Merge pull request #13667 from sneaxiy/release/1.0.0

Cherry-pick API change to Release/1.0.0

paddle/fluid/API.spec

@@ -145,14 +145,14 @@ paddle.fluid.layers.unstack ArgSpec(args=['x', 'axis', 'num'], varargs=None, key
 paddle.fluid.layers.sequence_enumerate ArgSpec(args=['input', 'win_size', 'pad_value', 'name'], varargs=None, keywords=None, defaults=(0, None))
 paddle.fluid.layers.expand ArgSpec(args=['x', 'expand_times', 'name'], varargs=None, keywords=None, defaults=(None,))
 paddle.fluid.layers.sequence_concat ArgSpec(args=['input', 'name'], varargs=None, keywords=None, defaults=(None,))
-paddle.fluid.layers.scale ArgSpec(args=['x', 'scale', 'bias', 'bias_after_scale', 'out', 'act', 'name'], varargs=None, keywords=None, defaults=(1.0, 0.0, True, None, None, None))
-paddle.fluid.layers.elementwise_add ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_div ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_sub ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_mul ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_max ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_min ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
-paddle.fluid.layers.elementwise_pow ArgSpec(args=['x', 'y', 'out', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, -1, False, None, None))
+paddle.fluid.layers.scale ArgSpec(args=['x', 'scale', 'bias', 'bias_after_scale', 'act', 'name'], varargs=None, keywords=None, defaults=(1.0, 0.0, True, None, None))
+paddle.fluid.layers.elementwise_add ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_div ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_sub ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_mul ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_max ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_min ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
+paddle.fluid.layers.elementwise_pow ArgSpec(args=['x', 'y', 'axis', 'use_mkldnn', 'act', 'name'], varargs=None, keywords=None, defaults=(-1, False, None, None))
 paddle.fluid.layers.uniform_random_batch_size_like ArgSpec(args=['input', 'shape', 'dtype', 'input_dim_idx', 'output_dim_idx', 'min', 'max', 'seed'], varargs=None, keywords=None, defaults=('float32', 0, 0, -1.0, 1.0, 0))
 paddle.fluid.layers.gaussian_random ArgSpec(args=['shape', 'mean', 'std', 'seed', 'dtype', 'use_mkldnn'], varargs=None, keywords=None, defaults=(0.0, 1.0, 0, 'float32', False))
 paddle.fluid.layers.sampling_id ArgSpec(args=['x', 'min', 'max', 'seed', 'dtype'], varargs=None, keywords=None, defaults=(0.0, 1.0, 0, 'float32'))

python/paddle/fluid/layers/nn.py

@@ -6630,14 +6630,12 @@ def _elementwise_op(helper):
     assert y is not None, 'y cannot be None in {}'.format(op_type)
     axis = helper.kwargs.get('axis', -1)
     use_mkldnn = helper.kwargs.get('use_mkldnn', False)
-    out = helper.kwargs.get('out', None)
-    if out is None:
-        name = helper.kwargs.get('name', None)
-        if name is None:
-            out = helper.create_tmp_variable(dtype=x.dtype)
-        else:
-            out = helper.create_variable(
-                name=name, dtype=x.dtype, persistable=False)
+    name = helper.kwargs.get('name', None)
+    if name is None:
+        out = helper.create_tmp_variable(dtype=x.dtype)
+    else:
+        out = helper.create_variable(
+            name=name, dtype=x.dtype, persistable=False)
 
     helper.append_op(
         type=op_type,
@@ -6650,13 +6648,7 @@ def _elementwise_op(helper):
 
 
 @templatedoc()
-def scale(x,
-          scale=1.0,
-          bias=0.0,
-          bias_after_scale=True,
-          out=None,
-          act=None,
-          name=None):
+def scale(x, scale=1.0, bias=0.0, bias_after_scale=True, act=None, name=None):
     """
     ${comment}
 
@@ -6665,7 +6657,6 @@ def scale(x,
         scale(${scale_type}): ${scale_comment}
         bias(${bias_type}): ${bias_comment}
         bias_after_scale(${bias_after_scale_type}): ${bias_after_scale_comment}
-        out(Tensor): Output tensor.
         act(basestring|None): Activation applied to the output.
         name(basestring|None): Name of the output. 
 
@@ -6674,12 +6665,11 @@ def scale(x,
     """
 
     helper = LayerHelper('scale', **locals())
-    if out is None:
-        if name is None:
-            out = helper.create_tmp_variable(dtype=x.dtype)
-        else:
-            out = helper.create_variable(
-                name=name, dtype=x.dtype, persistable=False)
+    if name is None:
+        out = helper.create_tmp_variable(dtype=x.dtype)
+    else:
+        out = helper.create_variable(
+            name=name, dtype=x.dtype, persistable=False)
 
     helper.append_op(
         type='scale',
@@ -6693,73 +6683,31 @@ def scale(x,
     return helper.append_activation(out)
 
 
-def elementwise_add(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_add(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_add', **locals()))
 
 
-def elementwise_div(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_div(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_div', **locals()))
 
 
-def elementwise_sub(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_sub(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_sub', **locals()))
 
 
-def elementwise_mul(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_mul(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_mul', **locals()))
 
 
-def elementwise_max(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_max(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_max', **locals()))
 
 
-def elementwise_min(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_min(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_min', **locals()))
 
 
-def elementwise_pow(x,
-                    y,
-                    out=None,
-                    axis=-1,
-                    use_mkldnn=False,
-                    act=None,
-                    name=None):
+def elementwise_pow(x, y, axis=-1, use_mkldnn=False, act=None, name=None):
     return _elementwise_op(LayerHelper('elementwise_pow', **locals()))
 
 
@@ -6771,7 +6719,6 @@ for func in [
     func.__doc__ = _generate_doc_string_(
         op_proto,
         additional_args_lines=[
-            "out (Tensor): The output tensor of elementwise op.",
             "act (basestring|None): Activation applied to the output.",
             "name (basestring|None): Name of the output."
         ])

python/paddle/fluid/layers/ops.py

@@ -56,6 +56,8 @@ for _OP in set(__all__):
 # e.g.: test_program_code.py, test_dist_train.py
 globals()['_scale'] = generate_layer_fn('scale')
 
+globals()['_elementwise_div'] = generate_layer_fn('elementwise_div')
+
 __all__ += __activations_noattr__
 
 for _OP in set(__activations_noattr__):

python/paddle/fluid/optimizer.py

@@ -26,6 +26,7 @@ from .layer_helper import LayerHelper
 from .regularizer import append_regularization_ops
 from .clip import append_gradient_clip_ops, error_clip_callback
 from contextlib import contextmanager
+from .layers import ops
 
 __all__ = [
     'SGD', 'Momentum', 'Adagrad', 'Adam', 'Adamax', 'DecayedAdagrad', 'Ftrl',
@@ -1301,7 +1302,7 @@ class ModelAverage(Optimizer):
             x=tmp, dtype='float32' if self._dtype == None else self._dtype)
         sum = layers.cast(
             x=sum, dtype='float32' if self._dtype == None else self._dtype)
-        layers.elementwise_div(x=sum, y=tmp, out=param)
+        ops._elementwise_div(x=sum, y=tmp, out=param)
 
     def _add_average_restore_op(self, block, param_grad):
         param = block._clone_variable(param_grad[0])