add unitest for nce layer.

python/paddle/trainer_config_helpers/layers.py

@@ -4926,7 +4926,7 @@ def crf_decoding_layer(input,
 @layer_support()
 def nce_layer(input,
               label,
-              num_classes,
+              num_classes=None,
               act=None,
               param_attr=None,
               weight=None,
@@ -4944,7 +4944,8 @@ def nce_layer(input,
 
     .. code-block:: python
 
-       cost = nce_layer(input=layer1, label=layer2, weight=layer3,
+       cost = nce_layer(input=[layer1, layer2], label=layer2,
+                        param_attr=[attr1, attr2], weight=layer3,
                         num_classes=3, neg_distribution=[0.1,0.3,0.6])
 
     :param name: layer name
@@ -4988,6 +4989,8 @@ def nce_layer(input,
 
     assert isinstance(label, LayerOutput)
     assert label.layer_type == LayerType.DATA
+    if num_classes is None:
+        num_classes = label.size
     if neg_distribution is not None:
         assert isinstance(neg_distribution, collections.Sequence)
         assert len(neg_distribution) == num_classes

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

@@ -215,6 +215,22 @@ layers {
   }
   coeff: 1.0
 }
+layers {
+  name: "__nce_layer_0__"
+  type: "nce"
+  size: 1
+  active_type: "sigmoid"
+  inputs {
+    input_layer_name: "__fc_layer_0__"
+    input_parameter_name: "___nce_layer_0__.w0"
+  }
+  inputs {
+    input_layer_name: "labels"
+  }
+  bias_parameter_name: "___nce_layer_0__.wbias"
+  num_classes: 5000
+  num_neg_samples: 10
+}
 parameters {
   name: "___fc_layer_0__.w0"
   size: 800
@@ -245,6 +261,26 @@ parameters {
   initial_strategy: 0
   initial_smart: true
 }
+parameters {
+  name: "___nce_layer_0__.w0"
+  size: 20000
+  initial_mean: 0.0
+  initial_std: 0.0141421356237
+  dims: 5000
+  dims: 4
+  initial_strategy: 0
+  initial_smart: true
+}
+parameters {
+  name: "___nce_layer_0__.wbias"
+  size: 5000
+  initial_mean: 0.0
+  initial_std: 0.0
+  dims: 1
+  dims: 5000
+  initial_strategy: 0
+  initial_smart: false
+}
 input_layer_names: "input"
 input_layer_names: "labels"
 input_layer_names: "crf_label"
@@ -267,6 +303,7 @@ output_layer_names: "__cross_entropy_with_selfnorm_0__"
 output_layer_names: "__huber_cost_0__"
 output_layer_names: "__multi_binary_label_cross_entropy_0__"
 output_layer_names: "__sum_cost_0__"
+output_layer_names: "__nce_layer_0__"
 sub_models {
   name: "root"
   layer_names: "input"
@@ -292,6 +329,7 @@ sub_models {
   layer_names: "__huber_cost_0__"
   layer_names: "__multi_binary_label_cross_entropy_0__"
   layer_names: "__sum_cost_0__"
+  layer_names: "__nce_layer_0__"
   input_layer_names: "input"
   input_layer_names: "labels"
   input_layer_names: "crf_label"
@@ -314,6 +352,7 @@ sub_models {
   output_layer_names: "__huber_cost_0__"
   output_layer_names: "__multi_binary_label_cross_entropy_0__"
   output_layer_names: "__sum_cost_0__"
+  output_layer_names: "__nce_layer_0__"
   is_recurrent_layer_group: false
 }
 

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

@@ -60,6 +60,31 @@ layers {
   }
   coeff: 1.0
 }
+layers {
+  name: "multi_class_label"
+  type: "data"
+  size: 500
+  active_type: ""
+}
+layers {
+  name: "__nce_layer_0__"
+  type: "nce"
+  size: 1
+  active_type: "sigmoid"
+  inputs {
+    input_layer_name: "__fc_layer_0__"
+    input_parameter_name: "___nce_layer_0__.w0"
+  }
+  inputs {
+    input_layer_name: "multi_class_label"
+  }
+  inputs {
+    input_layer_name: "weight"
+  }
+  bias_parameter_name: "___nce_layer_0__.wbias"
+  num_classes: 500
+  num_neg_samples: 10
+}
 parameters {
   name: "___fc_layer_0__.w0"
   size: 3000
@@ -80,9 +105,30 @@ parameters {
   initial_strategy: 0
   initial_smart: false
 }
+parameters {
+  name: "___nce_layer_0__.w0"
+  size: 5000
+  initial_mean: 0.0
+  initial_std: 0.04472135955
+  dims: 500
+  dims: 10
+  initial_strategy: 0
+  initial_smart: true
+}
+parameters {
+  name: "___nce_layer_0__.wbias"
+  size: 500
+  initial_mean: 0.0
+  initial_std: 0.0
+  dims: 1
+  dims: 500
+  initial_strategy: 0
+  initial_smart: false
+}
 input_layer_names: "input"
 input_layer_names: "label"
 input_layer_names: "weight"
+input_layer_names: "multi_class_label"
 output_layer_names: "__cost_0__"
 output_layer_names: "__mse_cost_0__"
 evaluators {
@@ -100,9 +146,12 @@ sub_models {
   layer_names: "__fc_layer_0__"
   layer_names: "__cost_0__"
   layer_names: "__mse_cost_0__"
+  layer_names: "multi_class_label"
+  layer_names: "__nce_layer_0__"
   input_layer_names: "input"
   input_layer_names: "label"
   input_layer_names: "weight"
+  input_layer_names: "multi_class_label"
   output_layer_names: "__cost_0__"
   output_layer_names: "__mse_cost_0__"
   evaluator_names: "classification_error_evaluator"

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

@@ -40,4 +40,6 @@ outputs(
             name='huber_label', size=1)),
     multi_binary_label_cross_entropy(
         input=probs, label=xe_label),
-    sum_cost(input=hidden))
+    sum_cost(input=hidden),
+    nce_layer(
+        input=hidden, label=labels))

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

@@ -11,4 +11,9 @@ outputs(
     classification_cost(
         input=fc, label=lbl, weight=wt),
     mse_cost(
-        input=fc, label=lbl, weight=wt))
+        input=fc, label=lbl, weight=wt),
+    nce_layer(
+        input=fc,
+        label=data_layer(
+            name='multi_class_label', size=500),
+        weight=wt))