我的问题和问题在两段代码下面说明。
def loss(labels, logits, sequence_lengths, label_lengths, logit_lengths):
scores = []
for i in xrange(runner.batch_size):
sequence_length = sequence_lengths[i]
for j in xrange(length):
label_length = label_lengths[i, j]
logit_length = logit_lengths[i, j]
# get top k indices <==> argmax_k(labels[i, j, 0, :], label_length)
top_labels = np.argpartition(labels[i, j, 0, :], -label_length)[-label_length:]
top_logits = np.argpartition(logits[i, j, 0, :], -logit_length)[-logit_length:]
scores.append(edit_distance(top_labels, top_logits))
return np.mean(scores)
# Levenshtein distance
def edit_distance(s, t):
n = s.size
m = t.size
d = np.zeros((n+1, m+1))
d[:, 0] = np.arrange(n+1)
d[0, :] = np.arrange(n+1)
for j in xrange(1, m+1):
for i in xrange(1, n+1):
if s[i] == t[j]:
d[i, j] = d[i-1, j-1]
else:
d[i, j] = min(d[i-1, j] + 1,
d[i, j-1] + 1,
d[i-1, j-1] + 1)
return d[m, n]
我试图压扁我的代码，以便一切都在一个地方发生。如果有混淆/混淆点，请告诉我。
sequence_lengths_placeholder = tf.placeholder(tf.int64, shape=(batch_size))
labels_placeholder = tf.placeholder(tf.float32, shape=(batch_size, max_feature_length, label_size))
label_lengths_placeholder = tf.placeholder(tf.int64, shape=(batch_size, max_feature_length))
loss_placeholder = tf.placeholder(tf.float32, shape=(1))
logit_W = tf.Variable(tf.zeros([lstm_units, label_size]))
logit_b = tf.Variable(tf.zeros([label_size]))
length_W = tf.Variable(tf.zeros([lstm_units, max_length]))
length_b = tf.Variable(tf.zeros([max_length]))
lstm = rnn_cell.BasicLSTMCell(lstm_units)
stacked_lstm = rnn_cell.MultiRNNCell([lstm] * layer_count)
rnn_out, state = rnn.rnn(stacked_lstm, features, dtype=tf.float32, sequence_length=sequence_lengths_placeholder)
logits = tf.concat(1, [tf.reshape(tf.matmul(t, logit_W) + logit_b, [batch_size, 1, 2, label_size]) for t in rnn_out])
logit_lengths = tf.concat(1, [tf.reshape(tf.matmul(t, length_W) + length_b, [batch_size, 1, max_length]) for t in rnn_out])
optimizer = tf.train.AdamOptimizer(learning_rate)
global_step = tf.Variable(0, name='global_step', trainable=False)
train_op = optimizer.minimize(loss_placeholder, global_step=global_step)
...
...
# Inside training loop
np_labels, np_logits, sequence_lengths, label_lengths, logit_lengths = sess.run([labels_placeholder, logits, sequence_lengths_placeholder, label_lengths_placeholder, logit_lengths], feed_dict=feed_dict)
loss = loss(np_labels, np_logits, sequence_lengths, label_lengths, logit_lengths)
_ = sess.run([train_op], feed_dict={loss_placeholder: loss})
问题是这会返回错误：
File "runner.py", line 63, in <module>
train_op = optimizer.minimize(loss_placeholder, global_step=global_step)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 188, in minimize
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 277, in apply_gradients
(grads_and_vars,))
ValueError: No gradients provided for any variable: <all my variables>
所以我认为这是TensorFlow抱怨它无法计算我的损失的梯度，因为损失是由超出TF范围的numpy执行的。
很自然地解决这个问题，我会尝试在TensorFlow中实现它。问题是，我的logit_lengths和label_lengths都是张量，所以当我尝试访问单个元素时，我返回了一个Tensor of shape []。当我尝试使用tf.nn.top_k() Int作为k参数时，这是一个问题。
另一个问题是我的label_lengths是一个占位符，因为我的loss值需要在optimizer.minimize(loss)调用之前定义，我还会收到一个错误，指出值需要为占位符传递。
我只是想知道如何尝试实现这种损失功能。或者，如果我遗漏了一些明显的东西。
编辑：经过一些further reading我看到通常像我描述的那样的损失被用于验证和培训中，在与真正的损失相同的地方最小化的代理损失是用过的。有谁知道代理损失用于像我这样的基于编辑距离的场景？
答案 0 :(得分：1)
我要做的第一件事是使用tensorflow而不是numpy来计算损失。这将允许tensorflow为您计算渐变，因此您将能够反向传播，这意味着您可以最大限度地减少损失。
核心库中有tf.edit_distance（https://www.tensorflow.org/api_docs/python/tf/edit_distance）函数。
很自然地解决这个问题，我会尝试在TensorFlow中实现它。问题是，我的logit_lengths和label_lengths都是张量，所以当我尝试访问单个元素时，我返回了一个Tensor of shape []。当我尝试使用tf.nn.top_k（）时，这是一个问题，它将Int作为其k参数。
您能否提供更多详细信息，为什么会出现问题？