refine some codes

02.recognize_digits/train.py

@@ -44,36 +44,36 @@ def convolutional_neural_network(img):
         input=conv_pool_2, size=10, act=paddle.activation.Softmax())
     return predict
 
+def main():
+    paddle.init(use_gpu=False, trainer_count=1)
 
-paddle.init(use_gpu=False, trainer_count=1)
-
-# define network topology
-images = paddle.layer.data(
+    # define network topology
+    images = paddle.layer.data(
         name='pixel', type=paddle.data_type.dense_vector(784))
-label = paddle.layer.data(name='label', type=paddle.data_type.integer_value(10))
+    label = paddle.layer.data(name='label', type=paddle.data_type.integer_value(10))
 
-# Here we can build the prediction network in different ways. Please
-# choose one by uncomment corresponding line.
-# predict = softmax_regression(images)
-# predict = multilayer_perceptron(images)
-predict = convolutional_neural_network(images)
+    # Here we can build the prediction network in different ways. Please
+    # choose one by uncomment corresponding line.
+    # predict = softmax_regression(images)
+    # predict = multilayer_perceptron(images)
+    predict = convolutional_neural_network(images)
 
-cost = paddle.layer.classification_cost(input=predict, label=label)
+    cost = paddle.layer.classification_cost(input=predict, label=label)
 
-parameters = paddle.parameters.create(cost)
+    parameters = paddle.parameters.create(cost)
 
-optimizer = paddle.optimizer.Momentum(
+    optimizer = paddle.optimizer.Momentum(
         learning_rate=0.1 / 128.0,
         momentum=0.9,
         regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128))
 
-trainer = paddle.trainer.SGD(
+    trainer = paddle.trainer.SGD(
         cost=cost, parameters=parameters, update_equation=optimizer)
 
-lists = []
+    lists = []
 
 
-def event_handler(event):
+    def event_handler(event):
         if isinstance(event, paddle.event.EndIteration):
             if event.batch_id % 100 == 0:
                 print "Pass %d, Batch %d, Cost %f, %s" % (
@@ -81,20 +81,24 @@ def event_handler(event):
         if isinstance(event, paddle.event.EndPass):
             result = trainer.test(reader=paddle.batch(
                 paddle.dataset.mnist.test(), batch_size=128))
-        print "Test with Pass %d, Cost %f, %s\n" % (event.pass_id, result.cost,
+            print "Test with Pass %d, Cost %f, %s\n" % (event.pass_id, 
+                                                        result.cost,
                                                         result.metrics)
             lists.append((event.pass_id, result.cost,
                             result.metrics['classification_error_evaluator']))
 
 
-trainer.train(
+    trainer.train(
         reader=paddle.batch(
             paddle.reader.shuffle(paddle.dataset.mnist.train(), buf_size=8192),
             batch_size=128),
         event_handler=event_handler,
         num_passes=100)
 
-# find the best pass
-best = sorted(lists, key=lambda list: float(list[1]))[0]
-print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
-print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
+    # find the best pass
+    best = sorted(lists, key=lambda list: float(list[1]))[0]
+    print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
+    print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
+
+if __name__ == '__main__':
+    main()    

08.recommender_system/train.py

@@ -3,9 +3,7 @@ import cPickle
 import copy
 
 
-def main():
-    paddle.init(use_gpu=False)
-    movie_title_dict = paddle.dataset.movielens.get_movie_title_dict()
+def get_usr_combined_features():    
     uid = paddle.layer.data(
         name='user_id',
         type=paddle.data_type.integer_value(
@@ -36,7 +34,10 @@ def main():
         input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc],
         size=200,
         act=paddle.activation.Tanh())
+    return usr_combined_features
 
+def get_mov_combined_features():
+    movie_title_dict = paddle.dataset.movielens.get_movie_title_dict()
     mov_id = paddle.layer.data(
         name='movie_id',
         type=paddle.data_type.integer_value(
@@ -61,7 +62,13 @@ def main():
         input=[mov_fc, mov_categories_hidden, mov_title_conv],
         size=200,
         act=paddle.activation.Tanh())
+    return mov_combined_features
     
+
+def main():
+    paddle.init(use_gpu=False)
+    usr_combined_features = get_usr_combined_features()
+    mov_combined_features = get_mov_combined_features()
     inference = paddle.layer.cos_sim(
         a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
     cost = paddle.layer.mse_cost(