update 1.7_api for PaddleTextGEN lexical_analysis sentiment_classification (#4304)

* update 1.7_api for PaddleTextGEN lexical_analysis sentiment_classification

PaddleNLP/PaddleTextGEN/seq2seq/README.md

-运行本目录下的范例模型需要安装PaddlePaddle Fluid 1.6版。如果您的 PaddlePaddle 安装版本低于此要求，请按照[安装文档](https://www.paddlepaddle.org.cn/#quick-start)中的说明更新 PaddlePaddle 安装版本。
+运行本目录下的范例模型需要安装PaddlePaddle Fluid 1.7版本。如果您的 PaddlePaddle 安装版本低于此要求，请按照[安装文档](https://www.paddlepaddle.org.cn/#quick-start)中的说明更新 PaddlePaddle 安装版本。
 
 # Sequence to Sequence (Seq2Seq)
 

PaddleNLP/PaddleTextGEN/seq2seq/infer.py

@@ -93,7 +93,7 @@ def infer():
     # clone from default main program and use it as the validation program
     main_program = fluid.default_main_program()
     main_program = main_program.clone(for_test=True)
-    print([param.name for param in main_program.blocks[0].all_parameters()])
+    print([param.name for param in main_program.all_parameters()])
 
     place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace()
     exe = Executor(place)

PaddleNLP/lexical_analysis/README.md

@@ -16,7 +16,7 @@ Lexical Analysis of Chinese，简称 LAC，是一个联合的词法分析模型
 
 #### 1.PaddlePaddle 安装
 
-本项目依赖 PaddlePaddle 1.6.0 及以上版本和PaddleHub 1.0.0及以上版本 ，PaddlePaddle安装请参考官网 [快速安装](http://www.paddlepaddle.org/paddle#quick-start)，PaddleHub安装参考 [PaddleHub](https://github.com/PaddlePaddle/PaddleHub)。
+本项目依赖 PaddlePaddle 1.7 及以上版本和PaddleHub 1.0.0及以上版本 ，PaddlePaddle安装请参考官网 [快速安装](http://www.paddlepaddle.org/paddle#quick-start)，PaddleHub安装参考 [PaddleHub](https://github.com/PaddlePaddle/PaddleHub)。
 
 > Warning: GPU 和 CPU 版本的 PaddlePaddle 分别是 paddlepaddle-gpu 和 paddlepaddle，请安装时注意区别。
 

PaddleNLP/lexical_analysis/creator.py

@@ -35,9 +35,9 @@ def create_model(args, vocab_size, num_labels, mode='train'):
     """create lac model"""
 
     # model's input data
-    words = fluid.data(name='words', shape=[-1, 1], dtype='int64', lod_level=1)
+    words = fluid.data(name='words', shape=[None, 1], dtype='int64', lod_level=1)
     targets = fluid.data(
-        name='targets', shape=[-1, 1], dtype='int64', lod_level=1)
+        name='targets', shape=[None, 1], dtype='int64', lod_level=1)
 
     # for inference process
     if mode == 'infer':
@@ -88,9 +88,10 @@ def create_pyreader(args,
                     return_reader=False,
                     mode='train'):
     # init reader
+    device_count = len(fluid.cuda_places()) if args.use_cuda else len(fluid.cpu_places())
 
     if model == 'lac':
-        pyreader = fluid.io.PyReader(
+        pyreader = fluid.io.DataLoader.from_generator(
             feed_list=feed_list,
             capacity=50,
             use_double_buffer=True,
@@ -101,19 +102,19 @@ def create_pyreader(args,
 
         # create lac pyreader
         if mode == 'train':
-            pyreader.decorate_sample_list_generator(
+            pyreader.set_sample_list_generator(
                 fluid.io.batch(
                     fluid.io.shuffle(
                         reader.file_reader(file_name),
                         buf_size=args.traindata_shuffle_buffer),
-                    batch_size=args.batch_size),
+                    batch_size=args.batch_size/device_count),
                 places=place)
         else:
-            pyreader.decorate_sample_list_generator(
+            pyreader.set_sample_list_generator(
                 fluid.io.batch(
                     reader.file_reader(
                         file_name, mode=mode),
-                    batch_size=args.batch_size),
+                    batch_size=args.batch_size/device_count),
                 places=place)
 
     elif model == 'ernie':
@@ -162,19 +163,19 @@ def create_ernie_model(args, ernie_config):
     # ERNIE's input data
 
     src_ids = fluid.data(
-        name='src_ids', shape=[-1, args.max_seq_len, 1], dtype='int64')
+        name='src_ids', shape=[None, args.max_seq_len, 1], dtype='int64')
     sent_ids = fluid.data(
-        name='sent_ids', shape=[-1, args.max_seq_len, 1], dtype='int64')
+        name='sent_ids', shape=[None, args.max_seq_len, 1], dtype='int64')
     pos_ids = fluid.data(
-        name='pos_ids', shape=[-1, args.max_seq_len, 1], dtype='int64')
+        name='pos_ids', shape=[None, args.max_seq_len, 1], dtype='int64')
     input_mask = fluid.data(
-        name='input_mask', shape=[-1, args.max_seq_len, 1], dtype='float32')
+        name='input_mask', shape=[None, args.max_seq_len, 1], dtype='float32')
 
     padded_labels = fluid.data(
-        name='padded_labels', shape=[-1, args.max_seq_len, 1], dtype='int64')
+        name='padded_labels', shape=[None, args.max_seq_len, 1], dtype='int64')
 
     seq_lens = fluid.data(
-        name='seq_lens', shape=[-1], dtype='int64', lod_level=0)
+        name='seq_lens', shape=[None], dtype='int64', lod_level=0)
 
     squeeze_labels = fluid.layers.squeeze(padded_labels, axes=[-1])
 

PaddleNLP/sentiment_classification/README.md

@@ -29,7 +29,7 @@
 
 1. PaddlePaddle 安装
 
-   本项目依赖于 PaddlePaddle Fluid 1.6 及以上版本，请参考 [安装指南](http://www.paddlepaddle.org/#quick-start) 进行安装
+   本项目依赖于 PaddlePaddle Fluid 1.7 及以上版本，请参考 [安装指南](http://www.paddlepaddle.org/#quick-start) 进行安装
 
 2. 代码安装
 

PaddleNLP/sentiment_classification/inference_model.py

@@ -107,12 +107,12 @@ def test_inference_model(args):
         params_filename="params.pdparams")
 
     infer_data_generator = processor.data_generator(
-        batch_size=args.batch_size,
+        batch_size=args.batch_size/dev_count,
         phase="infer",
         epoch=1,
         shuffle=False)
     
-    infer_pyreader.decorate_sample_list_generator(infer_data_generator)
+    infer_pyreader.set_sample_list_generator(infer_data_generator)
     inference(exe, test_prog, infer_pyreader,
         [probs.name], "infer")
 

PaddleNLP/sentiment_classification/inference_model_ernie.py

@@ -129,7 +129,7 @@ def test_inference_model(args):
     assert (args.inference_model_dir)
     infer_data_generator = reader.data_generator(
         input_file=args.test_set,
-        batch_size=args.batch_size,
+        batch_size=args.batch_size/dev_count,
         phase="infer",
         epoch=1,
         shuffle=False)
@@ -140,7 +140,7 @@ def test_inference_model(args):
         model_filename="model.pdmodel",
         params_filename="params.pdparams")
 
-    infer_pyreader.decorate_batch_generator(infer_data_generator)
+    infer_pyreader.set_batch_generator(infer_data_generator)
     inference(exe, test_prog, infer_pyreader,
         [probs.name], "infer")
 

PaddleNLP/sentiment_classification/run_classifier.py

@@ -39,14 +39,14 @@ def create_model(args,
     Create Model for sentiment classification
     """
     
-    data = fluid.layers.data(
-            name="src_ids", shape=[-1, args.max_seq_len], dtype='int64')
-    label = fluid.layers.data(
-            name="label", shape=[-1, 1], dtype="int64")
-    seq_len = fluid.layers.data(
-            name="seq_len", shape=[-1], dtype="int64")
+    data = fluid.data(
+            name="src_ids", shape=[None, args.max_seq_len], dtype='int64')
+    label = fluid.data(
+            name="label", shape=[None, 1], dtype="int64")
+    seq_len = fluid.data(
+            name="seq_len", shape=[None], dtype="int64")
     
-    data_reader = fluid.io.PyReader(feed_list=[data, label, seq_len], 
+    data_reader = fluid.io.DataLoader.from_generator(feed_list=[data, label, seq_len], 
         capacity=4, iterable=False)
 
     if args.model_type == "bilstm_net":
@@ -151,7 +151,7 @@ def main(args):
 
     if args.do_train:
         train_data_generator = processor.data_generator(
-            batch_size=args.batch_size,
+            batch_size=args.batch_size/dev_count,
             phase='train',
             epoch=args.epoch,
             shuffle=True)
@@ -187,7 +187,7 @@ def main(args):
 
     if args.do_val:
         test_data_generator = processor.data_generator(
-            batch_size=args.batch_size,
+            batch_size=args.batch_size/dev_count,
             phase='dev',
             epoch=1,
             shuffle=False)
@@ -204,7 +204,7 @@ def main(args):
 
     if args.do_infer:
         infer_data_generator = processor.data_generator(
-            batch_size=args.batch_size,
+            batch_size=args.batch_size/dev_count,
             phase='infer',
             epoch=1,
             shuffle=False)
@@ -238,15 +238,15 @@ def main(args):
 
     if args.do_train:
         train_exe = exe
-        train_reader.decorate_sample_list_generator(train_data_generator)
+        train_reader.set_sample_list_generator(train_data_generator)
     else:
         train_exe = None
     if args.do_val:
         test_exe = exe
-        test_reader.decorate_sample_list_generator(test_data_generator)
+        test_reader.set_sample_list_generator(test_data_generator)
     if args.do_infer:
         test_exe = exe
-        infer_reader.decorate_sample_list_generator(infer_data_generator)
+        infer_reader.set_sample_list_generator(infer_data_generator)
 
     if args.do_train:
         train_reader.start()

PaddleNLP/sentiment_classification/run_ernie_classifier.py

@@ -37,18 +37,18 @@ from config import PDConfig
 from utils import init_checkpoint
 
 def ernie_pyreader(args, pyreader_name):
-    src_ids = fluid.layers.data(
-        name="src_ids", shape=[-1, args.max_seq_len, 1], dtype="int64")
-    sent_ids = fluid.layers.data(
-        name="sent_ids", shape=[-1, args.max_seq_len, 1], dtype="int64")
-    pos_ids = fluid.layers.data(
-        name="pos_ids", shape=[-1, args.max_seq_len, 1], dtype="int64")
-    input_mask = fluid.layers.data(
-        name="input_mask", shape=[-1, args.max_seq_len, 1], dtype="float32")
-    labels = fluid.layers.data(
-        name="labels", shape=[-1, 1], dtype="int64")
-    seq_lens = fluid.layers.data(
-        name="seq_lens", shape=[-1], dtype="int64")
+    src_ids = fluid.data(
+        name="src_ids", shape=[None, args.max_seq_len, 1], dtype="int64")
+    sent_ids = fluid.data(
+        name="sent_ids", shape=[None, args.max_seq_len, 1], dtype="int64")
+    pos_ids = fluid.data(
+        name="pos_ids", shape=[None, args.max_seq_len, 1], dtype="int64")
+    input_mask = fluid.data(
+        name="input_mask", shape=[None, args.max_seq_len, 1], dtype="float32")
+    labels = fluid.data(
+        name="labels", shape=[None, 1], dtype="int64")
+    seq_lens = fluid.data(
+        name="seq_lens", shape=[None], dtype="int64")
     
     pyreader = fluid.io.DataLoader.from_generator(
         feed_list=[src_ids, sent_ids, pos_ids, input_mask, labels, seq_lens],