Add more comments in model conf and make it more concise

fluid/DeepASR/model.py

@@ -12,37 +12,20 @@ def stacked_lstmp_model(hidden_dim,
                         parallel=False,
                         is_train=True,
                         class_num=1749):
-    feature = fluid.layers.data(
-        name="feature", shape=[-1, 120 * 11], dtype="float32", lod_level=1)
-    label = fluid.layers.data(
-        name="label", shape=[-1, 1], dtype="int64", lod_level=1)
-
-    if parallel:
-        places = fluid.layers.get_places()
-        pd = fluid.layers.ParallelDo(places)
-        with pd.do():
-            feat_ = pd.read_input(feature)
-            label_ = pd.read_input(label)
-            prediction, avg_cost, acc = _net_conf(feat_, label_, hidden_dim,
-                                                  proj_dim, stacked_num,
-                                                  class_num, is_train)
-            for out in [avg_cost, acc]:
-                pd.write_output(out)
+    """ The model for DeepASR. The main structure is composed of stacked 
+        identical LSTMP (LSTM with recurrent projection) layers.
 
-        # get mean loss and acc through every devices.
-        avg_cost, acc = pd()
-        avg_cost = fluid.layers.mean(x=avg_cost)
-        acc = fluid.layers.mean(x=acc)
-    else:
-        prediction, avg_cost, acc = _net_conf(feature, label, hidden_dim,
-                                              proj_dim, stacked_num, class_num,
-                                              is_train)
-
-    return prediction, avg_cost, acc
+    Args:
+	hidden_dim(int): The hidden state's dimension of the LSTMP layer.
+	proj_dim(int): The projection size of the LSTMP layer.
+	stacked_num(int): The number of stacked LSTMP layers.
+	parallel(bool): Run in parallel or not, default `False`.
+	is_train(bool): Run in training phase or not, default `True`.
+	class_dim(int): The number of output classes.
+    """
 
-
-def _net_conf(feature, label, hidden_dim, proj_dim, stacked_num, class_num,
-              is_train):
+    # network configuration
+    def _net_conf(feature, label):
         seq_conv1 = fluid.layers.sequence_conv(
             input=feature,
             num_filters=1024,
@@ -88,3 +71,31 @@ def _net_conf(feature, label, hidden_dim, proj_dim, stacked_num, class_num,
         avg_cost = fluid.layers.mean(x=cost)
         acc = fluid.layers.accuracy(input=prediction, label=label)
         return prediction, avg_cost, acc
+
+    # data feeder
+    feature = fluid.layers.data(
+        name="feature", shape=[-1, 120 * 11], dtype="float32", lod_level=1)
+    label = fluid.layers.data(
+        name="label", shape=[-1, 1], dtype="int64", lod_level=1)
+
+    if parallel:
+        # When the execution place is specified to CUDAPlace, the program will
+        # run on all $CUDA_VISIBLE_DEVICES GPUs. Otherwise the program will 
+        # run on all CPU devices.
+        places = fluid.layers.get_places()
+        pd = fluid.layers.ParallelDo(places)
+        with pd.do():
+            feat_ = pd.read_input(feature)
+            label_ = pd.read_input(label)
+            prediction, avg_cost, acc = _net_conf(feat_, label_)
+            for out in [avg_cost, acc]:
+                pd.write_output(out)
+
+        # get mean loss and acc through every devices.
+        avg_cost, acc = pd()
+        avg_cost = fluid.layers.mean(x=avg_cost)
+        acc = fluid.layers.mean(x=acc)
+    else:
+        prediction, avg_cost, acc = _net_conf(feature, label)
+
+    return prediction, avg_cost, acc