update docs (#5049)

* add paddle.models api reference docs

* update docs

* update docs

* update docs

* tmp

* update docs

* update docs

* update docs

* update docs

* update docs

* update docs

PaddleNLP/examples/text_classification/rnn/README.md

@@ -98,20 +98,20 @@ wget https://paddlenlp.bj.bcebos.com/data/senta_word_dict.txt
 CPU 启动：
 
 ```shell
-python train.py --vocab_path='./senta_word_dict.txt' --use_gpu=False --network_name=bilstm --lr=5e-4 --batch_size=64 --epochs=5 --save_dir='./checkpoints'
+python train.py --vocab_path='./senta_word_dict.txt' --use_gpu=False --network=bilstm --lr=5e-4 --batch_size=64 --epochs=5 --save_dir='./checkpoints'
 ```
 
 GPU 启动：
 
 ```shell
-# CUDA_VISIBLE_DEVICES=0 python train.py --vocab_path='./senta_word_dict.txt' --use_gpu=True --network_name=bilstm --lr=5e-4 --batch_size=64 --epochs=5 --save_dir='./checkpoints'
+# CUDA_VISIBLE_DEVICES=0 python train.py --vocab_path='./senta_word_dict.txt' --use_gpu=True --network=bilstm --lr=5e-4 --batch_size=64 --epochs=5 --save_dir='./checkpoints'
 ```
 
 以上参数表示：
 
 * `vocab_path`: 词汇表文件路径。
 * `use_gpu`: 是否使用GPU进行训练， 默认为`False`。
-* `network_name`: 模型网络名称，默认为`bilstm_attn`， 可更换为bilstm, bigru, birnn，bow，lstm，rnn，gru，bilstm_attn，textcnn等。
+* `network`: 模型网络名称，默认为`bilstm_attn`， 可更换为bilstm, bigru, birnn，bow，lstm，rnn，gru，bilstm_attn，textcnn等。
 * `lr`: 学习率， 默认为5e-4。
 * `batch_size`: 运行一个batch大小，默认为64。
 * `epochs`: 训练轮次，默认为5。
@@ -140,13 +140,13 @@ checkpoints/
 CPU启动：
 
 ```shell
-python predict.py --vocab_path='./senta_word_dict.txt' --use_gpu=False --network_name=bilstm --params_path=checkpoints/final.pdparams
+python predict.py --vocab_path='./senta_word_dict.txt' --use_gpu=False --network=bilstm --params_path=checkpoints/final.pdparams
 ```
 
 GPU启动：
 
 ```shell
-CUDA_VISIBLE_DEVICES=0 python predict.py --vocab_path='./senta_word_dict.txt' --use_gpu=True --network_name=bilstm --params_path='./checkpoints/final.pdparams'
+CUDA_VISIBLE_DEVICES=0 python predict.py --vocab_path='./senta_word_dict.txt' --use_gpu=True --network=bilstm --params_path='./checkpoints/final.pdparams'
 ```
 
 将待预测数据分词完毕后，如以下示例：

PaddleNLP/examples/text_classification/rnn/train.py

@@ -17,14 +17,15 @@ import os
 
 import paddle
 import paddlenlp as ppnlp
+from paddlenlp.data import Stack, Tuple, Pad
 from paddlenlp.datasets import ChnSentiCorp
 
-from utils import load_vocab, generate_batch, convert_example
+from utils import load_vocab, convert_example
 
 # yapf: disable
 parser = argparse.ArgumentParser(__doc__)
 parser.add_argument("--epochs", type=int, default=3, help="Number of epoches for training.")
-parser.add_argument('--use_gpu', type=eval, default=True, help="Whether use GPU for training, input should be True or False")
+parser.add_argument('--use_gpu', type=eval, default=False, help="Whether use GPU for training, input should be True or False")
 parser.add_argument("--lr", type=float, default=5e-4, help="Learning rate used to train.")
 parser.add_argument("--save_dir", type=str, default='chekpoints/', help="Directory to save model checkpoint")
 parser.add_argument("--batch_size", type=int, default=64, help="Total examples' number of a batch for training.")
@@ -40,16 +41,21 @@ def create_dataloader(dataset,
                       mode='train',
                       batch_size=1,
                       use_gpu=False,
-                      pad_token_id=0):
+                      pad_token_id=0,
+                      batchify_fn=None):
     """
     Creats dataloader.
 
     Args:
         dataset(obj:`paddle.io.Dataset`): Dataset instance.
+        trans_fn(obj:`callable`, optional, defaults to `None`): function to convert a data sample to input ids, etc.
         mode(obj:`str`, optional, defaults to obj:`train`): If mode is 'train', it will shuffle the dataset randomly.
         batch_size(obj:`int`, optional, defaults to 1): The sample number of a mini-batch.
         use_gpu(obj:`bool`, optional, defaults to obj:`False`): Whether to use gpu to run.
         pad_token_id(obj:`int`, optional, defaults to 0): The pad token index.
+        batchify_fn(obj:`callable`, optional, defaults to `None`): function to generate mini-batch data by merging
+            the sample list, None for only stack each fields of sample in axis
+            0(same as :attr::`np.stack(..., axis=0)`).
 
     Returns:
         dataloader(obj:`paddle.io.DataLoader`): The dataloader which generates batches.
@@ -68,7 +74,7 @@ def create_dataloader(dataset,
         dataset,
         batch_sampler=sampler,
         return_list=True,
-        collate_fn=lambda batch: generate_batch(batch, pad_token_id=pad_token_id))
+        collate_fn=batchify_fn)
     return dataloader
 
 
@@ -99,15 +105,32 @@ if __name__ == "__main__":
         vocab=vocab,
         unk_token_id=vocab['[UNK]'],
         is_test=False)
+    batchify_fn = lambda samples, fn=Tuple(
+        Pad(axis=0, pad_val=vocab['[PAD]']),  # input_ids
+        Stack(dtype="int64"),  # seq len
+        Stack(dtype="int64")  # label
+    ): [data for data in fn(samples)]
     train_loader = create_dataloader(
-        train_ds, trans_fn=trans_fn, batch_size=args.batch_size, mode='train')
+        train_ds,
+        trans_fn=trans_fn,
+        batch_size=args.batch_size,
+        mode='train',
+        use_gpu=args.use_gpu,
+        batchify_fn=batchify_fn)
     dev_loader = create_dataloader(
         dev_ds,
         trans_fn=trans_fn,
         batch_size=args.batch_size,
-        mode='validation')
+        mode='validation',
+        use_gpu=args.use_gpu,
+        batchify_fn=batchify_fn)
     test_loader = create_dataloader(
-        test_ds, trans_fn=trans_fn, batch_size=args.batch_size, mode='test')
+        test_ds,
+        trans_fn=trans_fn,
+        batch_size=args.batch_size,
+        mode='test',
+        use_gpu=args.use_gpu,
+        batchify_fn=batchify_fn)
 
     optimizer = paddle.optimizer.Adam(
         parameters=model.parameters(), learning_rate=args.lr)

PaddleNLP/examples/text_classification/rnn/utils.py

@@ -149,6 +149,7 @@ def convert_example(example, vocab, unk_token_id=1, is_test=False):
         token_id = vocab.get(token, unk_token_id)
         input_ids.append(token_id)
     valid_length = len(input_ids)
+    valid_length = np.array(valid_length, dtype="int64")
 
     if not is_test:
         label = np.array(example[-1], dtype="int64")

PaddleNLP/paddlenlp/models/simnet.py

@@ -51,7 +51,7 @@ class SimNet(nn.Layer):
                 padding_idx=pad_token_id)
         else:
             raise ValueError(
-                "Unknown network: %s, it must be one of bow, lstm, bilstm, gru, bigru, rnn, birnn, bilstm_attn and textcnn."
+                "Unknown network: %s, it must be one of bow, cnn, lstm or gru."
                 % network)
 
     def forward(self, query, title, query_seq_len=None, title_seq_len=None):