PaddlePaddle在使用N-gram神经网络训练时出现ids[i]>row_number的错误

原创于 2019-02-26 09:48:17 发布 · 989 阅读

CC 4.0 BY-SA版权

本文描述了在使用N-gram神经网络训练PTB数据集时遇到的错误，即'ids[i]>row_number'的问题，并提供了详细的解决方案，包括正确的代码示例和对fluid.layers.embedding接口的正确使用说明。

关键字：词向量，N-gram神经网络
问题描述：在使用N-gram神经网络训练PTB数据集时，手动设置了字典大小，最后在启动训练的时候出现错误，错误提示ids[i]>row_number。
报错信息：

<ipython-input-6-daf8837e1db3> in train(use_cuda, train_program, params_dirname)
     37         num_epochs=1,
     38         event_handler=event_handler,
---> 39         feed_order=['firstw', 'secondw', 'thirdw', 'fourthw', 'nextw'])

/usr/local/lib/python3.5/dist-packages/paddle/fluid/contrib/trainer.py in train(self, num_epochs, event_handler, reader, feed_order)
    403         else:
    404             self._train_by_executor(num_epochs, event_handler, reader,
--> 405                                     feed_order)
    406 
    407     def test(self, reader, feed_order):

/usr/local/lib/python3.5/dist-packages/paddle/fluid/contrib/trainer.py in _train_by_executor(self, num_epochs, event_handler, reader, feed_order)
    481             exe = executor.Executor(self.place)
    482             reader = feeder.decorate_reader(reader, multi_devices=False)
--> 483             self._train_by_any_executor(event_handler, exe, num_epochs, reader)
    484 
    485     def _train_by_any_executor(self, event_handler, exe, num_epochs, reader):

/usr/local/lib/python3.5/dist-packages/paddle/fluid/contrib/trainer.py in _train_by_any_executor(self, event_handler, exe, num_epochs, reader)
    510                                       fetch_list=[
    511                                           var.name
--> 512                                           for var in self.train_func_outputs
    513                                       ])
    514                 else:

/usr/local/lib/python3.5/dist-packages/paddle/fluid/executor.py in run(self, program, feed, fetch_list, feed_var_name, fetch_var_name, scope, return_numpy, use_program_cache)
    468 
    469         self._feed_data(program, feed, feed_var_name, scope)
--> 470         self.executor.run(program.desc, scope, 0, True, True)
    471         outs = self._fetch_data(fetch_list, fetch_var_name, scope)
    472         if return_numpy:

EnforceNotMet: Enforce failed. Expected ids[i] < row_number, but received ids[i]:2073 >= row_number:32.
 at [/paddle/paddle/fluid/operators/lookup_table_op.h:59]
PaddlePaddle Call Stacks:

问题复现：在是使用fluid.layers.embedding接口构造N-gram神经网络，其中设置size参数的值为[32, 32]，在执行训练的时候就会报该错误。错误代码如下：

dict_size = 32
embed_first = fluid.layers.embedding(
    input=first_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_second = fluid.layers.embedding(
    input=second_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_third = fluid.layers.embedding(
    input=third_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_fourth = fluid.layers.embedding(
    input=fourth_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')

解决问题：fluid.layers.embedding接口的size参数的值应该是[数据集的字典大小, 词向量大小]。所以第一个参数的值应该是字典的大小，所以要根据字典的实际大小来进行赋值。正确代码如下：

word_dict = paddle.dataset.imikolov.build_dict()
dict_size = len(word_dict)

embed_first = fluid.layers.embedding(
    input=first_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_second = fluid.layers.embedding(
    input=second_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_third = fluid.layers.embedding(
    input=third_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')
embed_fourth = fluid.layers.embedding(
    input=fourth_word,
    size=[dict_size, EMBED_SIZE],
    dtype='float32',
    is_sparse=is_sparse,
    param_attr='shared_w')