error during training the student model about privacy HOT 6 CLOSED

from privacy.

@npapernot Thanks for the feedback. I change to python 2.7 running on Ubuntu.
However, I face another error here:

(pate17) harry@harry-VirtualBox:~/belajar/privacy/research/pate_2017$ python train_student.py --nb_teachers=100 --dataset=mnist --stdnt_share=5000
2019-03-05 22:22:23.491857: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2
2019-03-05 22:22:23.514316: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Traceback (most recent call last):
File "train_student.py", line 208, in
tf.app.run()
File "/home/harry/anaconda2/envs/pate17/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "train_student.py", line 205, in main
assert train_student(FLAGS.dataset, FLAGS.nb_teachers)
File "train_student.py", line 177, in train_student
stdnt_dataset = prepare_student_data(dataset, nb_teachers, save=True)
File "train_student.py", line 123, in prepare_student_data
teachers_preds = ensemble_preds(dataset, nb_teachers, stdnt_data)
File "train_student.py", line 82, in ensemble_preds
result[teacher_id] = deep_cnn.softmax_preds(stdnt_data, ckpt_path)
File "/home/harry/belajar/privacy/research/pate_2017/deep_cnn.py", line 587, in softmax_preds
saver.restore(sess, ckpt_path)
File "/home/harry/anaconda2/envs/pate17/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1538, in restore
+ compat.as_text(save_path))
ValueError: The passed save_path is not a valid checkpoint: /tmp/train_dir/mnist_100_teachers_0.ckpt-2999

from privacy.

Have you trained the 100 MNIST models (the teachers that make up the ensemble from which labels are aggregated to supervise the student)?

from privacy.

Have you trained the 100 MNIST models (the teachers that make up the ensemble from which labels are aggregated to supervise the student)?

i had the same question while training student model , but i did trained teachers first ,i first train teachers with teacher_id=0 , the result shows that "ValueError: The passed save_path is not a valid checkpoint: /tmp/train_dir/mnist_100_teachers_1.ckpt-2999",then i tried to change teacher_id=1,the result would be "ValueError: The passed save_path is not a valid checkpoint: /tmp/train_dir/mnist_100_teachers_2.ckpt-2999" , i am wondering weather the teacher model did not store all the checkpoint or student read checpoint which it did not need.

from privacy.

Oh I see: you need to run a training job for each teacher from teacher_id=0 to teacher_id=99, so you should execute train_teacher.py 100 times with a different teacher_id flag.

from privacy.

Feel free to reopen if that did not solve your problem

from privacy.