源自github用户yanmengqi:
使用paddlepaddle进行机器翻译训练,使用的语料是中英文语料,已分词已对齐
引用训练集直接更改的.cache/paddle/wmt/wmt14.tgz里的内容,其他代码参数未修改,在开始程序后出现AssertionError错误.
报错的信息如下:
I0201 20:07:38.419838 13473 Util.cpp:166] commandline: --use_gpu=False --trainer_count=2 I0201 20:07:38.691911 13473 GradientMachine.cpp:94] Initing parameters.. I0201 20:07:41.030560 13473 GradientMachine.cpp:101] Init parameters done. Traceback (most recent call last): File "train.py", line 163, in <module> main() File "train.py", line 159, in main train() File "train.py", line 154, in train feeding=feeding) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/trainer.py", line 162, in train for batch_id, data_batch in enumerate(reader()): File "/usr/local/lib/python2.7/dist-packages/paddle/v2/minibatch.py", line 33, in batch_reader for instance in r: File "/usr/local/lib/python2.7/dist-packages/paddle/v2/reader/decorator.py", line 70, in data_reader for e in reader(): File "/home/yanmengqi/桌面/mt_with_external_memory/data_utils.py", line 12, in new_reader for ins in reader(): File "/usr/local/lib/python2.7/dist-packages/paddle/v2/dataset/wmt14.py", line 73, in reader src_dict, trg_dict = __read_to_dict__(tar_file, dict_size) File "/usr/local/lib/python2.7/dist-packages/paddle/v2/dataset/wmt14.py", line 60, in __read_to_dict__ assert len(names) == 1 AssertionError