Add more details for CTC layer, fix CTC evalutor and add their interface test (#74)

* Add some comments for CTC layer and fix CTC evalutors, also add interface test

doc/build/contribute_to_paddle.md

@@ -25,7 +25,7 @@ repo or just head straight to the command line:
  
 ```shell
 # Clone your fork to your local machine
-git clone git@github.com:USERNAME/paddle.git
+git clone git@github.com:USERNAME/Paddle.git
 ```
 Then you can start to develop. 
 
@@ -52,7 +52,7 @@ To do this, you'll need to add a remote at first:
 # see the current configured remote repository
 git remote -v
 # add upstream repository
-git remote add upstream https://github.com/paddle/paddle.git
+git remote add upstream https://github.com/baidu/Paddle.git
 # verify the new upstream
 git remote -v
 ```

python/paddle/trainer_config_helpers/evaluators.py

@@ -94,7 +94,7 @@ def evaluator_base(
          Batch=200 samples=20000 AvgCost=0.679655 CurrentCost=0.662179 Eval:
          classification_error_evaluator=0.4486
          CurrentEval: ErrorRate=0.3964
-         
+
     :param input: Input layers, a object of LayerOutput or a list of
                   LayerOutput.
     :type input: list|LayerOutput
@@ -296,6 +296,7 @@ def precision_recall_evaluator(
 @wrap_name_default()
 def ctc_error_evaluator(
         input,
+        label,
         name=None,
         ):
     """
@@ -305,16 +306,19 @@ def ctc_error_evaluator(
 
     .. code-block:: python
 
-       eval = ctc_error_evaluator(input)
+       eval = ctc_error_evaluator(input=input, label=lbl)
 
     :param name: Evaluator name.
     :type name: None|basestring
     :param input: Input Layer.
     :type input: LayerOutput
+    :param label: input label, which is a data_layer.
+    :type label: LayerOutput
     """
     evaluator_base(name=name,
                    type="ctc_edit_distance",
-                   input=input)
+                   input=input,
+                   label=label)
 
 @evaluator(EvaluatorAttribute.FOR_CLASSIFICATION)
 @wrap_name_default()

python/paddle/trainer_config_helpers/layers.py

@@ -2944,7 +2944,7 @@ def linear_comb_layer(weights, vectors, size, name=None):
 
     .. math::
 
-       z = x^T Y
+       z = x^\mathrm{T} Y
 
     In this formular:
       - :math:`x`: weights
@@ -3064,6 +3064,17 @@ def ctc_layer(input, label, size, name=None, norm_by_times=False):
     classication task. That is, for sequence labeling problems where the
     alignment between the inputs and the target labels is unknown.
 
+    More details can be found by referring to `Connectionist Temporal
+    Classification: Labelling Unsegmented Sequence Data with Recurrent
+    Neural Networks <http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf>`_
+
+    Note:
+        Considering the 'blank' label needed by CTC, you need to use
+        (num_classes + 1) as the input size. num_classes is the category number.
+        And the 'blank' is the last category index. So the size of 'input' layer, such as
+        fc_layer with softmax activation, should be num_classes + 1. The size of ctc_layer
+        should also be num_classes + 1.
+
     The simple usage:
 
     .. code-block:: python
@@ -3077,7 +3088,7 @@ def ctc_layer(input, label, size, name=None, norm_by_times=False):
     :type input: LayerOutput
     :param label: The data layer of label with variable length.
     :type label: LayerOutput
-    :param size: category numbers.
+    :param size: category numbers + 1.
     :type size: int
     :param name: The name of this layer, which can not specify.
     :type name: string|None

python/paddle/trainer_config_helpers/tests/layers_test_config.py

@@ -34,6 +34,15 @@ out = fc_layer(input=[cos1, cos3, linear_comb],
 
 outputs(classification_cost(out, data_layer(name="label", size=num_classes)))
 
+# for ctc
+tmp = fc_layer(input=x1,
+               size=num_classes + 1,
+               act=SoftmaxActivation())
+ctc = ctc_layer(input=tmp,
+                label=y,
+                size=num_classes + 1)
+ctc_eval = ctc_error_evaluator(input=ctc, label=y)
+
 settings(
     batch_size=10,
     learning_rate=2e-3,