在tensorflow中,使用slim.learning.train(TF 0.11),我想从检查点恢复模型并继续训练。该模型有一个成功的培训课程,我想微调它。但是,当我这样做时,TF会因错误而崩溃
Init operations did not make model ready.
我用以下方式进行培训:
tf.contrib.slim.learning.train(
train_op,
train_dir,
log_every_n_steps=FLAGS.log_every_n_steps,
graph=g,
global_step=model.global_step,
number_of_steps=FLAGS.number_of_steps,
init_fn=model.init_fn,
saver=model.saver,
session_config=session_config)
我尝试了3种选择:
关注this doc
model.init_fn = None
with g.as_default():
model_path = tf.train.latest_checkpoint(train_dir)
if model_path:
def restore_fn(sess):
tf.logging.info(
"Restoring SA&T variables from checkpoint file %s",
restore_fn.model_path)
model.saver.restore(sess, restore_fn.model_path)
restore_fn.model_path = model_path
model.init_fn = restore_fn
else:
model.init_fn = None
with g.as_default():
model_path = tf.train.latest_checkpoint(train_dir)
if model_path:
variables_to_restore = tf.contrib.slim.get_variables_to_restore()
model.init_fn = tensorflow.contrib.framework.assign_from_checkpoint_fn(
model_path, variables_to_restore)
else:
model.init_fn = None
答案 0 :(得分:1)
问题解决了。这是因为在模型构建之后直接定义了saver(tf.train.Saver)。
相反,在列车操作定义之后定义它,解决了这个问题。