使用PaddlePaddle搭建一个循环神经网络出现输入的宽度和高度不一致

关键字：记忆单元，循环神经网络
问题描述：使用fluid.layers.DynamicRNN创建一个循环神经网络时，在执行训练的时候出现错误，错误提示：第一个矩阵的宽度必须等于第二个矩阵的高度。
报错信息：

<ipython-input-7-fd22a596e844> in train(use_cuda, train_program, params_dirname)
     41         event_handler=event_handler,
     42         reader=train_reader,
---> 43         feed_order=feed_order)

/opt/conda/envs/py35-paddle1.0.0/lib/python3.5/site-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):

/opt/conda/envs/py35-paddle1.0.0/lib/python3.5/site-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):

/opt/conda/envs/py35-paddle1.0.0/lib/python3.5/site-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:

/opt/conda/envs/py35-paddle1.0.0/lib/python3.5/site-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 x_mat_dims[1] == y_mat_dims[0], but received x_mat_dims[1]:64 != y_mat_dims[0]:128.
First matrix's width must be equal with second matrix's height.  at [/paddle/paddle/fluid/operators/mul_op.cc:59]
PaddlePaddle Call Stacks:

问题复现：使用rnn.block定义一个循环神经网络块，使用rnn.memory定义一个记忆单元，大小设置为128，接着使用fluid.layers.fc创建要给全连接层，大小设置为64。然后在执行训练的时就会出现上述的错误。错误代码如下：

emb = fluid.layers.embedding(input=ipt, size=[input_dim, 128], is_sparse=True)
sentence = fluid.layers.fc(input=emb, size=128, act='tanh')
rnn = fluid.layers.DynamicRNN()
with rnn.block():
    word = rnn.step_input(sentence)
    prev = rnn.memory(shape=[128])
    hidden = fluid.layers.fc(input=[word, prev], size=64, act='relu')
    rnn.update_memory(prev, hidden)
    rnn.output(hidden)
last = fluid.layers.sequence_last_step(rnn())
out = fluid.layers.fc(input=last, size=2, act='softmax')

解决问题：上面的错误是因为记忆单元的大小和全连接层的大小不一致，有些用户会错误理解上一层和下一层的大小是互补相干的，这是错误的，它们的大小必须是一样的。正确代码如下：

emb = fluid.layers.embedding(input=ipt, size=[input_dim, 128], is_sparse=True)
sentence = fluid.layers.fc(input=emb, size=128, act='tanh')
rnn = fluid.layers.DynamicRNN()
with rnn.block():
    word = rnn.step_input(sentence)
    prev = rnn.memory(shape=[128])
    hidden = fluid.layers.fc(input=[word, prev], size=128, act='relu')
    rnn.update_memory(prev, hidden)
    rnn.output(hidden)
last = fluid.layers.sequence_last_step(rnn())
out = fluid.layers.fc(input=last, size=2, act='softmax')

使用PaddlePaddle搭建一个循环神经网络出现输入的宽度和高度不一致

猜你喜欢