Comments (6)
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.
Related Issues (20)
- Insecure Random Number Generator HOT 1
- Potential bug using kernel regularizer
- tensorflow privacy requires numpy ~= 1.21 which is not compatible with python 11
- ValueError: Dimension size must be evenly divisible by 1048576 but is 1 for '{{node Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32](Mean, Reshape/shape)' with input shapes: [?,1024,1024], [0].
- from tensorflow_privacy.privacy.analysis import privacy_ledger HOT 3
- How can we specify to install it on tensorflow-gpu==2.4.0
- A Question about Research mi_lira_2021: why set training=True at Inference
- Inconsistency in released Versions between GitHub and PyPI HOT 1
- Privacy?
- cannot import name 'dp_event' from 'tensorflow_privacy.privacy.analysis' HOT 2
- Python version restricted to >=3.9, inability to use official docker containers of tensorflow HOT 1
- AttributeError: module 'tensorflow_privacy.privacy.analysis.compute_dp_sgd_privacy' has no attribute 'compute_dp_sgd_privacy' HOT 2
- Why isn't SampledWithoutReplacementDpEvent used instead of PoissonSampledDpEvent for DP-SGD epsilon calculation? HOT 2
- Question about rdp_accountant.py HOT 1
- question about "tensorflow_privacy.privacy.dp_query.gaussian_query" HOT 2
- Privacy guarantees of of privacy amplification by iteration example
- Federated DPFTRL and Adaptive Clipping noise injection. HOT 1
- Fresh install doesn't work (incompatible versions of tensorflow and tensorflow_privacy)
- Incompatible with hub.KerasLayer HOT 1
- Module Not Found Error
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from privacy.