我应用了Predicting the next word using the LSTM ptb model tensorflow example中描述的相同方法来使用tensorflow LSTM并预测我的测试文档中的下一个单词 . 但是，LSTM总是在每次运行时为每个序列预测相同的单词 .
更具体地说，我添加了这些行：
class PTBModel(object):
"""The PTB model."""
def __init__(self, is_training, config):
# General definition of LSTM (unrolled)
# identical to tensorflow example ...
# omitted for brevity ...
outputs = []
state = self._initial_state
with tf.variable_scope("RNN"):
for time_step in range(num_steps):
if time_step > 0: tf.get_variable_scope().reuse_variables()
(cell_output, state) = cell(inputs[:, time_step, :], state)
outputs.append(cell_output)
output = tf.reshape(tf.concat(1, outputs), [-1, size])
softmax_w = tf.get_variable("softmax_w", [size, vocab_size])
softmax_b = tf.get_variable("softmax_b", [vocab_size])
logits = tf.matmul(output, softmax_w) + softmax_b
#Storing the probabilities and logits
self.probabilities = probabilities = tf.nn.softmax(logits)
self.logits = logits
然后以下列方式更改run_epoch：
def run_epoch(session, m, data, eval_op, verbose=True, is_training = True):
"""Runs the model on the given data."""
# first part of function unchanged from example
for step, (x, y) in enumerate(reader.ptb_iterator(data, m.batch_size,
m.num_steps)):
# evaluate proobability and logit tensors too:
cost, state, probs, logits, _ = session.run([m.cost, m.final_state, m.probabilities, m.logits, eval_op],
{m.input_data: x,
m.targets: y,
m.initial_state: state})
costs += cost
iters += m.num_steps
if not is_training:
chosen_word = np.argmax(probs, 1)
print(chosen_word[-1])
return np.exp(costs / iters)
我想预测测试数据集中的下一个单词 . 当我运行这个程序时，它总是返回相同的索引（大多数时候是<eos>的索引） . 任何帮助表示赞赏 .
1 回答
也许SoftMax的温度太冷了？