Created by: sucuicong

模型信息    1）模型名称 Deep Attention Matching Network 2）使用数据集名称 ubuntu 3）使用算法名称 Deep Attention Matching Network 4）模型链接 https://github.com/PaddlePaddle/models/tree/release/1.5/PaddleNLP/dialogue_model_toolkit/deep_attention_matching

• 复现信息：如为报错，请给出复现环境、复现步骤

$ cd deep_attention_matching && python main.py \
  --do_train True \
  --data_path ./data/ubuntu/data_small.pkl \
  --save_path ./model_files/ubuntu \
  --vocab_size 434512 \
  --_EOS_ 28270 \
  --batch_size 16

Traceback (most recent call last):
  File "main.py", line 492, in <module>
    train(args)
  File "main.py", line 343, in train
    global_step, last_cost = train_with_feed(global_step)
  File "main.py", line 249, in train_with_feed
    cost = train_exe.run(feed=feed_list, fetch_list=[loss.name])
  File "/opt/conda/envs/python27-paddle120-env/lib/python2.7/site-packages/paddle/fluid/parallel_executor.py", line 280, in run
    return_numpy=return_numpy)
  File "/opt/conda/envs/python27-paddle120-env/lib/python2.7/site-packages/paddle/fluid/executor.py", line 665, in run
    return_numpy=return_numpy)
  File "/opt/conda/envs/python27-paddle120-env/lib/python2.7/site-packages/paddle/fluid/executor.py", line 507, in _run_parallel
    "Feed a list of tensor, the list should be the same size as places"
ValueError: Feed a list of tensor, the list should be the same size as places