TL;DR 尝试使用 tensorflow 构建用于序列标记的双向 RNN。
目标是输入“我喜欢纽约”并产生输出“OO LOC_START LOC”
该图编译并运行,但损失在 1 或 2 个批次后变为 NaN。我知道这可能是学习率的问题,但改变学习率似乎没有影响。目前使用 AdamOptimizer。
任何帮助,将不胜感激。
这是我的代码:
代码:
# The input and output: a sequence of words, embedded, and a sequence of word classifications, one-hot
self.input_x = tf.placeholder(tf.float32, [None, n_sequence_length, n_embedding_dim], name="input_x")
self.input_y = tf.placeholder(tf.float32, [None, n_sequence_length, n_output_classes], name="input_y")
# New shape: [sequence_length, batch_size (None), embedding_dim]
inputs = tf.transpose(self.input_x, [1, 0, 2])
# New shape: [sequence_length * batch_size (None), embedding_dim]
inputs = tf.reshape(inputs, [-1, n_embedding_dim])
# Define weights
w_hidden = tf.Variable(tf.random_normal([n_embedding_dim, 2 * n_hidden_states]))
b_hidden = tf.Variable(tf.random_normal([2 * n_hidden_states]))
w_out = tf.Variable(tf.random_normal([2 * n_hidden_states, n_output_classes]))
b_out = tf.Variable(tf.random_normal([n_output_classes]))
# Linear activation for the input; this will make it fit to the hidden size
inputs = tf.nn.xw_plus_b(inputs, w_hidden, b_hidden)
# Split up the batches into a Python list
inputs = tf.split(0, n_sequence_length, inputs)
# Now we define our cell. It takes one word as input, a vector of embedding_size length
cell_forward = rnn_cell.BasicLSTMCell(n_hidden_states, forget_bias=0.0)
cell_backward = rnn_cell.BasicLSTMCell(n_hidden_states, forget_bias=0.0)
# And we add a Dropout Wrapper as appropriate
if is_training and prob_keep < 1:
cell_forward = rnn_cell.DropoutWrapper(cell_forward, output_keep_prob=prob_keep)
cell_backward = rnn_cell.DropoutWrapper(cell_backward, output_keep_prob=prob_keep)
# And we make it a few layers deep
cell_forward_multi = rnn_cell.MultiRNNCell([cell_forward] * n_layers)
cell_backward_multi = rnn_cell.MultiRNNCell([cell_backward] * n_layers)
# returns outputs = a list T of tensors [batch, 2*hidden]
outputs = rnn.bidirectional_rnn(cell_forward_multi, cell_backward_multi, inputs, dtype=dtypes.float32)
# [sequence, batch, 2*hidden]
outputs = tf.pack(outputs)
# [batch, sequence, 2*hidden]
outputs = tf.transpose(outputs, [1, 0, 2])
# [batch * sequence, 2 * hidden]
outputs = tf.reshape(outputs, [-1, 2 * n_hidden_states])
# [batch * sequence, output_classes]
self.scores = tf.nn.xw_plus_b(outputs, w_out, b_out)
# [batch * sequence, output_classes]
inputs_y = tf.reshape(self.input_y, [-1, n_output_classes])
# [batch * sequence]
self.predictions = tf.argmax(self.scores, 1, name="predictions")
# Now calculate the cross-entropy
losses = tf.nn.softmax_cross_entropy_with_logits(self.scores, inputs_y)
self.loss = tf.reduce_mean(losses, name="loss")
if not is_training:
return
# Training
self.train_op = tf.train.AdamOptimizer(1e-4).minimize(self.loss)
# Evaluate model
correct_pred = tf.equal(self.predictions, tf.argmax(inputs_y, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32), name="accuracy")