Comments (1)
Hi, the noise shape for dropout has a specific syntax. In the noise_shape parameter, 1 means "keep the dropout mask the same when this dimension changes". A value equal to the dimension at that position in the shape means "draw a new dropout mask every time this dimension changes.
In convolutional layers, your inputs typically have this shape: [batch, x, y, filter]. You could use that as your noise shape but in convolutional layers, you get better results (really, I tried and you can try too) when dropout is used consistently with the way "neurons" work in convolutional layers. When convolving the image with a filter, the same filter weights are used at every position in the image where the filter is applied. So it kind of makes sense that the same dropout mask would be used at every position too. Of course, when you move to the next image in the batch or the next filter, you draw a new dropout mask. This is called "spatial dropout" and the appropriate mask parameter for this is [batch, 1, 1, filter]
See the documentation here: https://www.tensorflow.org/api_docs/python/tf/layers/dropout
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
- BatchNorm is not in 'test mode' inside update_train_data 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
- 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.