Merge pull request #1635 from luotao1/mse

rename regression_cost to mse_cost

demo/introduction/api_train_v2.py

@@ -14,7 +14,7 @@ def main():
                                 act=paddle.activation.Linear(),
                                 bias_attr=paddle.attr.Param(name='b'))
     y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-    cost = paddle.layer.regression_cost(input=y_predict, label=y)
+    cost = paddle.layer.mse_cost(input=y_predict, label=y)
 
     # create parameters
     parameters = paddle.parameters.create(cost)

demo/introduction/trainer_config.py

@@ -34,5 +34,5 @@ y_predict = fc_layer(
     size=1,
     act=LinearActivation(),
     bias_attr=ParamAttr(name='b'))
-cost = regression_cost(input=y_predict, label=y)
+cost = mse_cost(input=y_predict, label=y)
 outputs(cost)

demo/recommendation/api_train_v2.py

@@ -61,7 +61,7 @@ def main():
 
     inference = paddle.layer.cos_sim(
         a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
-    cost = paddle.layer.regression_cost(
+    cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))

demo/recommendation/trainer_config.py

@@ -86,10 +86,7 @@ movie_feature = construct_feature("movie")
 user_feature = construct_feature("user")
 similarity = cos_sim(a=movie_feature, b=user_feature)
 if not is_predict:
-    outputs(
-        regression_cost(
-            input=similarity, label=data_layer(
-                'rating', size=1)))
+    outputs(mse_cost(input=similarity, label=data_layer('rating', size=1)))
 
     define_py_data_sources2(
         'data/train.list',

doc/api/v1/trainer_config_helpers/layers.rst

@@ -432,6 +432,12 @@ multi_binary_label_cross_entropy
     :members: multi_binary_label_cross_entropy
     :noindex:
 
+mse_cost
+---------
+..  automodule:: paddle.trainer_config_helpers.layers
+    :members: mse_cost
+    :noindex:
+
 huber_cost
 ----------
 ..  automodule:: paddle.trainer_config_helpers.layers
@@ -450,6 +456,12 @@ rank_cost
     :members: rank_cost
     :noindex:
 
+sum_cost
+---------
+..  automodule:: paddle.trainer_config_helpers.layers
+    :members: sum_cost
+    :noindex:
+
 crf_layer
 -----------------
 ..  automodule:: paddle.trainer_config_helpers.layers
@@ -486,12 +498,6 @@ hsigmoid
     :members: hsigmoid
     :noindex:
 
-sum_cost
----------
-..  automodule:: paddle.trainer_config_helpers.layers
-    :members: sum_cost
-    :noindex:
-
 Check Layer 
 ============
 

doc/getstarted/basic_usage/index_cn.rst

@@ -55,7 +55,7 @@ PaddlePaddle是源于百度的一个深度学习平台。这份简短的介绍
     # 线性计算网络层: ȳ = wx + b
     ȳ = fc_layer(input=x, param_attr=ParamAttr(name='w'), size=1, act=LinearActivation(), bias_attr=ParamAttr(name='b'))
     # 计算误差函数，即  ȳ 和真实 y 之间的距离
-    cost = regression_cost(input= ȳ, label=y)
+    cost = mse_cost(input= ȳ, label=y)
     outputs(cost)
 
 
@@ -69,7 +69,7 @@ PaddlePaddle是源于百度的一个深度学习平台。这份简短的介绍
     
     - **数据层**：数据层 `data_layer` 是神经网络的入口，它读入数据并将它们传输到接下来的网络层。这里数据层有两个，分别对应于变量 `x` 和 `y`。
     - **全连接层**：全连接层 `fc_layer` 是基础的计算单元，这里利用它建模变量之间的线性关系。计算单元是神经网络的核心，PaddlePaddle支持大量的计算单元和任意深度的网络连接，从而可以拟合任意的函数来学习复杂的数据关系。
-    - **回归误差代价层**：回归误差代价层 `regression_cost` 是众多误差代价函数层的一种，它们在训练过程作为网络的出口，用来计算模型的误差，是模型参数优化的目标函数。
+    - **回归误差代价层**：回归误差代价层 `mse_cost` 是众多误差代价函数层的一种，它们在训练过程作为网络的出口，用来计算模型的误差，是模型参数优化的目标函数。
 
 定义了网络结构并保存为 `trainer_config.py` 之后，运行以下训练命令：
 

doc/getstarted/basic_usage/index_en.rst

@@ -49,7 +49,7 @@ To recover this relationship between ``X`` and ``Y``, we use a neural network wi
         x = data_layer(name='x', size=1)
         y = data_layer(name='y', size=1)
         y_predict = fc_layer(input=x, param_attr=ParamAttr(name='w'), size=1, act=LinearActivation(), bias_attr=ParamAttr(name='b'))
-        cost = regression_cost(input=y_predict, label=y)
+        cost = mse_cost(input=y_predict, label=y)
         outputs(cost)
 
 Some of the most fundamental usages of PaddlePaddle are demonstrated:

doc/howto/usage/k8s/k8s_distributed_cn.md

@@ -213,7 +213,7 @@ I1116 09:10:17.123440    50 Util.cpp:130] Calling runInitFunctions
 I1116 09:10:17.123764    50 Util.cpp:143] Call runInitFunctions done.
 [WARNING 2016-11-16 09:10:17,227 default_decorators.py:40] please use keyword arguments in paddle config.
 [INFO 2016-11-16 09:10:17,239 networks.py:1282] The input order is [movie_id, title, genres, user_id, gender, age, occupation, rating]
-[INFO 2016-11-16 09:10:17,239 networks.py:1289] The output order is [__regression_cost_0__]
+[INFO 2016-11-16 09:10:17,239 networks.py:1289] The output order is [__mse_cost_0__]
 I1116 09:10:17.392917    50 Trainer.cpp:170] trainer mode: Normal
 I1116 09:10:17.613910    50 PyDataProvider2.cpp:257] loading dataprovider dataprovider::process
 I1116 09:10:17.680917    50 PyDataProvider2.cpp:257] loading dataprovider dataprovider::process

python/paddle/trainer_config_helpers/layers.py

@@ -52,6 +52,7 @@ __all__ = [
     "cos_sim",
     "hsigmoid",
     "conv_projection",
+    "mse_cost",
     "regression_cost",
     'classification_cost',
     "LayerOutput",
@@ -3572,11 +3573,14 @@ def __cost_input__(input, label, weight=None):
 
 @wrap_name_default()
 @layer_support()
-def regression_cost(input, label, weight=None, name=None, layer_attr=None):
+def mse_cost(input, label, weight=None, name=None, layer_attr=None):
     """
-    Regression Layer.
+    mean squared error cost:
+
+    ..  math::
+
+       $\frac{1}{N}\sum_{i=1}^N(t _i- y_i)^2$
 
-    TODO(yuyang18): Complete this method.
 
     :param name: layer name.
     :type name: basestring
@@ -3602,6 +3606,9 @@ def regression_cost(input, label, weight=None, name=None, layer_attr=None):
     return LayerOutput(name, LayerType.COST, parents=parents, size=1)
 
 
+regression_cost = mse_cost
+
+
 @wrap_name_default("cost")
 @layer_support()
 def classification_cost(input,

python/paddle/trainer_config_helpers/tests/configs/protostr/test_cost_layers_with_weight.protostr

@@ -45,7 +45,7 @@ layers {
   coeff: 1.0
 }
 layers {
-  name: "__regression_cost_0__"
+  name: "__mse_cost_0__"
   type: "square_error"
   size: 1
   active_type: ""
@@ -84,7 +84,7 @@ input_layer_names: "input"
 input_layer_names: "label"
 input_layer_names: "weight"
 output_layer_names: "__cost_0__"
-output_layer_names: "__regression_cost_0__"
+output_layer_names: "__mse_cost_0__"
 evaluators {
   name: "classification_error_evaluator"
   type: "classification_error"
@@ -99,12 +99,12 @@ sub_models {
   layer_names: "weight"
   layer_names: "__fc_layer_0__"
   layer_names: "__cost_0__"
-  layer_names: "__regression_cost_0__"
+  layer_names: "__mse_cost_0__"
   input_layer_names: "input"
   input_layer_names: "label"
   input_layer_names: "weight"
   output_layer_names: "__cost_0__"
-  output_layer_names: "__regression_cost_0__"
+  output_layer_names: "__mse_cost_0__"
   evaluator_names: "classification_error_evaluator"
   is_recurrent_layer_group: false
 }

python/paddle/trainer_config_helpers/tests/configs/test_cost_layers_with_weight.py

@@ -10,5 +10,5 @@ fc = fc_layer(input=data, size=10, act=SoftmaxActivation())
 outputs(
     classification_cost(
         input=fc, label=lbl, weight=wt),
-    regression_cost(
+    mse_cost(
         input=fc, label=lbl, weight=wt))

python/paddle/v2/tests/test_layer.py

@@ -126,9 +126,8 @@ class CostLayerTest(unittest.TestCase):
         cost3 = layer.cross_entropy_cost(input=inference, label=label)
         cost4 = layer.cross_entropy_with_selfnorm_cost(
             input=inference, label=label)
-        cost5 = layer.regression_cost(input=inference, label=label)
-        cost6 = layer.regression_cost(
-            input=inference, label=label, weight=weight)
+        cost5 = layer.mse_cost(input=inference, label=label)
+        cost6 = layer.mse_cost(input=inference, label=label, weight=weight)
         cost7 = layer.multi_binary_label_cross_entropy_cost(
             input=inference, label=label)
         cost8 = layer.rank_cost(left=score, right=score, label=score)