Comments (8)
This isn't an issue so I am closing now.
from crepe.
Do you have a public aws ami with digits installed?
from crepe.
Sorry I don't have that. We have a docker image for DIGITS which makes installation very straightforward.
However you need a more recent version of DIGITS than available in the Docker image to run the Text Classification tutorial. @flx42 is it conceivable to publish a Dockerfile to allow users to create images off the latest DIGITS code from Github?
from crepe.
Thank you for implementing this, it works much faster. Because the input is 1024 characters instead of the 1014 in the original version, should the sizes of the layers be slightly different? e.g. 341 x 256 after the first TemporalMaxPooling, and so forth.
from crepe.
Oh yes I should have updated this comment. Or perhaps it should be removed since the idea is to have the number of input characters a parameter.
With feature_len=1024
don't we end up with (1024-6-3)/3+1=339
features after the first max pooling operation? So the successive shapes would be:
-- those shapes are assuming feature_len==1024
-- 1024 x alphabet_len
net:add(backend.TemporalConvolution(alphabet_len, 256, 7))
-- [1024-6=1018] x 256
net:add(nn.Threshold())
net:add(nn.TemporalMaxPooling(3, 3))
-- [(1018-3)/3+1=339] x 256
net:add(backend.TemporalConvolution(256, 256, 7))
-- [339-6=333] x 256
net:add(nn.Threshold())
net:add(nn.TemporalMaxPooling(3, 3))
-- [(333-3)/3+1=111] x 256
net:add(backend.TemporalConvolution(256, 256, 3))
net:add(nn.Threshold())
-- [111-2=109] x 256
net:add(backend.TemporalConvolution(256, 256, 3))
net:add(nn.Threshold())
-- [109-2=107] x 256
net:add(backend.TemporalConvolution(256, 256, 3))
net:add(nn.Threshold())
-- [107-2=105] x 256
net:add(backend.TemporalConvolution(256, 256, 3))
-- [105-2=103] x 256
net:add(nn.Threshold())
net:add(nn.TemporalMaxPooling(3, 3))
-- [(103-3)/3+1=34] x 256
net:add(nn.Reshape(8704))
We still end up with 8704 features at the input of the fully-connected layers.
from crepe.
Ah yes, I had forgotten the -6 in the first convolution. Thanks, this helps a lot. I was making some changes to the network and wanted make sure I was calculating everything correctly.
from crepe.
This is wonderful! I see the pull request is in DIGITS already. If you do not mind, I will probably brag about it on Facebook a bit :P
Thanks for the great contribution!
from crepe.
If you do not mind, I will probably brag about it on Facebook a bit :P
You are most welcome to do so :-)
from crepe.
Related Issues (20)
- Issue in saving data HOT 4
- [Question] Where is batch Tensor initialized? HOT 3
- How to run this in cpu only mode? HOT 33
- qlua: ./model.lua:237: inconsistent tensor size at /home/ubuntu/torch/pkg/torch/lib/TH/generic/THTensorCopy.c:7
- [Question] Would using ReLU instead of Threshold produce similar results? HOT 4
- Unable to connect X11 server HOT 4
- Forward propagation time benchmark HOT 2
- Printing classes HOT 4
- How to change Crepe configurations to TEST Dataset on Trained Model HOT 5
- Y-axis scale and units? HOT 1
- Replicating on mxnet - too much memory for GPU HOT 12
- Training on a custom dataset HOT 10
- Question on batch normalization. HOT 3
- Exception while testing on custom dataset HOT 2
- How do I save the confusion matrix data in a vector?
- Number of eras
- New dataset location? HOT 2
- Yelp dataset HOT 2
- yelp data set 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 crepe.