Tensorflow Python：无法使用 tf.train.Saver() 恢复变量：错误::未找到：在检查点中未找到关键变量/亚当

Question

I am confused. I don't know what's happening. I cannot restore my checkpoints. The weird thing is sometimes I can restore them then after 1-2 hours I can't.

I use this code to save

saver = tf.train.Saver()
with tf.Session() as sess:
    .....
    #sess.run(init)
    saver.restore(sess, 'models/my_model_2.ckpt')

I use this code to restore

with tf.Session() as sess:
    #sess.run(init)
    saver.restore(sess, 'models/my_model_2.ckpt')
    ......

Error

2020-10-15 01:10:35.195112: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at 
save_restore_v2_ops.cc:184 : Not found: Key Variable/Adam not found in checkpoint

If you don't know how to fix this, just tell me if there is another way to restore variables. Also, my program is a CNN with neural network at the end. Im using tensor flow for everything.

Answer 1

change your optimizer from Adam to other? i don't know why,but i solve this problem by this way.