From 9b611ea289482fb8616b99a641486e42e41bd9d0 Mon Sep 17 00:00:00 2001
From: Hao Lin <1184264181@qq.com>
Date: Thu, 8 Jul 2021 15:42:32 +0800
Subject: [PATCH] opt dygraph python code for 215 unchecked calls (#34024)

* opt dygraph python API, test=develop

* Fix unbind bug in manipulation.py
---
 python/paddle/distribution.py             |  4 +-
 python/paddle/fluid/contrib/layers/nn.py  | 13 +++---
 python/paddle/fluid/contrib/optimizer.py  |  8 ++--
 python/paddle/fluid/layers/detection.py   |  4 +-
 python/paddle/fluid/optimizer.py          |  8 ++--
 python/paddle/fluid/regularizer.py        |  3 --
 python/paddle/nn/functional/activation.py |  2 +-
 python/paddle/nn/functional/common.py     | 32 +++++++-------
 python/paddle/nn/functional/conv.py       | 13 ------
 python/paddle/nn/functional/pooling.py    | 52 ++++++++++++-----------
 python/paddle/nn/functional/vision.py     | 36 +++++++---------
 python/paddle/optimizer/optimizer.py      |  8 ++--
 python/paddle/tensor/linalg.py            |  4 +-
 python/paddle/tensor/manipulation.py      | 36 ++++++++--------
 python/paddle/tensor/search.py            |  4 +-
 15 files changed, 105 insertions(+), 122 deletions(-)

diff --git a/python/paddle/distribution.py b/python/paddle/distribution.py
index d866f74b0e8..1ed4fdc55a3 100644
--- a/python/paddle/distribution.py
+++ b/python/paddle/distribution.py
@@ -322,7 +322,6 @@ class Uniform(Distribution):
           Tensor: log probability.The data type is same with value.
 
         """
-        name = self.name + '_log_prob'
         value = self._check_values_dtype_in_probs(self.low, value)
         if in_dygraph_mode():
             # ensure value in [low, high]
@@ -335,6 +334,7 @@ class Uniform(Distribution):
                                value.dtype)
             return nn.log(lb * ub) - nn.log(self.high - self.low)
 
+        name = self.name + '_log_prob'
         lb_bool = self.low < value
         ub_bool = value < self.high
         lb = tensor.cast(lb_bool, dtype=value.dtype)
@@ -352,7 +352,6 @@ class Uniform(Distribution):
           Tensor: probability.The data type is same with value.
 
         """
-        name = self.name + '_probs'
         value = self._check_values_dtype_in_probs(self.low, value)
         if in_dygraph_mode():
             lb_bool = self.low < value
@@ -364,6 +363,7 @@ class Uniform(Distribution):
                                value.dtype)
             return (lb * ub) / (self.high - self.low)
 
+        name = self.name + '_probs'
         lb_bool = self.low < value
         ub_bool = value < self.high
         lb = tensor.cast(lb_bool, dtype=value.dtype)
diff --git a/python/paddle/fluid/contrib/layers/nn.py b/python/paddle/fluid/contrib/layers/nn.py
index 30316b77adc..21da74cc12d 100644
--- a/python/paddle/fluid/contrib/layers/nn.py
+++ b/python/paddle/fluid/contrib/layers/nn.py
@@ -1538,19 +1538,18 @@ def bilateral_slice(x, guide, grid, has_offset, name=None):
             output = fluid.contrib.bilateral_slice(x, guide, grid, has_offset=True)
 
     """
-    helper = LayerHelper("bilateral_slice", **locals())
+    if paddle.fluid.in_dygraph_mode():
+        attrs = ('has_offset', has_offset)
+        return getattr(core.ops, "bilateral_slice")(x, grid, guide, *attrs)
 
     check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'bilateral_slice')
     check_variable_and_dtype(guide, 'guide', ['float32', 'float64'],
                              'bilateral_slice')
     check_variable_and_dtype(grid, 'grid', ['float32', 'float64'],
                              'bilateral_slice')
-
+    helper = LayerHelper("bilateral_slice", **locals())
     out = helper.create_variable_for_type_inference(x.dtype)
     inputs = {'X': x, 'Guide': guide, 'Grid': grid}
-    if paddle.fluid.in_dygraph_mode():
-        attrs = ('has_offset', has_offset)
-        return getattr(core.ops, "bilateral_slice")(x, grid, guide, *attrs)
     helper.append_op(
         type='bilateral_slice',
         inputs=inputs,
@@ -1613,14 +1612,14 @@ def correlation(x,
 
     """
 
-    helper = LayerHelper("correlation", **locals())
-    output = helper.create_variable_for_type_inference(dtype=x.dtype)
     if paddle.fluid.in_dygraph_mode():
         attrs = ("pad_size", pad_size, "kernel_size", kernel_size,
                  "max_displacement", max_displacement, "stride1", stride1,
                  "stride2", stride2, "corr_type_multiply", corr_type_multiply)
         output = getattr(core.ops, "correlation")(x, y, *attrs)
     else:
+        helper = LayerHelper("correlation", **locals())
+        output = helper.create_variable_for_type_inference(dtype=x.dtype)
         helper.append_op(
             type="correlation",
             inputs={"Input1": x,
diff --git a/python/paddle/fluid/contrib/optimizer.py b/python/paddle/fluid/contrib/optimizer.py
index 2a22969d527..bff2a9818a9 100644
--- a/python/paddle/fluid/contrib/optimizer.py
+++ b/python/paddle/fluid/contrib/optimizer.py
@@ -200,10 +200,6 @@ class Momentum(Optimizer):
 
         velocity_acc = self._get_accumulator(self._velocity_acc_str,
                                              param_and_grad[0])
-        find_master = self._multi_precision and param_and_grad[
-            0].dtype == core.VarDesc.VarType.FP16
-        master_weight = (self._master_weights[param_and_grad[0].name]
-                         if find_master else None)
         lr = self._create_param_lr(param_and_grad)
 
         if framework.in_dygraph_mode():
@@ -215,6 +211,10 @@ class Momentum(Optimizer):
                 self._regularization_coeff)
             return None
 
+        find_master = self._multi_precision and param_and_grad[
+            0].dtype == core.VarDesc.VarType.FP16
+        master_weight = (self._master_weights[param_and_grad[0].name]
+                         if find_master else None)
         attrs = {
             "mu": self._momentum,
             "use_nesterov": self._use_nesterov,
diff --git a/python/paddle/fluid/layers/detection.py b/python/paddle/fluid/layers/detection.py
index 604bcc0e277..4fa955c9ae0 100644
--- a/python/paddle/fluid/layers/detection.py
+++ b/python/paddle/fluid/layers/detection.py
@@ -3945,8 +3945,6 @@ def collect_fpn_proposals(multi_rois,
                 max_level=5, 
                 post_nms_top_n=2000)
     """
-    check_type(multi_rois, 'multi_rois', list, 'collect_fpn_proposals')
-    check_type(multi_scores, 'multi_scores', list, 'collect_fpn_proposals')
     num_lvl = max_level - min_level + 1
     input_rois = multi_rois[:num_lvl]
     input_scores = multi_scores[:num_lvl]
@@ -3957,6 +3955,8 @@ def collect_fpn_proposals(multi_rois,
         output_rois, rois_num = core.ops.collect_fpn_proposals(
             input_rois, input_scores, rois_num_per_level, *attrs)
 
+    check_type(multi_rois, 'multi_rois', list, 'collect_fpn_proposals')
+    check_type(multi_scores, 'multi_scores', list, 'collect_fpn_proposals')
     helper = LayerHelper('collect_fpn_proposals', **locals())
     dtype = helper.input_dtype('multi_rois')
     check_dtype(dtype, 'multi_rois', ['float32', 'float64'],
diff --git a/python/paddle/fluid/optimizer.py b/python/paddle/fluid/optimizer.py
index eb2852db188..537e320a461 100755
--- a/python/paddle/fluid/optimizer.py
+++ b/python/paddle/fluid/optimizer.py
@@ -914,6 +914,9 @@ class Optimizer(object):
 
         assert regularization_term is not None
 
+        if framework.in_dygraph_mode():
+            return core.ops.sum([grad, regularization_term])
+
         new_grad = grad
         if grad.type == core.VarDesc.VarType.SELECTED_ROWS:
             # FIXME(zcd): If the grad is SELECTED_ROWS, after regularization,
@@ -929,10 +932,7 @@ class Optimizer(object):
 
         inputs = {"X": [grad, regularization_term]}
         outputs = {"Out": [new_grad]}
-        if framework.in_dygraph_mode():
-            new_grad = core.ops.sum([grad, regularization_term])
-        else:
-            grad.block.append_op(type='sum', inputs=inputs, outputs=outputs)
+        grad.block.append_op(type='sum', inputs=inputs, outputs=outputs)
 
         return new_grad
 
diff --git a/python/paddle/fluid/regularizer.py b/python/paddle/fluid/regularizer.py
index 64bbca6c57c..91aecc84ae7 100644
--- a/python/paddle/fluid/regularizer.py
+++ b/python/paddle/fluid/regularizer.py
@@ -132,9 +132,6 @@ class L2DecayRegularizer(WeightDecayRegularizer):
         assert isinstance(param, framework.Variable)
         assert isinstance(block, framework.Block)
 
-        inputs = {"X": [param]}
-        attrs = {"scale": self._regularization_coeff}
-
         if framework.in_dygraph_mode():
             return core.ops.scale(param, "scale", self._regularization_coeff)
         else:
diff --git a/python/paddle/nn/functional/activation.py b/python/paddle/nn/functional/activation.py
index d5dc6322522..7bb3b01b698 100644
--- a/python/paddle/nn/functional/activation.py
+++ b/python/paddle/nn/functional/activation.py
@@ -432,7 +432,6 @@ def prelu(x, weight, name=None):
     check_variable_and_dtype(weight, 'weight',
                              ['float16', 'float32', 'float64'], 'prelu')
 
-    helper = LayerHelper('prelu', **locals())
     assert len(weight.shape
                ) == 1, "The dim count of weight shape should be 1 in prelu()."
 
@@ -450,6 +449,7 @@ def prelu(x, weight, name=None):
     if in_dygraph_mode():
         return core.ops.prelu(x, weight, 'mode', mode)
 
+    helper = LayerHelper('prelu', **locals())
     out = helper.create_variable_for_type_inference(x.dtype)
     helper.append_op(
         type="prelu",
diff --git a/python/paddle/nn/functional/common.py b/python/paddle/nn/functional/common.py
index 57ce6c78e95..3ce832f3bd5 100644
--- a/python/paddle/nn/functional/common.py
+++ b/python/paddle/nn/functional/common.py
@@ -453,13 +453,13 @@ def interpolate(x,
 
         if resample_type == "linear":
             out = core.ops.linear_interp_v2(x, *dy_attr)
-        if resample_type == "bilinear":
+        elif resample_type == "bilinear":
             out = core.ops.bilinear_interp_v2(x, *dy_attr)
-        if resample_type == "trilinear":
+        elif resample_type == "trilinear":
             out = core.ops.trilinear_interp_v2(x, *dy_attr)
-        if resample_type == "nearest":
+        elif resample_type == "nearest":
             out = core.ops.nearest_interp_v2(x, *dy_attr)
-        if resample_type == "bicubic":
+        elif resample_type == "bicubic":
             out = core.ops.bicubic_interp_v2(x, *dy_attr)
         return out
     out = helper.create_variable_for_type_inference(dtype)
@@ -881,18 +881,6 @@ def dropout(x,
         seed = None
         mode = 'downgrade_in_infer' if mode == 'downscale_in_infer' else mode  #semantic transfer
 
-        def get_attrs(prog, dropout_prob, is_test, seed):
-            if (seed is None or seed == 0) and prog.random_seed != 0:
-                seed = prog.random_seed
-            attrs = {
-                'dropout_prob': dropout_prob,
-                'is_test': is_test,
-                'fix_seed': seed is not None,
-                'seed': seed if seed is not None else 0,
-                'dropout_implementation': mode,
-            }
-            return attrs
-
         if in_dygraph_mode():
             if default_main_program().random_seed != 0:
                 seed = default_main_program().random_seed
@@ -910,6 +898,18 @@ def dropout(x,
         mask = helper.create_variable_for_type_inference(
             dtype=core.VarDesc.VarType.UINT8, stop_gradient=True)
 
+        def get_attrs(prog, dropout_prob, is_test, seed):
+            if (seed is None or seed == 0) and prog.random_seed != 0:
+                seed = prog.random_seed
+            attrs = {
+                'dropout_prob': dropout_prob,
+                'is_test': is_test,
+                'fix_seed': seed is not None,
+                'seed': seed if seed is not None else 0,
+                'dropout_implementation': mode,
+            }
+            return attrs
+
         attrs = get_attrs(helper.main_program, p, not training, seed)
 
         helper.append_op(
diff --git a/python/paddle/nn/functional/conv.py b/python/paddle/nn/functional/conv.py
index 66913f3ad2f..c3a9e28878a 100644
--- a/python/paddle/nn/functional/conv.py
+++ b/python/paddle/nn/functional/conv.py
@@ -109,7 +109,6 @@ def _conv_nd(x,
              name=None):
 
     # Due to the poor performance of NHWC, we transpose the input to NCHW.
-    origin_format = data_format
     if in_dygraph_mode():
         attrs = ('strides', stride, 'paddings', padding, 'dilations', dilation,
                  'groups', groups, 'use_cudnn', use_cudnn, 'use_mkldnn',
@@ -332,18 +331,6 @@ def conv1d(x,
         l_type = 'depthwise_conv2d'
         use_cudnn = False
 
-    inputs = {'Input': [x], 'Filter': [weight]}
-    attrs = {
-        'strides': stride,
-        'paddings': padding,
-        'dilations': dilation,
-        'groups': groups,
-        'use_cudnn': use_cudnn,
-        'use_mkldnn': False,
-        'fuse_relu_before_depthwise_conv': False,
-        "padding_algorithm": padding_algorithm,
-        "data_format": conv2d_data_format
-    }
     squeeze_aixs = -2 if channel_last else -1
     x = nn.unsqueeze(input=x, axes=[squeeze_aixs])
     weight = nn.unsqueeze(input=weight, axes=[-1])
diff --git a/python/paddle/nn/functional/pooling.py b/python/paddle/nn/functional/pooling.py
index 1869ac15b17..3c255dff653 100755
--- a/python/paddle/nn/functional/pooling.py
+++ b/python/paddle/nn/functional/pooling.py
@@ -196,7 +196,8 @@ def avg_pool1d(x,
     """
     """NCL to NCHW"""
     data_format = "NCHW"
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'avg_pool1d')
+    if not in_dygraph_mode():
+        check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'avg_pool1d')
     _check_input(x, 3)
     x = unsqueeze(x, [2])
     kernel_size = utils.convert_to_list(kernel_size, 1, 'kernel_size')
@@ -315,7 +316,6 @@ def avg_pool2d(x,
                             stride=2, padding=0)
             # out.shape [1, 3, 16, 16]
     """
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'avg_pool2d')
     kernel_size = utils.convert_to_list(kernel_size, 2, 'pool_size')
     if stride is None:
         stride = kernel_size
@@ -341,6 +341,7 @@ def avg_pool2d(x,
 
     op_type = 'pool2d'
     helper = LayerHelper(op_type, **locals())
+    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'avg_pool2d')
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
 
@@ -434,7 +435,6 @@ def avg_pool3d(x,
                                             padding=0)
           # out.shape: [1, 3, 16, 16, 16]
     """
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool3d')
     kernel_size = utils.convert_to_list(kernel_size, 3, 'pool_size')
     if stride is None:
         stride = kernel_size
@@ -461,6 +461,7 @@ def avg_pool3d(x,
 
     op_type = "pool3d"
     helper = LayerHelper(op_type, **locals())
+    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool3d')
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
     outputs = {"Out": pool_out}
@@ -547,7 +548,8 @@ def max_pool1d(x,
     """
     """NCL to NCHW"""
     data_format = "NCHW"
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool1d')
+    if not in_dygraph_mode():
+        check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool1d')
     _check_input(x, 3)
     x = unsqueeze(x, [2])
     kernel_size = [1] + utils.convert_to_list(kernel_size, 1, 'pool_size')
@@ -679,8 +681,6 @@ def max_pool2d(x,
                                                return_mask=True)
             # out.shape [1, 3, 16, 16], max_indices.shape [1, 3, 16, 16],
     """
-    check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'],
-                             'max_pool2d')
     kernel_size = utils.convert_to_list(kernel_size, 2, 'pool_size')
     if stride is None:
         stride = kernel_size
@@ -722,6 +722,8 @@ def max_pool2d(x,
 
     op_type = 'max_pool2d_with_index' if return_mask else "pool2d"
     helper = LayerHelper(op_type, **locals())
+    check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'],
+                             'max_pool2d')
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
     mask = helper.create_variable_for_type_inference(dtype)
@@ -815,7 +817,6 @@ def max_pool3d(x,
                                           return_mask=True)
             # output.shape [None, 3, 16, 16, 16], max_indices.shape [None, 3, 16, 16, 16],
     """
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool3d')
     kernel_size = utils.convert_to_list(kernel_size, 3, 'pool_size')
     if stride is None:
         stride = kernel_size
@@ -852,6 +853,7 @@ def max_pool3d(x,
 
     op_type = "max_pool3d_with_index" if return_mask else "pool3d"
     helper = LayerHelper(op_type, **locals())
+    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'max_pool3d')
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
     mask = helper.create_variable_for_type_inference(dtype)
@@ -921,20 +923,21 @@ def adaptive_avg_pool1d(x, output_size, name=None):
               # pool_out shape: [1, 3, 16])
     """
     pool_type = 'avg'
-    check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'],
-                             'adaptive_pool2d')
+    if not in_dygraph_mode():
+        check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'],
+                                 'adaptive_pool2d')
+        check_type(output_size, 'pool_size', (int), 'adaptive_pool1d')
     _check_input(x, 3)
-    check_type(output_size, 'pool_size', (int), 'adaptive_pool1d')
-
     pool_size = [1] + utils.convert_to_list(output_size, 1, 'pool_size')
 
-    l_type = "pool2d"
     x = unsqueeze(x, [2])
     if in_dygraph_mode():
         pool_out = core.ops.pool2d(x, 'pooling_type', pool_type, 'ksize',
                                    pool_size, 'adaptive', True)
         return squeeze(pool_out, [2])
 
+    l_type = "pool2d"
+
     helper = LayerHelper(l_type, **locals())
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
@@ -1006,7 +1009,7 @@ def adaptive_avg_pool2d(x, output_size, data_format='NCHW', name=None):
     if not in_dygraph_mode():
         check_variable_and_dtype(x, 'x', ['float16', 'float32', 'float64'],
                                  'adaptive_avg_pool2d')
-    check_type(data_format, 'data_format', str, 'adaptive_avg_pool2d')
+        check_type(data_format, 'data_format', str, 'adaptive_avg_pool2d')
 
     if data_format not in ["NCHW", "NHWC"]:
         raise ValueError(
@@ -1110,7 +1113,7 @@ def adaptive_avg_pool3d(x, output_size, data_format='NCDHW', name=None):
     if not in_dygraph_mode():
         check_variable_and_dtype(x, 'x', ['float32', 'float64'],
                                  'adaptive_avg_pool3d')
-    check_type(data_format, 'data_format', str, 'adaptive_avg_pool3d')
+        check_type(data_format, 'data_format', str, 'adaptive_avg_pool3d')
 
     if data_format not in ["NCDHW", "NDHWC"]:
         raise ValueError(
@@ -1207,16 +1210,15 @@ def adaptive_max_pool1d(x, output_size, return_mask=False, name=None):
               # pool_out shape: [1, 3, 16] indices  shape: [1, 3, 16]
     """
     pool_type = 'max'
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'],
-                             'adaptive_max_pool1d')
+    if not in_dygraph_mode():
+        check_variable_and_dtype(x, 'x', ['float32', 'float64'],
+                                 'adaptive_max_pool1d')
+        check_type(output_size, 'pool_size', int, 'adaptive_max_pool1d')
+        check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool1d')
     _check_input(x, 3)
-    check_type(output_size, 'pool_size', int, 'adaptive_max_pool1d')
-    check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool1d')
 
     pool_size = [1] + utils.convert_to_list(output_size, 1, 'pool_size')
 
-    l_type = 'max_pool2d_with_index'
-
     x = unsqueeze(x, [2])
     if in_dygraph_mode():
         pool_out = core.ops.max_pool2d_with_index(
@@ -1224,6 +1226,8 @@ def adaptive_max_pool1d(x, output_size, return_mask=False, name=None):
         return (squeeze(pool_out[0], [2]), squeeze(
             pool_out[1], [2])) if return_mask else squeeze(pool_out[0], [2])
 
+    l_type = 'max_pool2d_with_index'
+
     helper = LayerHelper(l_type, **locals())
     dtype = helper.input_dtype(input_param_name='x')
     pool_out = helper.create_variable_for_type_inference(dtype)
@@ -1291,9 +1295,9 @@ def adaptive_max_pool2d(x, output_size, return_mask=False, name=None):
     if not in_dygraph_mode():
         check_variable_and_dtype(x, 'x', ['float32', 'float64'],
                                  'adaptive_max_pool2d')
+        check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool2d')
+        #check_type(output_size, 'pool_size', (int), 'adaptive_max_pool2d')
     _check_input(x, 4)
-    #check_type(output_size, 'pool_size', (int), 'adaptive_max_pool2d')
-    check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool2d')
 
     in_h, in_w = x.shape[2:4]
     if isinstance(output_size, int):
@@ -1382,9 +1386,9 @@ def adaptive_max_pool3d(x, output_size, return_mask=False, name=None):
     if not in_dygraph_mode():
         check_variable_and_dtype(x, 'x', ['float32', 'float64'],
                                  'adaptive_max_pool3d')
+        check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool3d')
+        #check_type(output_size, 'pool_size', (int), 'adaptive_max_pool3d')
     _check_input(x, 5)
-    #check_type(output_size, 'pool_size', (int), 'adaptive_max_pool3d')
-    check_type(return_mask, 'return_mask', bool, 'adaptive_max_pool3d')
 
     in_l, in_h, in_w = x.shape[2:5]
     if isinstance(output_size, int):
diff --git a/python/paddle/nn/functional/vision.py b/python/paddle/nn/functional/vision.py
index a2218a6e1aa..765919a8466 100644
--- a/python/paddle/nn/functional/vision.py
+++ b/python/paddle/nn/functional/vision.py
@@ -73,12 +73,9 @@ def affine_grid(theta, out_shape, align_corners=True, name=None):
             #   [-0.16666666  1.9000001 ]
             #   [-0.43333334  2.2333333 ]]]]
     """
-    helper = LayerHelper('affine_grid')
-
     if not isinstance(theta, Variable):
         raise ValueError("The theta should be a Tensor.")
-    check_variable_and_dtype(theta, 'theta', ['float32', 'float64'],
-                             'affine_grid')
+
     cudnn_version = get_cudnn_version()
     if cudnn_version is not None and cudnn_version >= 6000 and align_corners:
         use_cudnn = True
@@ -98,6 +95,9 @@ def affine_grid(theta, out_shape, align_corners=True, name=None):
                                     "align_corners", align_corners, "use_cudnn",
                                     use_cudnn)
 
+    helper = LayerHelper('affine_grid')
+    check_variable_and_dtype(theta, 'theta', ['float32', 'float64'],
+                             'affine_grid')
     out = helper.create_variable_for_type_inference(theta.dtype)
     ipts = {'Theta': theta}
     attrs = {"align_corners": align_corners, "use_cudnn": use_cudnn}
@@ -243,10 +243,6 @@ def grid_sample(x,
             #    [ 0.55  -0.076  0.35   0.59 ]
             #    [ 0.596  0.38   0.52   0.24 ]]]]
     """
-    helper = LayerHelper("grid_sample", **locals())
-    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'grid_sample')
-    check_variable_and_dtype(grid, 'grid', ['float32', 'float64'],
-                             'grid_sample')
 
     _modes = ['bilinear', 'nearest']
     _padding_modes = ['zeros', 'reflection', 'border']
@@ -272,19 +268,23 @@ def grid_sample(x,
         # CUDNN always computes gradients for all inputs
         x.stop_gradient = False
         grid.stop_gradient = False
-    ipts = {'X': x, 'Grid': grid}
-    attrs = {
-        'mode': mode,
-        'padding_mode': padding_mode,
-        'align_corners': align_corners,
-        'use_cudnn': use_cudnn
-    }
 
     if in_dygraph_mode():
         attrs = ('mode', mode, 'padding_mode', padding_mode, 'align_corners',
                  align_corners, 'use_cudnn', use_cudnn)
         out = getattr(core.ops, 'grid_sampler')(x, grid, *attrs)
     else:
+        helper = LayerHelper("grid_sample", **locals())
+        check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'grid_sample')
+        check_variable_and_dtype(grid, 'grid', ['float32', 'float64'],
+                                 'grid_sample')
+        ipts = {'X': x, 'Grid': grid}
+        attrs = {
+            'mode': mode,
+            'padding_mode': padding_mode,
+            'align_corners': align_corners,
+            'use_cudnn': use_cudnn
+        }
         out = helper.create_variable_for_type_inference(x.dtype)
         helper.append_op(
             type='grid_sampler',
@@ -319,10 +319,6 @@ def pixel_shuffle(x, upscale_factor, data_format="NCHW", name=None):
             out = out_var.numpy()
             # (2, 1, 12, 12)
     """
-    if not in_dygraph_mode():
-        check_variable_and_dtype(x, 'x', ['float32', 'float64'],
-                                 'pixel_shuffle')
-
     if not isinstance(upscale_factor, int):
         raise TypeError("upscale factor must be int type")
 
@@ -336,7 +332,7 @@ def pixel_shuffle(x, upscale_factor, data_format="NCHW", name=None):
                                       "data_format", data_format)
 
     helper = LayerHelper("pixel_shuffle", **locals())
-
+    check_variable_and_dtype(x, 'x', ['float32', 'float64'], 'pixel_shuffle')
     out = helper.create_variable_for_type_inference(dtype=x.dtype)
     helper.append_op(
         type="pixel_shuffle",
diff --git a/python/paddle/optimizer/optimizer.py b/python/paddle/optimizer/optimizer.py
index 93b618b7c9e..10213abd6b0 100644
--- a/python/paddle/optimizer/optimizer.py
+++ b/python/paddle/optimizer/optimizer.py
@@ -910,6 +910,9 @@ class Optimizer(object):
 
         assert regularization_term is not None
 
+        if framework.in_dygraph_mode():
+            return core.ops.sum([grad, regularization_term])
+
         new_grad = grad
         if grad.type == core.VarDesc.VarType.SELECTED_ROWS:
             # FIXME(zcd): If the grad is SELECTED_ROWS, after regularization,
@@ -925,10 +928,7 @@ class Optimizer(object):
 
         inputs = {"X": [grad, regularization_term]}
         outputs = {"Out": [new_grad]}
-        if framework.in_dygraph_mode():
-            new_grad = core.ops.sum([grad, regularization_term])
-        else:
-            grad.block.append_op(type='sum', inputs=inputs, outputs=outputs)
+        grad.block.append_op(type='sum', inputs=inputs, outputs=outputs)
 
         return new_grad
 
diff --git a/python/paddle/tensor/linalg.py b/python/paddle/tensor/linalg.py
index 8aa9c9bd2bd..91acb30b8d1 100644
--- a/python/paddle/tensor/linalg.py
+++ b/python/paddle/tensor/linalg.py
@@ -832,9 +832,11 @@ def bmm(x, y, name=None):
         raise ValueError(
             "x's batch (shape[0]) must be equal with y's batch (shape[0]). But received x's shape: {}, y's shape: {}".
             format(x_shape, y_shape))
-    helper = LayerHelper('bmm', **locals())
+
     if in_dygraph_mode():
         return core.ops.bmm(x, y)
+
+    helper = LayerHelper('bmm', **locals())
     out = helper.create_variable_for_type_inference(dtype=x.dtype)
     helper.append_op(type='bmm', inputs={'X': x, 'Y': y}, outputs={'Out': out})
     return out
diff --git a/python/paddle/tensor/manipulation.py b/python/paddle/tensor/manipulation.py
index 6d6d2c9f9a7..5e0c13b5ab1 100644
--- a/python/paddle/tensor/manipulation.py
+++ b/python/paddle/tensor/manipulation.py
@@ -190,7 +190,7 @@ def broadcast_tensors(input, name=None):
                     last_index = output_shape_r_last_tensor_index[i]
                     raise TypeError(
                         "Input tensors to broadcast_tensors does not follow bcast semantics"
-                        f"Tensor {last_index} conflicts with Tensor {j} in reversed dimension {i}"
+                        "Tensor {last_index} conflicts with Tensor {j} in reversed dimension {i}"
                     )
                 if output_shape_r[i] <= shape[i]:
                     output_shape_r[i] = shape[i]
@@ -339,10 +339,10 @@ def flatten(x, start_axis=0, stop_axis=-1, name=None):
     if not (isinstance(x, Variable)):
         raise ValueError("The input x should be a Tensor")
 
-    check_variable_and_dtype(
-        x, 'x', ['float32', 'float64', 'int8', 'int32', 'int64', 'uint8'],
-        'flatten')
-    helper = LayerHelper('flatten', **locals())
+    if not in_dygraph_mode():
+        check_variable_and_dtype(
+            x, 'x', ['float32', 'float64', 'int8', 'int32', 'int64', 'uint8'],
+            'flatten')
 
     x_dim = len(x.shape)
     if not (isinstance(start_axis, int)) or (
@@ -365,6 +365,7 @@ def flatten(x, start_axis=0, stop_axis=-1, name=None):
             x, 'start_axis', start_axis, 'stop_axis', stop_axis)
         return dy_out
 
+    helper = LayerHelper('flatten', **locals())
     out = helper.create_variable_for_type_inference(x.dtype)
     x_shape = helper.create_variable_for_type_inference(x.dtype)
     helper.append_op(
@@ -442,7 +443,6 @@ def roll(x, shifts, axis=None, name=None):
             # [1. 2. 3.]
             # [4. 5. 6.]]
     """
-    helper = LayerHelper("roll", **locals())
     origin_shape = x.shape
     if type(shifts) == int:
         shifts = [shifts]
@@ -456,17 +456,15 @@ def roll(x, shifts, axis=None, name=None):
                 raise ValueError(
                     "axis is out of range, it should be in range [{}, {}), but received {}".
                     format(-len_origin_shape, len_origin_shape, axis))
-
-    if axis:
-        check_type(axis, 'axis', (list, tuple), 'roll')
     else:
         axis = []
 
-    check_type(shifts, 'shifts', (list, tuple), 'roll')
-
     if in_dygraph_mode():
         return core.ops.roll(x, 'axis', axis, 'shifts', shifts)
 
+    helper = LayerHelper("roll", **locals())
+    check_type(axis, 'axis', (list, tuple), 'roll')
+    check_type(shifts, 'shifts', (list, tuple), 'roll')
     out = helper.create_variable_for_type_inference(x.dtype)
 
     helper.append_op(
@@ -1017,11 +1015,6 @@ def unbind(input, axis=0):
             # x3.shape [3, 5]
 
     """
-    helper = LayerHelper("unbind", **locals())
-    check_type(input, 'input', (Variable), 'unbind')
-    dtype = helper.input_dtype()
-    check_dtype(dtype, 'unbind', ['float32', 'float64', 'int32', 'int64'],
-                'unbind')
     if not isinstance(axis, (int)):
         raise TypeError("The type of 'axis'  must be int, but received %s." %
                         (type(axis)))
@@ -1030,13 +1023,18 @@ def unbind(input, axis=0):
     input_shape = input.shape
     axis_ = axis if axis >= 0 else len(input_shape) + axis
     num = input_shape[axis_]
+    if in_dygraph_mode():
+        return core.ops.unbind(input, num, 'axis', axis)
+
+    helper = LayerHelper("unbind", **locals())
+    check_type(input, 'input', (Variable), 'unbind')
+    dtype = helper.input_dtype()
+    check_dtype(dtype, 'unbind', ['float32', 'float64', 'int32', 'int64'],
+                'unbind')
     outs = [
         helper.create_variable_for_type_inference(dtype=helper.input_dtype())
         for i in range(num)
     ]
-    if in_dygraph_mode():
-        return core.ops.unbind(input, num, 'axis', axis)
-
     helper.append_op(
         type="unbind",
         inputs={"X": input},
diff --git a/python/paddle/tensor/search.py b/python/paddle/tensor/search.py
index 3d8a75f9277..5e828a100d3 100644
--- a/python/paddle/tensor/search.py
+++ b/python/paddle/tensor/search.py
@@ -159,7 +159,6 @@ def argmax(x, axis=None, keepdim=False, dtype="int64", name=None):
         )
 
     var_dtype = convert_np_dtype_to_dtype_(dtype)
-    check_dtype(var_dtype, 'dtype', ['int32', 'int64'], 'argmin')
     flatten = False
     if axis is None:
         flatten = True
@@ -174,6 +173,7 @@ def argmax(x, axis=None, keepdim=False, dtype="int64", name=None):
     check_variable_and_dtype(
         x, 'x', ['float32', 'float64', 'int16', 'int32', 'int64', 'uint8'],
         'paddle.argmax')
+    check_dtype(var_dtype, 'dtype', ['int32', 'int64'], 'argmin')
     attrs = {}
     out = helper.create_variable_for_type_inference(var_dtype)
     attrs['keepdims'] = keepdim
@@ -236,7 +236,6 @@ def argmin(x, axis=None, keepdim=False, dtype="int64", name=None):
         )
 
     var_dtype = convert_np_dtype_to_dtype_(dtype)
-    check_dtype(var_dtype, 'dtype', ['int32', 'int64'], 'argmin')
     flatten = False
     if axis is None:
         flatten = True
@@ -251,6 +250,7 @@ def argmin(x, axis=None, keepdim=False, dtype="int64", name=None):
     check_variable_and_dtype(
         x, 'x', ['float32', 'float64', 'int16', 'int32', 'int64', 'uint8'],
         'paddle.argmin')
+    check_dtype(var_dtype, 'dtype', ['int32', 'int64'], 'argmin')
     out = helper.create_variable_for_type_inference(var_dtype)
     attrs = {}
     attrs['keepdims'] = keepdim
-- 
GitLab