Revert "Unify 1.6 api in 06.understand_sentiment (#815)" (#820)

This reverts commit adcdb7b8.

06.understand_sentiment/README.cn.md

@@ -151,7 +151,7 @@ BATCH_SIZE = 128  #batch的大小
 ```python
 #文本卷积神经网络
 def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
     conv_3 = fluid.nets.sequence_conv_pool(
         input=emb,
@@ -183,7 +183,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
 def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
     #计算词向量
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
 
     #第一层栈
@@ -218,8 +218,8 @@ def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
 ```python
 def inference_program(word_dict):
-    data = fluid.data(
-        name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     net = convolution_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM)
@@ -235,7 +235,7 @@ def inference_program(word_dict):
 
 ```python
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1,1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -269,12 +269,12 @@ print("Loading IMDB word dict....")
 word_dict = paddle.dataset.imdb.word_dict()
 
 print ("Reading training data....")
-train_reader = fluid.io.batch(
+train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
 print("Reading testing data....")
-test_reader = fluid.io.batch(
+test_reader = paddle.batch(
     paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 word_dict是一个字典序列，是词和label的对应关系，运行下一行可以看到具体内容：
@@ -401,15 +401,11 @@ reviews = [c.split() for c in reviews_str]
 
 UNK = word_dict['<unk>']
 lod = []
-base_shape = []
-
 for c in reviews:
-    re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-    lod = np.concatenate([lod,re],axis = 0)
-    base_shape.insert(-1, re.shape[0])
+    lod.append([word_dict.get(words, UNK) for words in c])
+
+base_shape = [[len(c) for c in lod]]
 
-base_shape = [base_shape]
-lod = np.array(lod).astype('int64')
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 

06.understand_sentiment/README.md

@@ -140,7 +140,7 @@ Note that `fluid.nets.sequence_conv_pool` contains both convolution and pooling
 ```python
 #Textconvolution neural network
 def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
     conv_3 = fluid.nets.sequence_conv_pool(
         input=emb,
@@ -172,7 +172,7 @@ The code of the stack bidirectional LSTM `stacked_lstm_net` is as follows:
 def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
     # Calculate word vectorvector
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
 
     #First stack
@@ -191,7 +191,7 @@ def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
         inputs = [fc, lstm]
 
     #pooling layer
-    fc_last = fluid.layers.sequence_pool(input=inputs[0], pool_type='max')
+    pc_last = fluid.layers.sequence_pool(input=inputs[0], pool_type='max')
     lstm_last = fluid.layers.sequence_pool(input=inputs[1], pool_type='max')
 
     #Fully connected layer, softmax prediction
@@ -207,8 +207,8 @@ Next we define the prediction program (`inference_program`). We use `convolution
 
 ```python
 def inference_program(word_dict):
-    data = fluid.data(
-        name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     net = convolution_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM)
@@ -224,7 +224,7 @@ During the testing, the classifier calculates the probability of each output. Th
 
 ```python
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1, 1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -258,12 +258,12 @@ print("Loading IMDB word dict....")
 word_dict = paddle.dataset.imdb.word_dict()
 
 print ("Reading training data....")
-train_reader = fluid.io.batch(
+train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
 print("Reading testing data....")
-test_reader = fluid.io.batch(
+test_reader = paddle.batch(
     paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 Word_dict is a dictionary sequence, which is the correspondence between words and labels. You can see it specifically by running the next code:
@@ -390,15 +390,11 @@ reviews = [c.split() for c in reviews_str]
 
 UNK = word_dict['<unk>']
 lod = []
-base_shape = []
-
 for c in reviews:
-    re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-    lod = np.concatenate([lod,re],axis = 0)
-    base_shape.insert(-1, re.shape[0])
+    lod.append([word_dict.get(words, UNK) for words in c])
+
+base_shape = [[len(c) for c in lod]]
 
-base_shape = [base_shape]
-lod = np.array(lod).astype('int64')
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 

06.understand_sentiment/index.cn.html

@@ -193,7 +193,7 @@ BATCH_SIZE = 128  #batch的大小
 ```python
 #文本卷积神经网络
 def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
     conv_3 = fluid.nets.sequence_conv_pool(
         input=emb,
@@ -225,7 +225,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
 def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
     #计算词向量
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
 
     #第一层栈
@@ -260,8 +260,8 @@ def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
 ```python
 def inference_program(word_dict):
-    data = fluid.data(
-        name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     net = convolution_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM)
@@ -277,7 +277,7 @@ def inference_program(word_dict):
 
 ```python
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1,1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -311,12 +311,12 @@ print("Loading IMDB word dict....")
 word_dict = paddle.dataset.imdb.word_dict()
 
 print ("Reading training data....")
-train_reader = fluid.io.batch(
+train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
 print("Reading testing data....")
-test_reader = fluid.io.batch(
+test_reader = paddle.batch(
     paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 word_dict是一个字典序列，是词和label的对应关系，运行下一行可以看到具体内容：
@@ -443,15 +443,11 @@ reviews = [c.split() for c in reviews_str]
 
 UNK = word_dict['<unk>']
 lod = []
-base_shape = []
-
 for c in reviews:
-    re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-    lod = np.concatenate([lod,re],axis = 0)
-    base_shape.insert(-1, re.shape[0])
+    lod.append([word_dict.get(words, UNK) for words in c])
+
+base_shape = [[len(c) for c in lod]]
 
-base_shape = [base_shape]
-lod = np.array(lod).astype('int64')
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 

06.understand_sentiment/index.html

@@ -182,7 +182,7 @@ Note that `fluid.nets.sequence_conv_pool` contains both convolution and pooling
 ```python
 #Textconvolution neural network
 def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
     conv_3 = fluid.nets.sequence_conv_pool(
         input=emb,
@@ -214,7 +214,7 @@ The code of the stack bidirectional LSTM `stacked_lstm_net` is as follows:
 def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
     # Calculate word vectorvector
-    emb = fluid.embedding(
+    emb = fluid.layers.embedding(
         input=data, size=[input_dim, emb_dim], is_sparse=True)
 
     #First stack
@@ -233,7 +233,7 @@ def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
         inputs = [fc, lstm]
 
     #pooling layer
-    fc_last = fluid.layers.sequence_pool(input=inputs[0], pool_type='max')
+    pc_last = fluid.layers.sequence_pool(input=inputs[0], pool_type='max')
     lstm_last = fluid.layers.sequence_pool(input=inputs[1], pool_type='max')
 
     #Fully connected layer, softmax prediction
@@ -249,8 +249,8 @@ Next we define the prediction program (`inference_program`). We use `convolution
 
 ```python
 def inference_program(word_dict):
-    data = fluid.data(
-        name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     net = convolution_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM)
@@ -266,7 +266,7 @@ During the testing, the classifier calculates the probability of each output. Th
 
 ```python
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1, 1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -300,12 +300,12 @@ print("Loading IMDB word dict....")
 word_dict = paddle.dataset.imdb.word_dict()
 
 print ("Reading training data....")
-train_reader = fluid.io.batch(
+train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
 print("Reading testing data....")
-test_reader = fluid.io.batch(
+test_reader = paddle.batch(
     paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 Word_dict is a dictionary sequence, which is the correspondence between words and labels. You can see it specifically by running the next code:
@@ -432,15 +432,11 @@ reviews = [c.split() for c in reviews_str]
 
 UNK = word_dict['<unk>']
 lod = []
-base_shape = []
-
 for c in reviews:
-    re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-    lod = np.concatenate([lod,re],axis = 0)
-    base_shape.insert(-1, re.shape[0])
+    lod.append([word_dict.get(words, UNK) for words in c])
+
+base_shape = [[len(c) for c in lod]]
 
-base_shape = [base_shape]
-lod = np.array(lod).astype('int64')
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 

06.understand_sentiment/train_conv.py

@@ -42,7 +42,8 @@ def parse_args():
 
 
 def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
-    emb = fluid.embedding(input=data, size=[input_dim, emb_dim], is_sparse=True)
+    emb = fluid.layers.embedding(
+        input=data, size=[input_dim, emb_dim], is_sparse=True)
     conv_3 = fluid.nets.sequence_conv_pool(
         input=emb,
         num_filters=hid_dim,
@@ -61,15 +62,16 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
 
 
 def inference_program(word_dict):
-    dict_dim = len(word_dict)
-    data = fluid.data(name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
+    dict_dim = len(word_dict)
     net = convolution_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM)
     return net
 
 
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1, 1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -88,16 +90,16 @@ def train(use_cuda, params_dirname):
 
     print("Reading training data....")
     if args.enable_ce:
-        train_reader = fluid.io.batch(
+        train_reader = paddle.batch(
             paddle.dataset.imdb.train(word_dict), batch_size=BATCH_SIZE)
     else:
-        train_reader = fluid.io.batch(
-            fluid.io.shuffle(
+        train_reader = paddle.batch(
+            paddle.reader.shuffle(
                 paddle.dataset.imdb.train(word_dict), buf_size=25000),
             batch_size=BATCH_SIZE)
 
     print("Reading testing data....")
-    test_reader = fluid.io.batch(
+    test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
     feed_order = ['words', 'label']
@@ -211,15 +213,11 @@ def infer(use_cuda, params_dirname=None):
 
         UNK = word_dict['<unk>']
         lod = []
-        base_shape = []
-
         for c in reviews:
-            re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-            lod = np.concatenate([lod, re], axis=0)
-            base_shape.insert(-1, re.shape[0])
+            lod.append([np.int64(word_dict.get(words, UNK)) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
 
-        base_shape = [base_shape]
-        lod = np.array(lod).astype('int64')
         tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
         assert feed_target_names[0] == "words"
         results = exe.run(

06.understand_sentiment/train_dyn_rnn.py

@@ -42,7 +42,8 @@ def parse_args():
 
 
 def dynamic_rnn_lstm(data, input_dim, class_dim, emb_dim, lstm_size):
-    emb = fluid.embedding(input=data, size=[input_dim, emb_dim], is_sparse=True)
+    emb = fluid.layers.embedding(
+        input=data, size=[input_dim, emb_dim], is_sparse=True)
     sentence = fluid.layers.fc(input=emb, size=lstm_size * 4, act='tanh')
 
     lstm, _ = fluid.layers.dynamic_lstm(sentence, size=lstm_size * 4)
@@ -53,7 +54,8 @@ def dynamic_rnn_lstm(data, input_dim, class_dim, emb_dim, lstm_size):
 
 
 def inference_program(word_dict):
-    data = fluid.data(name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     pred = dynamic_rnn_lstm(data, dict_dim, CLASS_DIM, EMB_DIM, LSTM_SIZE)
@@ -61,7 +63,7 @@ def inference_program(word_dict):
 
 
 def train_program(prediction):
-    label = fluid.data(name="label", shape=[-1, 1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -79,16 +81,16 @@ def train(use_cuda, params_dirname):
 
     print("Reading training data....")
     if args.enable_ce:
-        train_reader = fluid.io.batch(
+        train_reader = paddle.batch(
             paddle.dataset.imdb.train(word_dict), batch_size=BATCH_SIZE)
     else:
-        train_reader = fluid.io.batch(
+        train_reader = paddle.batch(
             paddle.reader.shuffle(
                 paddle.dataset.imdb.train(word_dict), buf_size=25000),
             batch_size=BATCH_SIZE)
 
     print("Reading testing data....")
-    test_reader = fluid.io.batch(
+    test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
     feed_order = ['words', 'label']
@@ -200,15 +202,11 @@ def infer(use_cuda, params_dirname=None):
 
         UNK = word_dict['<unk>']
         lod = []
-        base_shape = []
-
         for c in reviews:
-            re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-            lod = np.concatenate([lod, re], axis=0)
-            base_shape.insert(-1, re.shape[0])
+            lod.append([np.int64(word_dict.get(words, UNK)) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
 
-        base_shape = [base_shape]
-        lod = np.array(lod).astype('int64')
         tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
         assert feed_target_names[0] == "words"
         results = exe.run(

06.understand_sentiment/train_stacked_lstm.py

@@ -46,7 +46,8 @@ def parse_args():
 def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
     assert stacked_num % 2 == 1
 
-    emb = fluid.embedding(input=data, size=[input_dim, emb_dim], is_sparse=True)
+    emb = fluid.layers.embedding(
+        input=data, size=[input_dim, emb_dim], is_sparse=True)
 
     fc1 = fluid.layers.fc(input=emb, size=hid_dim)
     lstm1, cell1 = fluid.layers.dynamic_lstm(input=fc1, size=hid_dim)
@@ -68,7 +69,8 @@ def stacked_lstm_net(data, input_dim, class_dim, emb_dim, hid_dim, stacked_num):
 
 
 def inference_program(word_dict):
-    data = fluid.data(name="words", shape=[-1], dtype="int64", lod_level=1)
+    data = fluid.layers.data(
+        name="words", shape=[1], dtype="int64", lod_level=1)
 
     dict_dim = len(word_dict)
     net = stacked_lstm_net(data, dict_dim, CLASS_DIM, EMB_DIM, HID_DIM,
@@ -78,7 +80,7 @@ def inference_program(word_dict):
 
 def train_program(prediction):
     # prediction = inference_program(word_dict)
-    label = fluid.data(name="label", shape=[-1, 1], dtype="int64")
+    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
     accuracy = fluid.layers.accuracy(input=prediction, label=label)
@@ -98,16 +100,16 @@ def train(use_cuda, params_dirname):
     print("Reading training data....")
 
     if args.enable_ce:
-        train_reader = fluid.io.batch(
+        train_reader = paddle.batch(
             paddle.dataset.imdb.train(word_dict), batch_size=BATCH_SIZE)
     else:
-        train_reader = fluid.io.batch(
+        train_reader = paddle.batch(
             paddle.reader.shuffle(
                 paddle.dataset.imdb.train(word_dict), buf_size=25000),
             batch_size=BATCH_SIZE)
 
     print("Reading testing data....")
-    test_reader = fluid.io.batch(
+    test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
     feed_order = ['words', 'label']
@@ -221,15 +223,11 @@ def infer(use_cuda, params_dirname=None):
 
         UNK = word_dict['<unk>']
         lod = []
-        base_shape = []
-
         for c in reviews:
-            re = np.array([np.int64(word_dict.get(words, UNK)) for words in c])
-            lod = np.concatenate([lod, re], axis=0)
-            base_shape.insert(-1, re.shape[0])
+            lod.append([np.int64(word_dict.get(words, UNK)) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
 
-        base_shape = [base_shape]
-        lod = np.array(lod).astype('int64')
         tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
         assert feed_target_names[0] == "words"
         results = exe.run(