Comments (2)
Good question. It will not change anything in the training. The values computed here are for visualisation only. So question is: will this change produce "more relevant" curves on the graphs ?
If this was dropout, then yes, definitely, you need to disable dropout when you compute the test and training curves, otherwise your training curve, computed on a half-brain-dead (dropped out) network will be very bad, sometimes worse than the test curve which should never happen (test loss is normally always higher(=worse) than training loss).
For batch norm, maybe that is the case as well. You have to try. I implemented this in this way because of the way batchnorm works. It uses statistics computed on the current batch of training data. When measuring performance on your test dataset, there is no "current batch of training data" so you have to use some other stats (running average of multiple previous batches). That is what the tst:True flag enables. When measuring your training metrics, the current batch exists and using stats computed on it for batch norm is not a problem so I did not feel I should enable a solution for a problem that I did not have. But maybe I was wrong there.
from tensorflow-mnist-tutorial.
Thank you very much for the explanation
from tensorflow-mnist-tutorial.
Related Issues (20)
- max test accuracy: 0 HOT 5
- Empty plots HOT 6
- line 37 (3.0, 3.1, 4.2) HOT 1
- cross_entropy * 100 HOT 2
- Guide for Installing TensorFlow and Python 3.5 on Windows HOT 2
- Error in mnist_1.0_softmax.py file HOT 4
- Doesn't work with latest pandas 0.20.1 and 0.20.2 HOT 4
- Issue with OSX HOT 2
- Examples are running very slow on AWS HOT 1
- _tkinter.TclError: no display name and no $DISPLAY environment variable HOT 1
- error while compiling the model HOT 1
- How to visualize? HOT 1
- How about tf.contrib.layers.batch_norm ? HOT 1
- Error occured when trying to run the script mnist_1.0_softmax.py HOT 1
- How to run on GPU? HOT 2
- how to download slides HOT 1
- Prediction is missing HOT 1
- Question related to compatible_convolutional_noise_shape function. HOT 1
- Point classification using DNN HOT 1
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 tensorflow-mnist-tutorial.