Comments (6)
1)You only need the validation set (or a subset of it) to evaluate
2-3) I followed the instructions here: https://github.com/tensorflow/models/tree/master/research/slim#Data
This was a while ago though, and I remember it not being a super easy process. At the end of it, you should have the ImageNet dataset in TFRecord format. The images are automatically preprocessed before being input to the model.
from slalom.
@ohsai I'm having the exact same issue right now to get the dataset ready, did you have any luck on this? It would be greatly appreciated if any help can provided!
from slalom.
@ohsai @ftramer @DRyan1995 Hi, when I run "python -m python.slalom.scripts.eval mobilenet sgxdnn --batch_size=8 --max_num_batches=4 --verify --verify_batched --use_sgx", it returned an error "ValueError: No data files found in ../imagenet/validation-*".
I think the error is same as this issue, but I am a beginner for tensorflow, could you give some detial tips about downloading the validation dataset, please? Thanks.
from slalom.
@bronzeMe same issue. Have u tackle this issue now?
from slalom.
Hi guys:
Convert the input data to tfrecord format first. Then rename the generated tf-record validation file to validation-xxxxx-of-xxxxx.tfrecord will help.
Remind that after the word validation , I replace the underline with the simple dash.
from slalom.
@GuoJinnan Thank you so much !! I will try it.
from slalom.
Related Issues (20)
- Can not use --batch_verify and --verify_preproc toghther HOT 1
- Freivald check for Dense and Conv Layer questions HOT 2
- Using Eigen/Sparse HOT 2
- Random r vector HOT 3
- loop over output_map HOT 6
- compile error
- error
- the code about implementing DNN in SGX without outsourcing HOT 1
- Three issues for building HOT 2
- Undefinied reference error in lib/sgxdnn.so HOT 3
- How to run TEE base line HOT 1
- Parallelization is working? HOT 1
- ModuleNotFoundError: No module named 'python.slalom.resnet2 HOT 1
- Question about fixed-point representation HOT 2
- I cannot run this project. HOT 5
- Error executing make while tring to build SGX application
- Question about field computation
- Question about running slalom app HOT 4
- Reproducing the results for quantisation
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 slalom.