如果您在训练之间重置指标,则会出现此行为。
如果训练指标是两个不同的操作,则它们不会聚合验证指标。我将举例说明如何保持这些指标不同以及如何仅重置其中一个指标。
玩具示例:
logits = tf.placeholder(tf.int64, [2,3])
labels = tf.Variable([[0, 1, 0], [1, 0, 1]])
#create two different ops
with tf.name_scope('train'):
train_acc, train_acc_op = tf.metrics.accuracy(labels=tf.argmax(labels, 1),
predictions=tf.argmax(logits,1))
with tf.name_scope('valid'):
valid_acc, valid_acc_op = tf.metrics.accuracy(labels=tf.argmax(labels, 1),
predictions=tf.argmax(logits,1))
训练:
#initialize the local variables has it holds the variables used for metrics calculation.
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
# initial state
print(sess.run(train_acc, {logits:[[0,1,0],[1,0,1]]}))
print(sess.run(valid_acc, {logits:[[0,1,0],[1,0,1]]}))
#0.0
#0.0
初始状态是0.0
正如预期的那样。
现在调用训练操作指标:
#training loop
for _ in range(10):
sess.run(train_acc_op, {logits:[[0,1,0],[1,0,1]]})
print(sess.run(train_acc, {logits:[[0,1,0],[1,0,1]]}))
# 1.0
print(sess.run(valid_acc, {logits:[[0,1,0],[1,0,1]]}))
# 0.0
仅更新了训练准确率,而有效准确率仍然存在0.0
。调用有效的操作:
for _ in range(10):
sess.run(valid_acc_op, {logits:[[0,1,0],[0,1,0]]})
print(sess.run(valid_acc, {logits:[[0,1,0],[1,0,1]]}))
#0.5
print(sess.run(train_acc, {logits:[[0,1,0],[1,0,1]]}))
#1.0
这里,有效精度更新为新值,而训练精度保持不变。
让我们只重置验证操作:
stream_vars_valid = [v for v in tf.local_variables() if 'valid/' in v.name]
sess.run(tf.variables_initializer(stream_vars_valid))
print(sess.run(valid_acc, {logits:[[0,1,0],[1,0,1]]}))
#0.0
print(sess.run(train_acc, {logits:[[0,1,0],[1,0,1]]}))
#1.0
有效精度重置为零,而训练精度保持不变。