.shape[0]` is transformed into

python/paddle/fluid/tests/unittests/dygraph_to_static/test_tsm.py

@@ -200,16 +200,16 @@ class TSM_ResNet(fluid.dygraph.Layer):
 
     @declarative
     def forward(self, inputs):
-        y = fluid.layers.reshape(inputs, [-1] + self.reshape_list)
+        y = paddle.reshape(inputs, [-1] + self.reshape_list)
         y = self.conv(y)
         y = self.pool2d_max(y)
         for bottleneck_block in self.bottleneck_block_list:
             y = bottleneck_block(y)
         y = self.pool2d_avg(y)
         y = fluid.layers.dropout(y, dropout_prob=0.5)
-        y = fluid.layers.reshape(y, [-1, self.seg_num, y.shape[1]])
+        y = paddle.reshape(y, [-1, self.seg_num, y.shape[1]])
         y = fluid.layers.reduce_mean(y, dim=1)
-        y = fluid.layers.reshape(y, shape=[-1, 2048])
+        y = paddle.reshape(y, shape=[-1, 2048])
         y = self.out(y)
         return y
 

python/paddle/fluid/tests/unittests/dygraph_to_static/transformer_dygraph_model.py

@@ -138,11 +138,11 @@ class MultiHeadAttention(Layer):
         k = self.k_fc(keys)
         v = self.v_fc(values)
         # split head
-        q = layers.reshape(x=q, shape=[0, 0, self.n_head, self.d_key])
+        q = paddle.reshape(x=q, shape=[0, 0, self.n_head, self.d_key])
         q = layers.transpose(x=q, perm=[0, 2, 1, 3])
-        k = layers.reshape(x=k, shape=[0, 0, self.n_head, self.d_key])
+        k = paddle.reshape(x=k, shape=[0, 0, self.n_head, self.d_key])
         k = layers.transpose(x=k, perm=[0, 2, 1, 3])
-        v = layers.reshape(x=v, shape=[0, 0, self.n_head, self.d_value])
+        v = paddle.reshape(x=v, shape=[0, 0, self.n_head, self.d_value])
         v = layers.transpose(x=v, perm=[0, 2, 1, 3])
 
         if cache is not None:
@@ -161,7 +161,7 @@ class MultiHeadAttention(Layer):
             weights = layers.dropout(weights, dropout_prob=self.dropout_rate)
             out = layers.matmul(weights, v)
         out = layers.transpose(out, perm=[0, 2, 1, 3])
-        out = layers.reshape(x=out, shape=[0, 0, out.shape[2] * out.shape[3]])
+        out = paddle.reshape(x=out, shape=[0, 0, out.shape[2] * out.shape[3]])
         out = self.proj_fc(out)
         return out
 
@@ -557,7 +557,7 @@ class WrapDecoder(Layer):
         dec_output = self.decoder(
             dec_input, enc_output, trg_slf_attn_bias, trg_src_attn_bias, caches
         )
-        dec_output = layers.reshape(
+        dec_output = paddle.reshape(
             dec_output,
             shape=[-1, dec_output.shape[-1]],
         )
@@ -694,7 +694,7 @@ class Transformer(Layer):
         max_len=256,
     ):
         def expand_to_beam_size(tensor, beam_size):
-            tensor = layers.reshape(
+            tensor = paddle.reshape(
                 tensor, [tensor.shape[0], 1] + list(tensor.shape[1:])
             )
             tile_dims = [1] * len(tensor.shape)
@@ -709,7 +709,7 @@ class Transformer(Layer):
                 + list(range(0, var_dim_in_state)),
             )
 
-            tensor = layers.reshape(
+            tensor = paddle.reshape(
                 tensor,
                 [0] * (len(tensor.shape) - var_dim_in_state)
                 + [batch_size * beam_size],
@@ -733,7 +733,7 @@ class Transformer(Layer):
                 list(range(var_dim_in_state, len(tensor.shape)))
                 + list(range(0, var_dim_in_state)),
             )
-            tensor = layers.reshape(
+            tensor = paddle.reshape(
                 tensor,
                 [0] * (len(tensor.shape) - var_dim_in_state)
                 + [batch_size, beam_size],
@@ -849,7 +849,7 @@ class Transformer(Layer):
             log_probs = layers.elementwise_add(
                 x=step_log_probs, y=log_probs, axis=0
             )
-            log_probs = layers.reshape(
+            log_probs = paddle.reshape(
                 log_probs, [-1, beam_size * self.trg_vocab_size]
             )
             scores = log_probs
@@ -868,7 +868,7 @@ class Transformer(Layer):
             finished = layers.logical_or(
                 finished, layers.equal(token_indices, end_token_tensor)
             )
-            trg_word = layers.reshape(token_indices, [-1, 1])
+            trg_word = paddle.reshape(token_indices, [-1, 1])
 
             predict_ids.append(token_indices)
             parent_ids.append(beam_indices)

python/paddle/fluid/tests/unittests/ipu/test_reshape_inplace_op_ipu.py

@@ -50,7 +50,7 @@ class TestBase(IPUOpTest):
             name=self.feed_list[0], shape=self.feed_shape[0], dtype='float32'
         )
         add = paddle.fluid.layers.elementwise_add(x, x)
-        out = paddle.fluid.layers.reshape(add, **self.attrs)
+        out = paddle.reshape(add, **self.attrs)
         self.fetch_list = [out.name]
 
     def run_model(self, exec_mode):

python/paddle/fluid/tests/unittests/ipu/test_reshape_op_ipu.py

@@ -47,7 +47,7 @@ class TestBase(IPUOpTest):
         x = paddle.static.data(
             name=self.feed_list[0], shape=self.feed_shape[0], dtype='float32'
         )
-        out = paddle.fluid.layers.reshape(x=x, **self.attrs)
+        out = paddle.reshape(x=x, **self.attrs)
         self.fetch_list = [out.name]
 
     def run_model(self, exec_mode):

python/paddle/fluid/tests/unittests/ipu/test_varname_inplace_ipu.py

@@ -59,7 +59,7 @@ class TestBase(IPUOpTest):
                     dtype=self.feed_dtype[0],
                 )
                 add1 = paddle.fluid.layers.elementwise_add(x, x)
-                reshape = paddle.fluid.layers.reshape(add1, **self.attrs)
+                reshape = paddle.reshape(add1, **self.attrs)
                 add2 = paddle.fluid.layers.elementwise_add(reshape, reshape)
                 scale1 = paddle.fluid.layers.scale(add2)
                 scale2 = paddle.fluid.layers.scale(scale1, scale=1.3, bias=0.5)

python/paddle/fluid/tests/unittests/ir/inference/test_mkldnn_cpu_bfloat16_pass.py

@@ -17,6 +17,7 @@ import numpy as np
 from inference_pass_test import InferencePassTest
 import paddle.fluid as fluid
 from paddle.fluid.core import PassVersionChecker
+import paddle
 
 
 class TestMKLDNNCpuBfloat16Pass(InferencePassTest):
@@ -27,7 +28,7 @@ class TestMKLDNNCpuBfloat16Pass(InferencePassTest):
                 name='x', shape=[-1] + self.shape_x, dtype=self.d_type
             )
             out = fluid.layers.transpose(x, perm=[0, 1, 2, 3])
-            out = fluid.layers.reshape(out, [0, 0, 0, 0])
+            out = paddle.reshape(out, [0, 0, 0, 0])
             out = fluid.layers.fc(out, size=1)
 
             self.feeds = {

python/paddle/fluid/tests/unittests/ir/inference/test_mkldnn_matmul_op_output_fuse_pass.py

@@ -14,7 +14,7 @@
 
 import unittest
 import numpy as np
-
+import paddle
 import paddle.fluid as fluid
 from inference_pass_test import InferencePassTest
 
@@ -37,9 +37,7 @@ class TestMKLDNNMatmulFuseOp(InferencePassTest):
             )
             out = fluid.layers.matmul(x, y)
             out = fluid.layers.transpose(out, perm=[0, 2, 1, 3])
-            out = fluid.layers.reshape(
-                out, [0, 0, self.shape_y[0] * self.shape_y[2]]
-            )
+            out = paddle.reshape(out, [0, 0, self.shape_y[0] * self.shape_y[2]])
             out = fluid.layers.relu(out)
         return out
 
@@ -80,7 +78,7 @@ class TestMKLDNNMatmulOpNotFusedWrongTransposeAxis(TestMKLDNNMatmulFuseOp):
             )
             out = fluid.layers.matmul(x, y)
             out = fluid.layers.transpose(out, perm=[0, 1, 2, 3])
-            out = fluid.layers.reshape(out, [0, 0, 0, 0])
+            out = paddle.reshape(out, [0, 0, 0, 0])
             out = fluid.layers.fc(out, size=1)
         return out
 
@@ -106,9 +104,7 @@ class TestMKLDNNMatmulOpNotFusedBreakPattern(TestMKLDNNMatmulFuseOp):
             out = fluid.layers.transpose(
                 out, perm=[0, 1, 2, 3]
             )  # breaks pattern
-            out = fluid.layers.reshape(
-                out, [0, 0, self.shape_y[0] * self.shape_y[2]]
-            )
+            out = paddle.reshape(out, [0, 0, self.shape_y[0] * self.shape_y[2]])
             out = fluid.layers.relu(out)
         return out
 

python/paddle/fluid/tests/unittests/ir/inference/test_mkldnn_reshape_transpose_matmul_v2_fuse_pass.py

@@ -33,7 +33,7 @@ class TestReshapeTransposeMatmulV2OneDNNFusePass(InferencePassTest):
             weight = fluid.layers.create_parameter(
                 shape=self.weight_shape, dtype="float32"
             )
-            reshape = fluid.layers.reshape(data, shape=self.reshape_shape)
+            reshape = paddle.reshape(data, shape=self.reshape_shape)
             transpose = fluid.layers.transpose(reshape, self.tranpose_perm)
             matmul = paddle.matmul(
                 transpose,

python/paddle/fluid/tests/unittests/ir/inference/test_trt_conv_quant_dequant_pass.py

@@ -30,9 +30,9 @@ class QuantDequantTensorRTSubgraphPassConvTest(QuantDequantTest):
             self.data = fluid.data(
                 name='data', shape=[1, 28, 28], dtype='float32'
             )
-            data_reshape = fluid.layers.reshape(self.data, shape=[1, 4, 14, 14])
+            data_reshape = paddle.reshape(self.data, shape=[1, 4, 14, 14])
             self.label = fluid.data(name='label', shape=[1, 1], dtype='int64')
-            label_shape = fluid.layers.reshape(self.label, shape=[1, 1, 1])
+            label_shape = paddle.reshape(self.label, shape=[1, 1, 1])
             conv_out = fluid.layers.conv2d(
                 input=data_reshape,
                 num_filters=self.conv_num_filters,
@@ -44,13 +44,13 @@ class QuantDequantTensorRTSubgraphPassConvTest(QuantDequantTest):
                 act=None,
             )
             if self.conv_padding == [1, 1]:
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 10816])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 10816])
             elif self.conv_padding == 'VALID':
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 7744])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 7744])
             elif self.conv_padding == 'SAME':
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 12544])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 12544])
             elif self.conv_groups == 4:
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 10816])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 10816])
             result = fluid.layers.relu(cout)
             loss = fluid.layers.cross_entropy(input=result, label=label_shape)
             avg_loss = paddle.mean(loss)
@@ -140,9 +140,9 @@ class DynamicShapeQuantDequantTensorRTSubgraphPassConvTest(QuantDequantTest):
             self.data = fluid.data(
                 name='data', shape=[1, 28, 28], dtype='float32'
             )
-            data_reshape = fluid.layers.reshape(self.data, shape=[1, 4, 14, 14])
+            data_reshape = paddle.reshape(self.data, shape=[1, 4, 14, 14])
             self.label = fluid.data(name='label', shape=[1, 1], dtype='int64')
-            label_shape = fluid.layers.reshape(self.label, shape=[1, 1, 1])
+            label_shape = paddle.reshape(self.label, shape=[1, 1, 1])
             conv_out = fluid.layers.conv2d(
                 input=data_reshape,
                 num_filters=self.conv_num_filters,
@@ -153,7 +153,7 @@ class DynamicShapeQuantDequantTensorRTSubgraphPassConvTest(QuantDequantTest):
                 use_cudnn=self.use_cudnn,
                 act=None,
             )
-            cout = fluid.layers.reshape(conv_out, shape=[1, 1, 10816])
+            cout = paddle.reshape(conv_out, shape=[1, 1, 10816])
             result = fluid.layers.relu(cout)
             loss = fluid.layers.cross_entropy(input=result, label=label_shape)
             avg_loss = paddle.mean(loss)
@@ -234,9 +234,9 @@ class QuantDequantTensorRTSubgraphPassConvTransposeTest(QuantDequantTest):
             self.data = fluid.data(
                 name='data', shape=[1, 28, 28], dtype='float32'
             )
-            data_reshape = fluid.layers.reshape(self.data, shape=[1, 4, 14, 14])
+            data_reshape = paddle.reshape(self.data, shape=[1, 4, 14, 14])
             self.label = fluid.data(name='label', shape=[1, 1], dtype='int64')
-            label_shape = fluid.layers.reshape(self.label, shape=[1, 1, 1])
+            label_shape = paddle.reshape(self.label, shape=[1, 1, 1])
             conv_out = fluid.layers.conv2d_transpose(
                 input=data_reshape,
                 num_filters=self.conv_num_filters,
@@ -248,13 +248,13 @@ class QuantDequantTensorRTSubgraphPassConvTransposeTest(QuantDequantTest):
                 act=None,
             )
             if self.conv_padding == [1, 1]:
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 14400])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 14400])
             elif self.conv_padding == 'VALID':
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 18496])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 18496])
             elif self.conv_padding == 'SAME':
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 12544])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 12544])
             elif self.conv_groups == 4:
-                cout = fluid.layers.reshape(conv_out, shape=[1, 1, 10816])
+                cout = paddle.reshape(conv_out, shape=[1, 1, 10816])
             result = fluid.layers.relu(cout)
             loss = fluid.layers.cross_entropy(input=result, label=label_shape)
             avg_loss = paddle.mean(loss)

python/paddle/fluid/tests/unittests/ir/inference/test_trt_fc_fuse_quant_dequant_pass.py

@@ -102,7 +102,7 @@ class FCQuantDequantFusePassTRTDims3Cols2Test(QuantDequantTest):
                 bias_attr=False,
                 act=None,
             )
-            c_out = fluid.layers.reshape(fc_out, shape=[0, 784])
+            c_out = paddle.reshape(fc_out, shape=[0, 784])
             result = fluid.layers.relu(c_out)
             loss = fluid.layers.cross_entropy(input=result, label=self.label)
             avg_loss = paddle.mean(loss)
@@ -162,8 +162,8 @@ class FCQuantDequantFusePassTRTDims3Cols3Test(QuantDequantTest):
                 name='data', shape=[1, 28, 28], dtype='float32'
             )
             self.label = fluid.data(name='label', shape=[1, 1], dtype='int64')
-            label_shape = fluid.layers.reshape(self.label, shape=[1, 1, 1])
-            reshape_out = fluid.layers.reshape(self.data, shape=[1, 14, 14, 4])
+            label_shape = paddle.reshape(self.label, shape=[1, 1, 1])
+            reshape_out = paddle.reshape(self.data, shape=[1, 14, 14, 4])
             fc_out = fluid.layers.fc(
                 input=reshape_out,
                 size=14,
@@ -171,7 +171,7 @@ class FCQuantDequantFusePassTRTDims3Cols3Test(QuantDequantTest):
                 bias_attr=False,
                 act=None,
             )
-            c_out = fluid.layers.reshape(fc_out, shape=[1, 1, 2744])
+            c_out = paddle.reshape(fc_out, shape=[1, 1, 2744])
             result = fluid.layers.relu(c_out)
             loss = fluid.layers.cross_entropy(input=result, label=label_shape)
             avg_loss = paddle.mean(loss)

python/paddle/fluid/tests/unittests/ir/inference/test_trt_matmul_quant_dequant.py

@@ -126,7 +126,7 @@ class TensorRTMatMulQuantDequantDims4Test(QuantDequantTest):
                 name='data', shape=[1, 28, 28], dtype='float32'
             )
             self.label = fluid.data(name='label', shape=[1, 1], dtype='int64')
-            reshape_out = fluid.layers.reshape(self.data, shape=[1, 4, 14, 14])
+            reshape_out = paddle.reshape(self.data, shape=[1, 4, 14, 14])
             matmul_out = fluid.layers.matmul(
                 x=reshape_out,
                 y=reshape_out,

python/paddle/fluid/tests/unittests/ir/inference/test_trt_multiclass_nms3_op.py

@@ -22,6 +22,7 @@ from paddle.fluid.framework import in_dygraph_mode
 from paddle.fluid.layer_helper import LayerHelper
 from paddle.fluid.core import PassVersionChecker
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 def multiclass_nms(
@@ -235,7 +236,7 @@ class TensorRTMultiClassNMS3Test(InferencePassTest):
                 nms_eta=self.nms_eta,
             )
             mutliclass_nms_out = multiclass_nms_out + 1.0
-            multiclass_nms_out = fluid.layers.reshape(
+            multiclass_nms_out = paddle.reshape(
                 multiclass_nms_out,
                 [self.bs, 1, self.keep_top_k, 6],
                 name='reshape',

python/paddle/fluid/tests/unittests/ir/inference/test_trt_multiclass_nms_op.py

@@ -20,6 +20,7 @@ import paddle.fluid as fluid
 import paddle.fluid.core as core
 from paddle.fluid.core import PassVersionChecker
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 class TensorRTMultiClassNMSTest(InferencePassTest):
@@ -62,7 +63,7 @@ class TensorRTMultiClassNMSTest(InferencePassTest):
                 normalized=self.normalized,
             )
             mutliclass_nms_out = multiclass_nms_out + 1.0
-            multiclass_nms_out = fluid.layers.reshape(
+            multiclass_nms_out = paddle.reshape(
                 multiclass_nms_out,
                 [self.bs, 1, self.keep_top_k, 6],
                 name='reshape',

python/paddle/fluid/tests/unittests/ir/inference/test_trt_reshape_op.py

@@ -19,6 +19,7 @@ import paddle.fluid as fluid
 import paddle.fluid.core as core
 from paddle.fluid.core import PassVersionChecker
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 class TRTReshapeTest(InferencePassTest):
@@ -48,7 +49,7 @@ class TRTReshapeTest(InferencePassTest):
         self.fetch_list = [out]
 
     def append_reshape(self, data, reshape):
-        return fluid.layers.reshape(data, reshape)
+        return paddle.reshape(data, reshape)
 
     def test_check_output(self):
         if core.is_compiled_with_cuda():
@@ -101,7 +102,7 @@ class TRTReshapeTest2(TRTReshapeTest):
             data = fluid.data(
                 name='data', shape=self.data_shape, dtype='float32'
             )
-            reshape_out = fluid.layers.reshape(x=data, shape=self.reshape)
+            reshape_out = paddle.reshape(x=data, shape=self.reshape)
             out = fluid.layers.batch_norm(reshape_out, is_test=True)
         self.feeds = {
             'data': np.random.random(self.data_shape).astype('float32')

python/paddle/fluid/tests/unittests/ir/inference/test_trt_shuffle_channel_detect_pass.py

@@ -18,6 +18,7 @@ from inference_pass_test import InferencePassTest
 import paddle.fluid as fluid
 from paddle.fluid.core import PassVersionChecker
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 class ShuffleChannelFuseTRTPassTest(InferencePassTest):
@@ -26,9 +27,9 @@ class ShuffleChannelFuseTRTPassTest(InferencePassTest):
             data = fluid.data(
                 name="data", shape=[-1, 6, 64, 64], dtype="float32"
             )
-            reshape1 = fluid.layers.reshape(x=data, shape=[-1, 2, 3, 64, 64])
+            reshape1 = paddle.reshape(x=data, shape=[-1, 2, 3, 64, 64])
             trans = fluid.layers.transpose(x=reshape1, perm=[0, 2, 1, 3, 4])
-            reshape2 = fluid.layers.reshape(x=trans, shape=[-1, 6, 64, 64])
+            reshape2 = paddle.reshape(x=trans, shape=[-1, 6, 64, 64])
             out = fluid.layers.batch_norm(reshape2, is_test=True)
 
         self.feeds = {

python/paddle/fluid/tests/unittests/ir/inference/test_trt_subgraph_pass.py

@@ -21,6 +21,7 @@ import paddle.fluid as fluid
 import paddle.fluid.core as core
 from paddle.fluid.core import PassVersionChecker
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 class TensorRTSubgraphPassFcTest(InferencePassTest):
@@ -30,7 +31,7 @@ class TensorRTSubgraphPassFcTest(InferencePassTest):
                 name="data", shape=[-1, 6, 64, 64], dtype="float32"
             )
             fc_out = fluid.layers.fc(input=[data], act=None, size=1000)
-            reshape_out = fluid.layers.reshape(x=fc_out, shape=[1, 1000])
+            reshape_out = paddle.reshape(x=fc_out, shape=[1, 1000])
         self.feeds = {
             "data": np.random.random([1, 6, 64, 64]).astype("float32"),
         }

python/paddle/fluid/tests/unittests/ir/inference/test_trt_transpose_flatten_concat_fuse_pass.py

@@ -18,6 +18,7 @@ from inference_pass_test import InferencePassTest
 import paddle.fluid as fluid
 import paddle.fluid.core as core
 from paddle.fluid.core import AnalysisConfig
+import paddle
 
 
 class TransposeFlattenConcatFusePassTRTTest(InferencePassTest):
@@ -36,7 +37,7 @@ class TransposeFlattenConcatFusePassTRTTest(InferencePassTest):
             concat_out = fluid.layers.concat([flatt1, flatt2], axis=1)
             # There is no parameters for above structure.
             # Hence, append a batch_norm to avoid failure caused by load_combined.
-            reshape_out = fluid.layers.reshape(concat_out, [-1, 0, 1, 1])
+            reshape_out = paddle.reshape(concat_out, [-1, 0, 1, 1])
             out = fluid.layers.batch_norm(reshape_out, is_test=True)
 
         self.feeds = {

python/paddle/fluid/tests/unittests/parallel_dygraph_mnist.py

@@ -100,7 +100,7 @@ class MNIST(fluid.dygraph.Layer):
     def forward(self, inputs, label):
         x = self._simple_img_conv_pool_1(inputs)
         x = self._simple_img_conv_pool_2(x)
-        x = fluid.layers.reshape(x, shape=[-1, self.pool_2_shape])
+        x = paddle.reshape(x, shape=[-1, self.pool_2_shape])
         cost = self._fc(x)
         loss = fluid.layers.cross_entropy(cost, label)
         avg_loss = paddle.mean(loss)

python/paddle/fluid/tests/unittests/parallel_dygraph_sparse_embedding.py

@@ -68,11 +68,11 @@ class SimpleNet(fluid.Layer):
         x_emb = self.embedding(input)
         fc = fluid.layers.matmul(x_emb, self.softmax_weight)
         fc = fluid.layers.elementwise_add(fc, self.softmax_bias)
-        projection = fluid.layers.reshape(fc, shape=[-1, self.vocab_size])
+        projection = paddle.reshape(fc, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/seresnext_net.py

@@ -48,9 +48,7 @@ def squeeze_excitation(input, num_channels, reduction_ratio):
     #    input=input, pool_size=0, pool_type='avg', global_pooling=True)
     conv = input
     shape = conv.shape
-    reshape = fluid.layers.reshape(
-        x=conv, shape=[-1, shape[1], shape[2] * shape[3]]
-    )
+    reshape = paddle.reshape(x=conv, shape=[-1, shape[1], shape[2] * shape[3]])
     pool = fluid.layers.reduce_mean(input=reshape, dim=2)
 
     squeeze = fluid.layers.fc(
@@ -161,9 +159,7 @@ def SE_ResNeXt50Small(use_feed):
             )
 
     shape = conv.shape
-    reshape = fluid.layers.reshape(
-        x=conv, shape=[-1, shape[1], shape[2] * shape[3]]
-    )
+    reshape = paddle.reshape(x=conv, shape=[-1, shape[1], shape[2] * shape[3]])
     pool = fluid.layers.reduce_mean(input=reshape, dim=2)
     dropout = (
         pool

python/paddle/fluid/tests/unittests/test_beam_search_op.py

@@ -18,6 +18,7 @@ import unittest
 import numpy as np
 import paddle.fluid as fluid
 from paddle.fluid.framework import Program, program_guard
+import paddle
 
 
 def create_tensor(scope, name, np_data):
@@ -312,7 +313,7 @@ class TestBeamSearchOpError(unittest.TestCase):
             topk_scores, topk_indices = fluid.layers.topk(probs, k=4)
             accu_scores = fluid.layers.elementwise_add(
                 x=fluid.layers.log(x=topk_scores),
-                y=fluid.layers.reshape(pre_scores, shape=[-1]),
+                y=paddle.reshape(pre_scores, shape=[-1]),
                 axis=0,
             )
 

python/paddle/fluid/tests/unittests/test_dist_fleet_ps.py

@@ -84,7 +84,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -116,7 +116,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -147,7 +147,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps11.py

@@ -80,7 +80,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -108,7 +108,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -135,7 +135,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps12.py

@@ -83,7 +83,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -111,7 +111,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -138,7 +138,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps13.py

@@ -86,7 +86,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -116,7 +116,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -145,7 +145,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps2.py

@@ -85,7 +85,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -116,7 +116,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -145,7 +145,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps3.py

@@ -84,7 +84,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -116,7 +116,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -147,7 +147,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps4.py

@@ -82,7 +82,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -112,7 +112,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -141,7 +141,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps5.py

@@ -84,7 +84,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -116,7 +116,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=is_sparse,
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -147,7 +147,7 @@ class TestPSPassWithBow(unittest.TestCase):
             ),
             is_sparse=False,
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_fleet_ps6.py

@@ -82,7 +82,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        q_emb = fluid.layers.reshape(q_emb, [-1, emb_dim])
+        q_emb = paddle.reshape(q_emb, [-1, emb_dim])
         # vsum
         q_sum = fluid.layers.sequence_pool(input=q_emb, pool_type='sum')
         q_ss = paddle.nn.functional.softsign(q_sum)
@@ -112,7 +112,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        pt_emb = fluid.layers.reshape(pt_emb, [-1, emb_dim])
+        pt_emb = paddle.reshape(pt_emb, [-1, emb_dim])
         # vsum
         pt_sum = fluid.layers.sequence_pool(input=pt_emb, pool_type='sum')
         pt_ss = paddle.nn.functional.softsign(pt_sum)
@@ -141,7 +141,7 @@ class TestPSPassWithBow(unittest.TestCase):
                 learning_rate=emb_lr,
             ),
         )
-        nt_emb = fluid.layers.reshape(nt_emb, [-1, emb_dim])
+        nt_emb = paddle.reshape(nt_emb, [-1, emb_dim])
         # vsum
         nt_sum = fluid.layers.sequence_pool(input=nt_emb, pool_type='sum')
         nt_ss = paddle.nn.functional.softsign(nt_sum)

python/paddle/fluid/tests/unittests/test_dist_transpiler.py

@@ -381,7 +381,7 @@ class TestFakeInit(TranspilerTest):
             ),
         )
 
-        neg_word_reshape = fluid.layers.reshape(inputs[2], shape=[-1, 1])
+        neg_word_reshape = paddle.reshape(inputs[2], shape=[-1, 1])
         neg_word_reshape.stop_gradient = True
 
         neg_emb_w = fluid.layers.embedding(
@@ -391,7 +391,7 @@ class TestFakeInit(TranspilerTest):
             param_attr=fluid.ParamAttr(name='emb_w', learning_rate=1.0),
         )
 
-        neg_emb_w_re = fluid.layers.reshape(
+        neg_emb_w_re = paddle.reshape(
             neg_emb_w, shape=[-1, neg_num, embedding_size]
         )
 
@@ -402,7 +402,7 @@ class TestFakeInit(TranspilerTest):
             param_attr=fluid.ParamAttr(name='emb_b', learning_rate=1.0),
         )
 
-        neg_emb_b_vec = fluid.layers.reshape(neg_emb_b, shape=[-1, neg_num])
+        neg_emb_b_vec = paddle.reshape(neg_emb_b, shape=[-1, neg_num])
 
         true_logits = fluid.layers.elementwise_add(
             fluid.layers.reduce_sum(
@@ -413,14 +413,12 @@ class TestFakeInit(TranspilerTest):
             true_emb_b,
         )
 
-        input_emb_re = fluid.layers.reshape(
-            input_emb, shape=[-1, 1, embedding_size]
-        )
+        input_emb_re = paddle.reshape(input_emb, shape=[-1, 1, embedding_size])
 
         neg_matmul = fluid.layers.matmul(
             input_emb_re, neg_emb_w_re, transpose_y=True
         )
-        neg_matmul_re = fluid.layers.reshape(neg_matmul, shape=[-1, neg_num])
+        neg_matmul_re = paddle.reshape(neg_matmul, shape=[-1, neg_num])
         neg_logits = fluid.layers.elementwise_add(neg_matmul_re, neg_emb_b_vec)
         # nce loss
         label_ones = fluid.layers.fill_constant_batch_size_like(

python/paddle/fluid/tests/unittests/test_dygraph_mnist_fp16.py

@@ -115,7 +115,7 @@ class MNIST(fluid.dygraph.Layer):
     def forward(self, inputs, label):
         x = paddle.nn.functional.relu(self._simple_img_conv_pool_1(inputs))
         x = paddle.nn.functional.relu(self._simple_img_conv_pool_2(x))
-        x = fluid.layers.reshape(x, shape=[-1, self.pool_2_shape])
+        x = paddle.reshape(x, shape=[-1, self.pool_2_shape])
         cost = self._linear(x)
         loss = fluid.layers.cross_entropy(cost, label)
         avg_loss = paddle.mean(loss)

python/paddle/fluid/tests/unittests/test_dygraph_multi_forward.py

@@ -104,7 +104,7 @@ class MNIST(fluid.dygraph.Layer):
     def forward(self, inputs):
         x = self._simple_img_conv_pool_1(inputs)
         x = self._simple_img_conv_pool_2(x)
-        x = fluid.layers.reshape(x, shape=[-1, self.pool_2_shape])
+        x = paddle.reshape(x, shape=[-1, self.pool_2_shape])
         x = self._fc(x)
         return x
 

python/paddle/fluid/tests/unittests/test_eager_deletion_padding_rnn.py

@@ -149,8 +149,8 @@ def lm_model(
             pre_cell = layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = layers.reshape(pre_hidden, shape=[-1, hidden_size])
-            pre_cell = layers.reshape(pre_cell, shape=[-1, hidden_size])
+            pre_hidden = paddle.reshape(pre_hidden, shape=[-1, hidden_size])
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, hidden_size])
             hidden_array.append(pre_hidden)
             cell_array.append(pre_cell)
 
@@ -270,12 +270,8 @@ def lm_model(
             pre_cell = layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = layers.reshape(
-                pre_hidden, shape=[-1, hidden_size], inplace=True
-            )
-            pre_cell = layers.reshape(
-                pre_cell, shape=[-1, hidden_size], inplace=True
-            )
+            pre_hidden = paddle.reshape(pre_hidden, shape=[-1, hidden_size])
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, hidden_size])
             hidden_array.append(pre_hidden)
             cell_array.append(pre_cell)
 
@@ -286,7 +282,7 @@ def lm_model(
 
         for index in range(len):
             input = sliced_inputs[index]
-            input = layers.reshape(input, shape=[-1, hidden_size], inplace=True)
+            input = paddle.reshape(input, shape=[-1, hidden_size])
             for k in range(num_layers):
                 pre_hidden = hidden_array[k]
                 pre_cell = cell_array[k]
@@ -318,21 +314,19 @@ def lm_model(
             res.append(input)
 
         last_hidden = layers.concat(hidden_array, 1)
-        last_hidden = layers.reshape(
-            last_hidden, shape=[-1, num_layers, hidden_size], inplace=True
+        last_hidden = paddle.reshape(
+            last_hidden, shape=[-1, num_layers, hidden_size]
         )
         last_hidden = layers.transpose(x=last_hidden, perm=[1, 0, 2])
 
         last_cell = layers.concat(cell_array, 1)
-        last_cell = layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, num_layers, hidden_size]
         )
         last_cell = layers.transpose(x=last_cell, perm=[1, 0, 2])
 
         real_res = layers.concat(res, 0)
-        real_res = layers.reshape(
-            real_res, shape=[len, -1, hidden_size], inplace=True
-        )
+        real_res = paddle.reshape(real_res, shape=[len, -1, hidden_size])
         real_res = layers.transpose(x=real_res, perm=[1, 0, 2])
 
         return real_res, last_hidden, last_cell
@@ -367,10 +361,10 @@ def lm_model(
     init_cell.persistable = True
     init_hidden.persistable = True
 
-    init_hidden_reshape = layers.reshape(
+    init_hidden_reshape = paddle.reshape(
         init_hidden, shape=[num_layers, -1, hidden_size]
     )
-    init_cell_reshape = layers.reshape(
+    init_cell_reshape = paddle.reshape(
         init_cell, shape=[num_layers, -1, hidden_size]
     )
 
@@ -387,9 +381,7 @@ def lm_model(
         ),
     )
 
-    x_emb = layers.reshape(
-        x_emb, shape=[-1, num_steps, hidden_size], inplace=True
-    )
+    x_emb = paddle.reshape(x_emb, shape=[-1, num_steps, hidden_size])
     if dropout is not None and dropout > 0.0:
         x_emb = layers.dropout(
             x_emb,
@@ -447,9 +439,7 @@ def lm_model(
         print("type not support")
         return
 
-    rnn_out = layers.reshape(
-        rnn_out, shape=[-1, num_steps, hidden_size], inplace=True
-    )
+    rnn_out = paddle.reshape(rnn_out, shape=[-1, num_steps, hidden_size])
 
     softmax_weight = layers.create_parameter(
         [hidden_size, vocab_size],
@@ -470,15 +460,13 @@ def lm_model(
 
     projection = layers.matmul(rnn_out, softmax_weight)
     projection = layers.elementwise_add(projection, softmax_bias)
-    projection = layers.reshape(
-        projection, shape=[-1, vocab_size], inplace=True
-    )
+    projection = paddle.reshape(projection, shape=[-1, vocab_size])
 
     loss = layers.softmax_with_cross_entropy(
         logits=projection, label=y, soft_label=False
     )
 
-    loss = layers.reshape(loss, shape=[-1, num_steps], inplace=True)
+    loss = paddle.reshape(loss, shape=[-1, num_steps])
     loss = layers.reduce_mean(loss, dim=[0])
     loss = layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_eager_deletion_while_op.py

@@ -107,8 +107,8 @@ class TestEagerDeletionWhileOpBase(unittest.TestCase):
         with while_op.block():
             d = layers.array_read(array=data_array, i=i)
             prev = layers.array_read(array=mem_array, i=i)
-            d = layers.reshape(d, shape=[10])
-            prev = layers.reshape(prev, shape=[10])
+            d = paddle.reshape(d, shape=[10])
+            prev = paddle.reshape(prev, shape=[10])
             result = layers.sums(input=[d, prev])
 
             i = layers.increment(x=i, in_place=True)
@@ -117,8 +117,8 @@ class TestEagerDeletionWhileOpBase(unittest.TestCase):
             with while_op2.block():
                 d2 = layers.array_read(array=data_array, i=j)
                 prev2 = layers.array_read(array=mem_array, i=j)
-                d2 = layers.reshape(d2, shape=[10])
-                prev2 = layers.reshape(prev2, shape=[10])
+                d2 = paddle.reshape(d2, shape=[10])
+                prev2 = paddle.reshape(prev2, shape=[10])
                 result2 = layers.sums(input=[d2, prev2])
 
                 j = layers.increment(x=j, in_place=True)

python/paddle/fluid/tests/unittests/test_embedding_id_stop_gradient.py

@@ -52,7 +52,7 @@ class TestEmbeddingIdStopGradientBase(unittest.TestCase):
                 x = fluid.layers.concat([x_1, x_2], axis=-1)
 
                 for _ in range(self.reshape_times):
-                    x = fluid.layers.reshape(x, [-1, 1])
+                    x = paddle.reshape(x, [-1, 1])
 
                 x.stop_gradient = stop_gradient
 

python/paddle/fluid/tests/unittests/test_fuse_relu_depthwise_conv_pass.py

@@ -54,7 +54,7 @@ def simple_depthwise_net(use_feed):
     assert use_feed
     img = fluid.layers.data(name='image', shape=[784], dtype='float32')
     label = fluid.layers.data(name='label', shape=[1], dtype='int64')
-    hidden = fluid.layers.reshape(img, (-1, 1, 28, 28))
+    hidden = paddle.reshape(img, (-1, 1, 28, 28))
     for _ in range(4):
         hidden = sep_conv(hidden, channel=200, stride=2, filter=5)
         hidden = fluid.layers.relu(hidden)

python/paddle/fluid/tests/unittests/test_imperative_basic.py

@@ -140,7 +140,7 @@ class SimpleRNN(fluid.Layer):
             input = fluid.layers.slice(
                 inputs, axes=[1], starts=[i], ends=[i + 1]
             )
-            input = fluid.layers.reshape(input, shape=[1, 3])
+            input = paddle.reshape(input, shape=[1, 3])
             out_softmax, pre_hidden = self._cell(input, pre_hidden)
             outs.append(out_softmax)
 
@@ -739,15 +739,11 @@ class TestImperative(unittest.TestCase):
             )
 
             a = fluid.layers.expand(
-                fluid.layers.reshape(
-                    fluid.layers.reduce_sum(inp_data1), [1, 1]
-                ),
+                paddle.reshape(fluid.layers.reduce_sum(inp_data1), [1, 1]),
                 [4, 1],
             )
             b = fluid.layers.expand(
-                fluid.layers.reshape(
-                    fluid.layers.reduce_sum(inp_data2), [1, 1]
-                ),
+                paddle.reshape(fluid.layers.reduce_sum(inp_data2), [1, 1]),
                 [4, 1],
             )
             cond = fluid.layers.less_than(x=a, y=b)
@@ -796,7 +792,7 @@ class TestImperative(unittest.TestCase):
         np_inp = np_inp.astype(np.float32)
         with fluid.dygraph.guard():
             var_inp = paddle.to_tensor(np_inp)
-            var_inp = fluid.layers.reshape(var_inp, shape=[1, 4, 3])
+            var_inp = paddle.reshape(var_inp, shape=[1, 4, 3])
             simple_rnn = SimpleRNN()
             outs, pre_hiddens = simple_rnn.forward(var_inp)
             dy_out = outs[3].numpy()
@@ -807,7 +803,7 @@ class TestImperative(unittest.TestCase):
 
         with fluid.dygraph.guard():
             var_inp2 = paddle.to_tensor(np_inp)
-            var_inp2 = fluid.layers.reshape(var_inp2, shape=[1, 4, 3])
+            var_inp2 = paddle.reshape(var_inp2, shape=[1, 4, 3])
             simple_rnn2 = SimpleRNN()
             outs2, pre_hiddens2 = simple_rnn2.forward(var_inp2)
             dy_out2 = outs2[3].numpy()

python/paddle/fluid/tests/unittests/test_imperative_gnn.py

@@ -92,7 +92,7 @@ class TestDygraphGNN(unittest.TestCase):
 
             model = GCN('test_gcn', 50)
             logits = model(features, adj)
-            logits = fluid.layers.reshape(logits, logits.shape[1:])
+            logits = paddle.reshape(logits, logits.shape[1:])
             # In other example, it's nll with log_softmax. However, paddle's
             # log_loss only supports binary classification now.
             loss = fluid.layers.softmax_with_cross_entropy(logits, labels)
@@ -130,7 +130,7 @@ class TestDygraphGNN(unittest.TestCase):
 
             model = GCN('test_gcn', 50)
             logits = model(to_variable(features), to_variable(adj))
-            logits = fluid.layers.reshape(logits, logits.shape[1:])
+            logits = paddle.reshape(logits, logits.shape[1:])
             # In other example, it's nll with log_softmax. However, paddle's
             # log_loss only supports binary classification now.
             loss = fluid.layers.softmax_with_cross_entropy(
@@ -158,7 +158,7 @@ class TestDygraphGNN(unittest.TestCase):
 
             model2 = GCN('test_gcn', 50)
             logits2 = model2(to_variable(features2), to_variable(adj2))
-            logits2 = fluid.layers.reshape(logits2, logits2.shape[1:])
+            logits2 = paddle.reshape(logits2, logits2.shape[1:])
             # In other example, it's nll with log_softmax. However, paddle's
             # log_loss only supports binary classification now.
             loss2 = fluid.layers.softmax_with_cross_entropy(

python/paddle/fluid/tests/unittests/test_imperative_lod_tensor_to_selected_rows.py

@@ -66,13 +66,11 @@ class SimpleNet(fluid.Layer):
             x_emb, fluid.layers.transpose(self.embedding.weight, perm=[1, 0])
         )
         projection = fluid.layers.elementwise_add(projection, self.softmax_bias)
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_imperative_mnist.py

@@ -103,7 +103,7 @@ class MNIST(fluid.dygraph.Layer):
     def forward(self, inputs):
         x = self._simple_img_conv_pool_1(inputs)
         x = self._simple_img_conv_pool_2(x)
-        x = fluid.layers.reshape(x, shape=[-1, self.pool_2_shape])
+        x = paddle.reshape(x, shape=[-1, self.pool_2_shape])
         x = self._fc(x)
         return x
 

python/paddle/fluid/tests/unittests/test_imperative_ocr_attention_model.py

@@ -195,13 +195,9 @@ class DynamicGRU(fluid.dygraph.Layer):
             input_ = fluid.layers.slice(
                 inputs, axes=[1], starts=[i], ends=[i + 1]
             )
-            input_ = fluid.layers.reshape(
-                input_, [-1, input_.shape[2]], inplace=False
-            )
+            input_ = paddle.reshape(input_, [-1, input_.shape[2]])
             hidden, reset, gate = self.gru_unit(input_, hidden)
-            hidden_ = fluid.layers.reshape(
-                hidden, [-1, 1, hidden.shape[1]], inplace=False
-            )
+            hidden_ = paddle.reshape(hidden, [-1, 1, hidden.shape[1]])
             if self.is_reverse:
                 res = [hidden_] + res
             else:
@@ -271,7 +267,7 @@ class EncoderNet(fluid.dygraph.Layer):
         transpose_conv_features = fluid.layers.transpose(
             conv_features, perm=[0, 3, 1, 2]
         )
-        sliced_feature = fluid.layers.reshape(
+        sliced_feature = paddle.reshape(
             transpose_conv_features,
             [
                 -1,
@@ -279,7 +275,6 @@ class EncoderNet(fluid.dygraph.Layer):
                 transpose_conv_features.shape[2]
                 * transpose_conv_features.shape[3],
             ],
-            inplace=False,
         )
         fc_1 = self.fc_1_layer(sliced_feature)
         fc_2 = self.fc_2_layer(sliced_feature)
@@ -308,8 +303,8 @@ class SimpleAttention(fluid.dygraph.Layer):
     def forward(self, encoder_vec, encoder_proj, decoder_state):
 
         decoder_state_fc = self.fc_1(decoder_state)
-        decoder_state_proj_reshape = fluid.layers.reshape(
-            decoder_state_fc, [-1, 1, decoder_state_fc.shape[1]], inplace=False
+        decoder_state_proj_reshape = paddle.reshape(
+            decoder_state_fc, [-1, 1, decoder_state_fc.shape[1]]
         )
         decoder_state_expand = fluid.layers.expand(
             decoder_state_proj_reshape, [1, encoder_proj.shape[1], 1]
@@ -320,10 +315,9 @@ class SimpleAttention(fluid.dygraph.Layer):
         concated = paddle.tanh(x=concated)
         attention_weight = self.fc_2(concated)
 
-        weights_reshape = fluid.layers.reshape(
+        weights_reshape = paddle.reshape(
             x=attention_weight,
             shape=[attention_weight.shape[0], attention_weight.shape[1]],
-            inplace=False,
         )
 
         weights_reshape = fluid.layers.softmax(weights_reshape)
@@ -364,8 +358,8 @@ class GRUDecoderWithAttention(fluid.dygraph.Layer):
             current_word = fluid.layers.slice(
                 target_embedding, axes=[1], starts=[i], ends=[i + 1]
             )
-            current_word = fluid.layers.reshape(
-                current_word, [-1, current_word.shape[2]], inplace=False
+            current_word = paddle.reshape(
+                current_word, [-1, current_word.shape[2]]
             )
 
             context = self.simple_attention(
@@ -407,17 +401,16 @@ class OCRAttention(fluid.dygraph.Layer):
         backward_first = fluid.layers.slice(
             gru_backward, axes=[1], starts=[0], ends=[1]
         )
-        backward_first = fluid.layers.reshape(
-            backward_first, [-1, backward_first.shape[2]], inplace=False
+        backward_first = paddle.reshape(
+            backward_first, [-1, backward_first.shape[2]]
         )
         decoder_boot = self.fc(backward_first)
-        label_in = fluid.layers.reshape(label_in, [-1], inplace=False)
+        label_in = paddle.reshape(label_in, [-1])
         trg_embedding = self.embedding(label_in)
 
-        trg_embedding = fluid.layers.reshape(
+        trg_embedding = paddle.reshape(
             trg_embedding,
             [-1, Config.max_length, trg_embedding.shape[1]],
-            inplace=False,
         )
 
         prediction = self.gru_decoder_with_attention(
@@ -497,11 +490,9 @@ class TestDygraphOCRAttention(unittest.TestCase):
                     label_out.stop_gradient = True
                     img = to_variable(image_np)
                     dy_prediction = ocr_attention(img, label_in)
-                    label_out = fluid.layers.reshape(
-                        label_out, [-1, 1], inplace=False
-                    )
-                    dy_prediction = fluid.layers.reshape(
-                        dy_prediction, [label_out.shape[0], -1], inplace=False
+                    label_out = paddle.reshape(label_out, [-1, 1])
+                    dy_prediction = paddle.reshape(
+                        dy_prediction, [label_out.shape[0], -1]
                     )
                     loss = fluid.layers.cross_entropy(
                         input=dy_prediction, label=label_out
@@ -577,7 +568,7 @@ class TestDygraphOCRAttention(unittest.TestCase):
 
             static_prediction = ocr_attention(images, static_label_in)
 
-            static_prediction = fluid.layers.reshape(
+            static_prediction = paddle.reshape(
                 static_prediction, shape=[-1, Config.num_classes + 2]
             )
 

python/paddle/fluid/tests/unittests/test_imperative_optimizer.py

@@ -141,7 +141,7 @@ class TestImperativeOptimizerBase(unittest.TestCase):
                 label = data[1]
                 label.stop_gradient = True
 
-                img = fluid.layers.reshape(img, shape=[batch_size, -1])
+                img = paddle.reshape(img, shape=[batch_size, -1])
                 cost = mlp(img)
                 avg_loss = fluid.layers.reduce_mean(cost)
                 dy_out = avg_loss.numpy()
@@ -180,7 +180,7 @@ class TestImperativeOptimizerBase(unittest.TestCase):
                 name='pixel', shape=[1, 28, 28], dtype='float32'
             )
             label = fluid.layers.data(name='label', shape=[1], dtype='int64')
-            img = fluid.layers.reshape(img, shape=[batch_size, 784])
+            img = paddle.reshape(img, shape=[batch_size, 784])
             cost = mlp(img)
             avg_loss = fluid.layers.reduce_mean(cost)
             optimizer.minimize(avg_loss)

python/paddle/fluid/tests/unittests/test_imperative_optimizer_v2.py

@@ -139,7 +139,7 @@ class TestImperativeOptimizerBase(unittest.TestCase):
 
             label.stop_gradient = True
 
-            img = fluid.layers.reshape(img, shape=[batch_size, -1])
+            img = paddle.reshape(img, shape=[batch_size, -1])
             cost = mlp(img)
             avg_loss = fluid.layers.reduce_mean(cost)
             dy_out = avg_loss.numpy()
@@ -189,7 +189,7 @@ class TestImperativeOptimizerBase(unittest.TestCase):
                 name='pixel', shape=[1, 28, 28], dtype='float32'
             )
             label = fluid.layers.data(name='label', shape=[1], dtype='int64')
-            img = fluid.layers.reshape(img, shape=[batch_size, 784])
+            img = paddle.reshape(img, shape=[batch_size, 784])
             cost = mlp(img)
             avg_loss = fluid.layers.reduce_mean(cost)
             optimizer.minimize(avg_loss)

python/paddle/fluid/tests/unittests/test_imperative_ptb_rnn.py

@@ -85,12 +85,10 @@ class SimpleLSTMRNN(fluid.Layer):
             pre_cell = fluid.layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = fluid.layers.reshape(
+            pre_hidden = paddle.reshape(
                 pre_hidden, shape=[-1, self._hidden_size]
             )
-            pre_cell = fluid.layers.reshape(
-                pre_cell, shape=[-1, self._hidden_size]
-            )
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, self._hidden_size])
             self.hidden_array.append(pre_hidden)
             self.cell_array.append(pre_cell)
 
@@ -99,7 +97,7 @@ class SimpleLSTMRNN(fluid.Layer):
             self._input = fluid.layers.slice(
                 input_embedding, axes=[1], starts=[index], ends=[index + 1]
             )
-            self._input = fluid.layers.reshape(
+            self._input = paddle.reshape(
                 self._input, shape=[-1, self._hidden_size]
             )
             for k in range(self._num_layers):
@@ -130,19 +128,17 @@ class SimpleLSTMRNN(fluid.Layer):
                         dropout_implementation='upscale_in_train',
                     )
             res.append(
-                fluid.layers.reshape(
-                    self._input, shape=[1, -1, self._hidden_size]
-                )
+                paddle.reshape(self._input, shape=[1, -1, self._hidden_size])
             )
         real_res = fluid.layers.concat(res, 0)
         real_res = fluid.layers.transpose(x=real_res, perm=[1, 0, 2])
         last_hidden = fluid.layers.concat(self.hidden_array, 1)
-        last_hidden = fluid.layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_hidden = fluid.layers.transpose(x=last_hidden, perm=[1, 0, 2])
         last_cell = fluid.layers.concat(self.cell_array, 1)
-        last_cell = fluid.layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_cell = fluid.layers.transpose(x=last_cell, perm=[1, 0, 2])
@@ -203,16 +199,16 @@ class PtbModel(fluid.Layer):
         )
 
     def forward(self, input, label, init_hidden, init_cell):
-        init_h = fluid.layers.reshape(
+        init_h = paddle.reshape(
             init_hidden, shape=[self.num_layers, -1, self.hidden_size]
         )
 
-        init_c = fluid.layers.reshape(
+        init_c = paddle.reshape(
             init_cell, shape=[self.num_layers, -1, self.hidden_size]
         )
 
         x_emb = self.embedding(input)
-        x_emb = fluid.layers.reshape(
+        x_emb = paddle.reshape(
             x_emb, shape=[-1, self.num_steps, self.hidden_size]
         )
         if self.dropout is not None and self.dropout > 0.0:
@@ -224,18 +220,16 @@ class PtbModel(fluid.Layer):
         rnn_out, last_hidden, last_cell = self.simple_lstm_rnn(
             x_emb, init_h, init_c
         )
-        rnn_out = fluid.layers.reshape(
+        rnn_out = paddle.reshape(
             rnn_out, shape=[-1, self.num_steps, self.hidden_size]
         )
         projection = fluid.layers.matmul(rnn_out, self.softmax_weight)
         projection = fluid.layers.elementwise_add(projection, self.softmax_bias)
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_imperative_reinforcement.py

@@ -36,7 +36,7 @@ class Policy(fluid.dygraph.Layer):
         self.rewards = []
 
     def forward(self, inputs):
-        x = fluid.layers.reshape(inputs, shape=[-1, 4])
+        x = paddle.reshape(inputs, shape=[-1, 4])
         x = self.affine1(x)
         x = fluid.layers.dropout(x, self.dropout_ratio)
         x = fluid.layers.relu(x)

python/paddle/fluid/tests/unittests/test_imperative_resnet.py

@@ -241,7 +241,7 @@ class ResNet(fluid.Layer):
         for bottleneck_block in self.bottleneck_block_list:
             y = bottleneck_block(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_output])
         y = self.out(y)
         return y
 

python/paddle/fluid/tests/unittests/test_imperative_save_load.py

@@ -80,12 +80,10 @@ class SimpleLSTMRNN(fluid.Layer):
             pre_cell = fluid.layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = fluid.layers.reshape(
+            pre_hidden = paddle.reshape(
                 pre_hidden, shape=[-1, self._hidden_size]
             )
-            pre_cell = fluid.layers.reshape(
-                pre_cell, shape=[-1, self._hidden_size]
-            )
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, self._hidden_size])
             self.hidden_array.append(pre_hidden)
             self.cell_array.append(pre_cell)
 
@@ -94,7 +92,7 @@ class SimpleLSTMRNN(fluid.Layer):
             self._input = fluid.layers.slice(
                 input_embedding, axes=[1], starts=[index], ends=[index + 1]
             )
-            self._input = fluid.layers.reshape(
+            self._input = paddle.reshape(
                 self._input, shape=[-1, self._hidden_size]
             )
             for k in range(self._num_layers):
@@ -125,19 +123,17 @@ class SimpleLSTMRNN(fluid.Layer):
                         dropout_implementation='upscale_in_train',
                     )
             res.append(
-                fluid.layers.reshape(
-                    self._input, shape=[1, -1, self._hidden_size]
-                )
+                paddle.reshape(self._input, shape=[1, -1, self._hidden_size])
             )
         real_res = fluid.layers.concat(res, 0)
         real_res = fluid.layers.transpose(x=real_res, perm=[1, 0, 2])
         last_hidden = fluid.layers.concat(self.hidden_array, 1)
-        last_hidden = fluid.layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_hidden = fluid.layers.transpose(x=last_hidden, perm=[1, 0, 2])
         last_cell = fluid.layers.concat(self.cell_array, 1)
-        last_cell = fluid.layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_cell = fluid.layers.transpose(x=last_cell, perm=[1, 0, 2])
@@ -198,16 +194,16 @@ class PtbModel(fluid.Layer):
         )
 
     def forward(self, input, label, init_hidden, init_cell):
-        init_h = fluid.layers.reshape(
+        init_h = paddle.reshape(
             init_hidden, shape=[self.num_layers, -1, self.hidden_size]
         )
 
-        init_c = fluid.layers.reshape(
+        init_c = paddle.reshape(
             init_cell, shape=[self.num_layers, -1, self.hidden_size]
         )
 
         x_emb = self.embedding(input)
-        x_emb = fluid.layers.reshape(
+        x_emb = paddle.reshape(
             x_emb, shape=[-1, self.num_steps, self.hidden_size]
         )
         if self.dropout is not None and self.dropout > 0.0:
@@ -219,19 +215,17 @@ class PtbModel(fluid.Layer):
         rnn_out, last_hidden, last_cell = self.simple_lstm_rnn(
             x_emb, init_h, init_c
         )
-        rnn_out = fluid.layers.reshape(
+        rnn_out = paddle.reshape(
             rnn_out, shape=[-1, self.num_steps, self.hidden_size]
         )
 
         projection = fluid.layers.matmul(rnn_out, self.softmax_weight)
         projection = fluid.layers.elementwise_add(projection, self.softmax_bias)
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_imperative_save_load_v2.py

@@ -82,12 +82,10 @@ class SimpleLSTMRNN(fluid.Layer):
             pre_cell = fluid.layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = fluid.layers.reshape(
+            pre_hidden = paddle.reshape(
                 pre_hidden, shape=[-1, self._hidden_size]
             )
-            pre_cell = fluid.layers.reshape(
-                pre_cell, shape=[-1, self._hidden_size]
-            )
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, self._hidden_size])
             self.hidden_array.append(pre_hidden)
             self.cell_array.append(pre_cell)
 
@@ -96,7 +94,7 @@ class SimpleLSTMRNN(fluid.Layer):
             self._input = fluid.layers.slice(
                 input_embedding, axes=[1], starts=[index], ends=[index + 1]
             )
-            self._input = fluid.layers.reshape(
+            self._input = paddle.reshape(
                 self._input, shape=[-1, self._hidden_size]
             )
             for k in range(self._num_layers):
@@ -127,19 +125,17 @@ class SimpleLSTMRNN(fluid.Layer):
                         dropout_implementation='upscale_in_train',
                     )
             res.append(
-                fluid.layers.reshape(
-                    self._input, shape=[1, -1, self._hidden_size]
-                )
+                paddle.reshape(self._input, shape=[1, -1, self._hidden_size])
             )
         real_res = fluid.layers.concat(res, 0)
         real_res = fluid.layers.transpose(x=real_res, perm=[1, 0, 2])
         last_hidden = fluid.layers.concat(self.hidden_array, 1)
-        last_hidden = fluid.layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_hidden = fluid.layers.transpose(x=last_hidden, perm=[1, 0, 2])
         last_cell = fluid.layers.concat(self.cell_array, 1)
-        last_cell = fluid.layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_cell = fluid.layers.transpose(x=last_cell, perm=[1, 0, 2])
@@ -200,16 +196,16 @@ class PtbModel(fluid.Layer):
         )
 
     def forward(self, input, label, init_hidden, init_cell):
-        init_h = fluid.layers.reshape(
+        init_h = paddle.reshape(
             init_hidden, shape=[self.num_layers, -1, self.hidden_size]
         )
 
-        init_c = fluid.layers.reshape(
+        init_c = paddle.reshape(
             init_cell, shape=[self.num_layers, -1, self.hidden_size]
         )
 
         x_emb = self.embedding(input)
-        x_emb = fluid.layers.reshape(
+        x_emb = paddle.reshape(
             x_emb, shape=[-1, self.num_steps, self.hidden_size]
         )
         if self.dropout is not None and self.dropout > 0.0:
@@ -221,19 +217,17 @@ class PtbModel(fluid.Layer):
         rnn_out, last_hidden, last_cell = self.simple_lstm_rnn(
             x_emb, init_h, init_c
         )
-        rnn_out = fluid.layers.reshape(
+        rnn_out = paddle.reshape(
             rnn_out, shape=[-1, self.num_steps, self.hidden_size]
         )
 
         projection = fluid.layers.matmul(rnn_out, self.softmax_weight)
         projection = fluid.layers.elementwise_add(projection, self.softmax_bias)
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_imperative_se_resnext.py

@@ -123,7 +123,7 @@ class SqueezeExcitation(fluid.dygraph.Layer):
 
     def forward(self, input):
         y = self._pool(input)
-        y = fluid.layers.reshape(y, shape=[-1, self._num_channels])
+        y = paddle.reshape(y, shape=[-1, self._num_channels])
         y = self._squeeze(y)
         y = self._excitation(y)
         y = fluid.layers.elementwise_mul(x=input, y=y, axis=0)
@@ -318,7 +318,7 @@ class SeResNeXt(fluid.dygraph.Layer):
         for bottleneck_block in self.bottleneck_block_list:
             y = bottleneck_block(y)
         y = self.pool2d_avg(y)
-        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
+        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_output])
         y = self.out(y)
         return y
 

python/paddle/fluid/tests/unittests/test_imperative_selected_rows_to_lod_tensor.py

@@ -75,13 +75,11 @@ class SimpleNet(fluid.Layer):
         projection = fluid.layers.matmul(
             fc, fluid.layers.transpose(self.embedding.weight, perm=[1, 0])
         )
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_imperative_star_gan_with_gradient_penalty.py

@@ -309,9 +309,7 @@ class Generator(fluid.dygraph.Layer):
 
     def forward(self, input, label_trg):
         shape = input.shape
-        label_trg_e = fluid.layers.reshape(
-            label_trg, [-1, label_trg.shape[1], 1, 1]
-        )
+        label_trg_e = paddle.reshape(label_trg, [-1, label_trg.shape[1], 1, 1])
         label_trg_e = fluid.layers.expand(
             x=label_trg_e, expand_times=[1, 1, shape[2], shape[3]]
         )
@@ -380,9 +378,7 @@ class Discriminator(fluid.dygraph.Layer):
 
 def loss_cls(cls, label, cfg):
     cls_shape = cls.shape
-    cls = fluid.layers.reshape(
-        cls, [-1, cls_shape[1] * cls_shape[2] * cls_shape[3]]
-    )
+    cls = paddle.reshape(cls, [-1, cls_shape[1] * cls_shape[2] * cls_shape[3]])
     return (
         fluid.layers.reduce_sum(
             fluid.layers.sigmoid_cross_entropy_with_logits(cls, label)
@@ -432,7 +428,7 @@ def gradient_penalty(f, real, fake, no_grad_set, cfg):
     gradient = gradient[0]
     grad_shape = gradient.shape
 
-    gradient = fluid.layers.reshape(
+    gradient = paddle.reshape(
         gradient, [-1, grad_shape[1] * grad_shape[2] * grad_shape[3]]
     )
 

python/paddle/fluid/tests/unittests/test_imperative_transformer_sorted_gradient.py

@@ -476,16 +476,16 @@ class MultiHeadAttentionLayer(Layer):
         v = self._v_fc(values)
 
         # split head
-        reshaped_q = fluid.layers.reshape(
-            x=q, shape=[0, 0, self._n_head, self._d_key], inplace=False
+        reshaped_q = paddle.reshape(
+            x=q, shape=[0, 0, self._n_head, self._d_key]
         )
         transpose_q = fluid.layers.transpose(x=reshaped_q, perm=[0, 2, 1, 3])
-        reshaped_k = fluid.layers.reshape(
-            x=k, shape=[0, 0, self._n_head, self._d_key], inplace=False
+        reshaped_k = paddle.reshape(
+            x=k, shape=[0, 0, self._n_head, self._d_key]
         )
         transpose_k = fluid.layers.transpose(x=reshaped_k, perm=[0, 2, 1, 3])
-        reshaped_v = fluid.layers.reshape(
-            x=v, shape=[0, 0, self._n_head, self._d_value], inplace=False
+        reshaped_v = paddle.reshape(
+            x=v, shape=[0, 0, self._n_head, self._d_value]
         )
         transpose_v = fluid.layers.transpose(x=reshaped_v, perm=[0, 2, 1, 3])
 
@@ -514,10 +514,9 @@ class MultiHeadAttentionLayer(Layer):
         if len(out.shape) != 4:
             raise ValueError("Input(x) should be a 4-D Tensor.")
         trans_x = fluid.layers.transpose(out, perm=[0, 2, 1, 3])
-        final_out = fluid.layers.reshape(
+        final_out = paddle.reshape(
             x=trans_x,
             shape=[0, 0, trans_x.shape[2] * trans_x.shape[3]],
-            inplace=False,
         )
 
         # fc to output
@@ -994,8 +993,8 @@ class WrapDecoderLayer(Layer):
             dec_input, enc_output, trg_slf_attn_bias, trg_src_attn_bias
         )
 
-        dec_output_reshape = fluid.layers.reshape(
-            dec_output, shape=[-1, dec_output.shape[-1]], inplace=False
+        dec_output_reshape = paddle.reshape(
+            dec_output, shape=[-1, dec_output.shape[-1]]
         )
 
         if self._weight_sharing:

python/paddle/fluid/tests/unittests/test_ir_memory_optimize_pass.py

@@ -43,8 +43,8 @@ def fc_with_inplace_net(use_feed):
     x, y = _feed_data_helper()
     fc = fluid.layers.fc(input=x, size=20, act='relu')
     fc = fluid.layers.fc(input=fc, size=10, act='relu')
-    reshape = fluid.layers.reshape(x=fc, shape=[-1, 2, 5])
-    reshape = fluid.layers.reshape(x=reshape, shape=[-1, 5, 2])
+    reshape = paddle.reshape(x=fc, shape=[-1, 2, 5])
+    reshape = paddle.reshape(x=reshape, shape=[-1, 5, 2])
     y_predict = fluid.layers.fc(input=reshape, size=10, act='softmax')
     cost = fluid.layers.cross_entropy(input=y_predict, label=y)
     avg_cost = paddle.mean(cost)

python/paddle/fluid/tests/unittests/test_nn_grad.py

@@ -148,7 +148,7 @@ class TestExpandDoubleGradCheck(unittest.TestCase):
 
         x = layers.data('x', x_shape, False, dtype)
         x.persistable = True
-        out = layers.reshape(x, new_shape)
+        out = paddle.reshape(x, new_shape)
         x_arr = np.random.uniform(-1, 1, x_shape).astype(dtype)
 
         gradient_checker.double_grad_check(

python/paddle/fluid/tests/unittests/test_reshape_op.py

@@ -301,11 +301,6 @@ class TestReshapeAPI(unittest.TestCase):
     def _executed_api(self):
         self.reshape = paddle.reshape
 
-    def _set_fluid_api(self):
-        self.fill_constant = fluid.layers.fill_constant
-        self.data = paddle.static.data
-        self.reshape = fluid.layers.reshape
-
     def _test_api(self):
         paddle.enable_static()
         input = np.random.random([2, 25]).astype("float32")
@@ -317,18 +312,16 @@ class TestReshapeAPI(unittest.TestCase):
 
             actual_shape = self.data(name="shape", shape=[3], dtype="int32")
 
-            # situation 1: have shape( list, no tensor), no actual shape(Tensor)
+            # situation 1: have shape( list, no tensor)
             out_1 = self.reshape(x, shape)
 
-            # situation 2: have shape(list, no tensor), have actual shape(Tensor)
-            out_2 = fluid.layers.reshape(
-                x, shape=shape, actual_shape=actual_shape
-            )
+            # situation 2: have shape(list, no tensor)
+            out_2 = paddle.reshape(x, actual_shape)
 
-            # Situation 3: have shape(list, have tensor), no actual shape(Tensor)
+            # Situation 3: have shape(list, have tensor)
             out_3 = self.reshape(x, shape=[positive_five, 10])
 
-            # Situation 4: have shape(Tensor), no actual shape(Tensor)
+            # Situation 4: have shape(Tensor)
             out_4 = self.reshape(x, shape=actual_shape)
 
         exe = paddle.static.Executor(place=paddle.CPUPlace())
@@ -347,10 +340,6 @@ class TestReshapeAPI(unittest.TestCase):
         self._set_paddle_api()
         self._test_api()
 
-    def test_fluid_api(self):
-        self._set_fluid_api()
-        self._test_api()
-
     def test_imperative(self):
         self._set_paddle_api()
         input = np.random.random([2, 25]).astype("float32")
@@ -401,10 +390,6 @@ class TestReshapeOpError(unittest.TestCase):
         self.data = paddle.static.data
         self.reshape = paddle.reshape
 
-    def _set_fluid_api(self):
-        self.data = fluid.data
-        self.reshape = fluid.layers.reshape
-
     def _test_errors(self):
         with program_guard(Program(), Program()):
             # The x type of reshape_op must be Variable.
@@ -439,12 +424,6 @@ class TestReshapeOpError(unittest.TestCase):
 
             self.assertRaises(TypeError, test_shape_type)
 
-            # The argument actual_shape's type of reshape_op must be Variable or None.
-            def test_actual_shape_type():
-                self.reshape(x3, shape=[25, 2], actual_shape=1)
-
-            self.assertRaises(TypeError, test_actual_shape_type)
-
             # The argument shape have more than one -1.
             def test_shape_1():
                 self.reshape(x3, shape=[-1, -1, 5])
@@ -467,10 +446,6 @@ class TestReshapeOpError(unittest.TestCase):
         self._set_paddle_api()
         self._test_errors()
 
-    def test_fluid_api_error(self):
-        self._set_fluid_api()
-        self._test_errors()
-
 
 class TestDygraphReshapeAPI(unittest.TestCase):
     def setUp(self):

python/paddle/fluid/tests/unittests/test_static_save_load.py

@@ -92,12 +92,10 @@ class SimpleLSTMRNN(fluid.Layer):
             pre_cell = fluid.layers.slice(
                 init_cell, axes=[0], starts=[i], ends=[i + 1]
             )
-            pre_hidden = fluid.layers.reshape(
+            pre_hidden = paddle.reshape(
                 pre_hidden, shape=[-1, self._hidden_size]
             )
-            pre_cell = fluid.layers.reshape(
-                pre_cell, shape=[-1, self._hidden_size]
-            )
+            pre_cell = paddle.reshape(pre_cell, shape=[-1, self._hidden_size])
             self.hidden_array.append(pre_hidden)
             self.cell_array.append(pre_cell)
 
@@ -106,7 +104,7 @@ class SimpleLSTMRNN(fluid.Layer):
             self._input = fluid.layers.slice(
                 input_embedding, axes=[1], starts=[index], ends=[index + 1]
             )
-            self._input = fluid.layers.reshape(
+            self._input = paddle.reshape(
                 self._input, shape=[-1, self._hidden_size]
             )
             for k in range(self._num_layers):
@@ -137,19 +135,17 @@ class SimpleLSTMRNN(fluid.Layer):
                         dropout_implementation='upscale_in_train',
                     )
             res.append(
-                fluid.layers.reshape(
-                    self._input, shape=[1, -1, self._hidden_size]
-                )
+                paddle.reshape(self._input, shape=[1, -1, self._hidden_size])
             )
         real_res = fluid.layers.concat(res, 0)
         real_res = fluid.layers.transpose(x=real_res, perm=[1, 0, 2])
         last_hidden = fluid.layers.concat(self.hidden_array, 1)
-        last_hidden = fluid.layers.reshape(
+        last_hidden = paddle.reshape(
             last_hidden, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_hidden = fluid.layers.transpose(x=last_hidden, perm=[1, 0, 2])
         last_cell = fluid.layers.concat(self.cell_array, 1)
-        last_cell = fluid.layers.reshape(
+        last_cell = paddle.reshape(
             last_cell, shape=[-1, self._num_layers, self._hidden_size]
         )
         last_cell = fluid.layers.transpose(x=last_cell, perm=[1, 0, 2])
@@ -210,18 +206,18 @@ class PtbModel(fluid.Layer):
         )
 
     def forward(self, input, label, init_hidden, init_cell):
-        init_h = fluid.layers.reshape(
+        init_h = paddle.reshape(
             init_hidden, shape=[self.num_layers, -1, self.hidden_size]
         )
 
-        init_c = fluid.layers.reshape(
+        init_c = paddle.reshape(
             init_cell, shape=[self.num_layers, -1, self.hidden_size]
         )
 
         # NPU 'tok_k' kernel only support `int32` dtype, so cast `input` from `int64` to `int32`.
         input = fluid.layers.cast(input, "int32")
         x_emb = self.embedding(input)
-        x_emb = fluid.layers.reshape(
+        x_emb = paddle.reshape(
             x_emb, shape=[-1, self.num_steps, self.hidden_size]
         )
         if self.dropout is not None and self.dropout > 0.0:
@@ -234,18 +230,16 @@ class PtbModel(fluid.Layer):
             x_emb, init_h, init_c
         )
 
-        rnn_out = fluid.layers.reshape(
+        rnn_out = paddle.reshape(
             rnn_out, shape=[-1, self.num_steps, self.hidden_size]
         )
         projection = fluid.layers.matmul(rnn_out, self.softmax_weight)
         projection = fluid.layers.elementwise_add(projection, self.softmax_bias)
-        projection = fluid.layers.reshape(
-            projection, shape=[-1, self.vocab_size]
-        )
+        projection = paddle.reshape(projection, shape=[-1, self.vocab_size])
         loss = fluid.layers.softmax_with_cross_entropy(
             logits=projection, label=label, soft_label=False
         )
-        loss = fluid.layers.reshape(loss, shape=[-1, self.num_steps])
+        loss = paddle.reshape(loss, shape=[-1, self.num_steps])
         loss = fluid.layers.reduce_mean(loss, dim=[0])
         loss = fluid.layers.reduce_sum(loss)
 

python/paddle/fluid/tests/unittests/test_var_base.py

@@ -727,7 +727,7 @@ class TestVarBase(unittest.TestCase):
         var3 = var[0:1]
         var4 = var[::-1]
         var5 = var[1, 1:, 1:]
-        var_reshape = fluid.layers.reshape(var, [3, -1, 3])
+        var_reshape = paddle.reshape(var, [3, -1, 3])
         var6 = var_reshape[:, :, -1]
         var7 = var[:, :, :-1]
         var8 = var[:1, :1, :1]
@@ -820,7 +820,7 @@ class TestVarBase(unittest.TestCase):
         var3 = var[0:one]
         var4 = var[::negative_one]
         var5 = var[one, one:, one:]
-        var_reshape = fluid.layers.reshape(var, [3, negative_one, 3])
+        var_reshape = paddle.reshape(var, [3, negative_one, 3])
         var6 = var_reshape[:, :, negative_one]
         var7 = var[:, :, :negative_one]
         var8 = var[:one, :one, :1]

python/paddle/fluid/tests/unittests/test_variable.py

@@ -156,7 +156,7 @@ class TestVariable(unittest.TestCase):
             var3 = var[0:1]
             var4 = var[::-1]
             var5 = var[1, 1:, 1:]
-            var_reshape = fluid.layers.reshape(var, [3, -1, 3])
+            var_reshape = paddle.reshape(var, [3, -1, 3])
             var6 = var_reshape[:, :, -1]
             var7 = var[:, :, :-1]
             var8 = var[:1, :1, :1]

python/paddle/fluid/tests/unittests/test_while_loop_op.py

@@ -92,7 +92,7 @@ class TestApiWhileLoop(unittest.TestCase):
             test_dict["test_key"] = i
             test_dict["test_key"] += 1
 
-            test_list[0] = fluid.layers.reshape(test_list[0], [2, -1]) + 1
+            test_list[0] = paddle.reshape(test_list[0], [2, -1]) + 1
 
             test_list_dict[0]["test_key"] += 1
             test_list_dict[0]["test_key"] = fluid.layers.relu(

python/paddle/fluid/tests/unittests/transformer_model.py

@@ -115,7 +115,7 @@ def multi_head_attention(
 
         hidden_size = x.shape[-1]
         # FIXME(guosheng): Decouple the program desc with batch_size.
-        reshaped = layers.reshape(
+        reshaped = paddle.reshape(
             x=x, shape=[batch_size, -1, n_head, hidden_size // n_head]
         )
 
@@ -135,7 +135,7 @@ def multi_head_attention(
 
         trans_x = layers.transpose(x, perm=[0, 2, 1, 3])
         # FIXME(guosheng): Decouple the program desc with batch_size.
-        return layers.reshape(
+        return paddle.reshape(
             x=trans_x,
             shape=list(
                 map(int, [batch_size, -1, trans_x.shape[2] * trans_x.shape[3]])
@@ -281,7 +281,7 @@ def prepare_encoder(
     enc_input = src_word_emb + src_pos_enc
 
     # FIXME(guosheng): Decouple the program desc with batch_size.
-    enc_input = layers.reshape(x=enc_input, shape=[batch_size, -1, src_emb_dim])
+    enc_input = paddle.reshape(x=enc_input, shape=[batch_size, -1, src_emb_dim])
     return (
         layers.dropout(enc_input, dropout_prob=dropout, is_test=False)
         if dropout
@@ -581,7 +581,7 @@ def transformer(
 
     # TODO(guosheng): Share the weight matrix between the embedding layers and
     # the pre-softmax linear transformation.
-    predict = layers.reshape(
+    predict = paddle.reshape(
         x=layers.fc(
             input=dec_output,
             size=trg_vocab_size,
@@ -590,8 +590,8 @@ def transformer(
             num_flatten_dims=2,
         ),
         shape=[-1, trg_vocab_size],
-        act="softmax",
     )
+    predict = paddle.nn.functional.softmax(predict)
 
     cost = layers.cross_entropy(input=predict, label=gold)
     weighted_cost = cost * weights