Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into book

Author: gangliao

authors

@@ -29,13 +29,16 @@ Luo, Tao
 Lyu, Qin
 Mao, Hongyue
 Qian, Xiaojun
+Qiao, Longfei
 Qi, Jun
 Qin, Duohao
 Shen, Guolong
 Shi, Guangchuan
 Song, Xiang
+Wang, Helin
 Wang, Jiang
 Wang, Yanfei
+Wang, Yi
 Wang, Yong
 Weng, Renliang
 Xu, Tianbing

demo/mnist/api_train_v2.py

@@ -122,13 +122,14 @@ def event_handler(event):
     test_creator = paddle.dataset.mnist.test()
     test_data = []
     for item in test_creator():
-        test_data.append(item[0])
+        test_data.append((item[0], ))
         if len(test_data) == 100:
             break
 
     # output is a softmax layer. It returns probabilities.
     # Shape should be (100, 10)
-    probs = paddle.infer(output=predict, parameters=parameters, input=test_data)
+    probs = paddle.infer(
+        output_layer=predict, parameters=parameters, input=test_data)
     print probs.shape
 
 

demo/sentiment/train_v2.py

@@ -13,8 +13,6 @@
 # limitations under the License.
 
 import sys
-import paddle.trainer_config_helpers.attrs as attrs
-from paddle.trainer_config_helpers.poolings import MaxPooling
 import paddle.v2 as paddle
 
 
@@ -51,16 +49,14 @@ def stacked_lstm_net(input_dim,
     emb_dim: dimension of word embedding.
     hid_dim: dimension of hidden layer.
     stacked_num: number of stacked lstm-hidden layer.
-    is_predict: is predicting or not.
-                Some layers is not needed in network when predicting.
     """
     assert stacked_num % 2 == 1
 
-    layer_attr = attrs.ExtraLayerAttribute(drop_rate=0.5)
-    fc_para_attr = attrs.ParameterAttribute(learning_rate=1e-3)
-    lstm_para_attr = attrs.ParameterAttribute(initial_std=0., learning_rate=1.)
+    layer_attr = paddle.attr.Extra(drop_rate=0.5)
+    fc_para_attr = paddle.attr.Param(learning_rate=1e-3)
+    lstm_para_attr = paddle.attr.Param(initial_std=0., learning_rate=1.)
     para_attr = [fc_para_attr, lstm_para_attr]
-    bias_attr = attrs.ParameterAttribute(initial_std=0., l2_rate=0.)
+    bias_attr = paddle.attr.Param(initial_std=0., l2_rate=0.)
     relu = paddle.activation.Relu()
     linear = paddle.activation.Linear()
 
@@ -90,8 +86,10 @@ def stacked_lstm_net(input_dim,
             layer_attr=layer_attr)
         inputs = [fc, lstm]
 
-    fc_last = paddle.layer.pooling(input=inputs[0], pooling_type=MaxPooling())
-    lstm_last = paddle.layer.pooling(input=inputs[1], pooling_type=MaxPooling())
+    fc_last = paddle.layer.pooling(
+        input=inputs[0], pooling_type=paddle.pooling.Max())
+    lstm_last = paddle.layer.pooling(
+        input=inputs[1], pooling_type=paddle.pooling.Max())
     output = paddle.layer.fc(input=[fc_last, lstm_last],
                              size=class_dim,
                              act=paddle.activation.Softmax(),
@@ -105,14 +103,23 @@ def stacked_lstm_net(input_dim,
 
 if __name__ == '__main__':
     # init
-    paddle.init(use_gpu=False, trainer_count=4)
+    paddle.init(use_gpu=False)
 
-    # network config
+    #data
     print 'load dictionary...'
     word_dict = paddle.dataset.imdb.word_dict()
     dict_dim = len(word_dict)
     class_dim = 2
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(
+            lambda: paddle.dataset.imdb.train(word_dict), buf_size=1000),
+        batch_size=100)
+    test_reader = paddle.batch(
+        lambda: paddle.dataset.imdb.test(word_dict), batch_size=100)
+
+    feeding = {'word': 0, 'label': 1}
 
+    # network config
     # Please choose the way to build the network
     # by uncommenting the corresponding line.
     cost = convolution_net(dict_dim, class_dim=class_dim)
@@ -137,12 +144,7 @@ def event_handler(event):
                 sys.stdout.write('.')
                 sys.stdout.flush()
         if isinstance(event, paddle.event.EndPass):
-            result = trainer.test(
-                reader=paddle.batch(
-                    lambda: paddle.dataset.imdb.test(word_dict),
-                    batch_size=128),
-                feeding={'word': 0,
-                         'label': 1})
+            result = trainer.test(reader=test_reader, feeding=feeding)
             print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 
     # create trainer
@@ -151,11 +153,7 @@ def event_handler(event):
                                  update_equation=adam_optimizer)
 
     trainer.train(
-        reader=paddle.batch(
-            paddle.reader.shuffle(
-                lambda: paddle.dataset.imdb.train(word_dict), buf_size=1000),
-            batch_size=100),
+        reader=train_reader,
         event_handler=event_handler,
-        feeding={'word': 0,
-                 'label': 1},
-        num_passes=10)
+        feeding=feeding,
+        num_passes=2)

demo/seqToseq/api_train_v2.py

@@ -1,3 +1,4 @@
+import sys
 import paddle.v2 as paddle
 
 
@@ -104,7 +105,9 @@ def main():
     parameters = paddle.parameters.create(cost)
 
     # define optimize method and trainer
-    optimizer = paddle.optimizer.Adam(learning_rate=1e-4)
+    optimizer = paddle.optimizer.Adam(
+        learning_rate=5e-5,
+        regularization=paddle.optimizer.L2Regularization(rate=1e-3))
     trainer = paddle.trainer.SGD(cost=cost,
                                  parameters=parameters,
                                  update_equation=optimizer)
@@ -125,8 +128,11 @@ def main():
     def event_handler(event):
         if isinstance(event, paddle.event.EndIteration):
             if event.batch_id % 10 == 0:
-                print "Pass %d, Batch %d, Cost %f, %s" % (
+                print "\nPass %d, Batch %d, Cost %f, %s" % (
                     event.pass_id, event.batch_id, event.cost, event.metrics)
+            else:
+                sys.stdout.write('.')
+                sys.stdout.flush()
 
     # start to train
     trainer.train(