-
Notifications
You must be signed in to change notification settings - Fork 628
Open
Description
I am executing the omniglot test with the following command:
python main.py --datasource=omniglot --metatrain_iterations=60000 --meta_batch_size=32 --update_batch_size=1 --update_lr=0.4 --num_updates=1 --logdir=logs/omniglot5way/
However, I am getting the error:
Done initializing, starting training.
Traceback (most recent call last):
File "main.py", line 348, in <module>
main()
File "main.py", line 343, in main
train(model, saver, sess, exp_string, data_generator, resume_itr)
File "main.py", line 160, in train
saver.save(sess, FLAGS.logdir + '/' + exp_string + '/model' + str(itr))
UnboundLocalError: local variable 'itr' referenced before assignment
I inspected the code of main.py and I find that in line 160, saver.save(sess, FLAGS.logdir + '/' + exp_string + '/model' + str(itr)) is being executed outside the for loop but itr variable is a loop iterator variable. Should the save function go inside the for loop?
Metadata
Metadata
Assignees
Labels
No labels