Comments (3)
Hi, I can't reproduce your error.
This is the output I get:
(theano) Gregoires-MacBook-Air:examples gregoire$ python elman-keras.py
Using Theano backend.
NEW BEST: epoch 0 valid F1 51.42 best test F1 46.93
NEW BEST: epoch 1 valid F1 63.54 best test F1 58.99
NEW BEST: epoch 2 valid F1 73.0 best test F1 71.3
NEW BEST: epoch 3 valid F1 77.99 best test F1 75.23
NEW BEST: epoch 4 valid F1 82.08 best test F1 79.31
NEW BEST: epoch 5 valid F1 84.16 best test F1 81.05
NEW BEST: epoch 6 valid F1 85.66 best test F1 82.0
NEW BEST: epoch 7 valid F1 86.4 best test F1 83.04
NEW BEST: epoch 8 valid F1 87.57 best test F1 84.64
NEW BEST: epoch 9 valid F1 88.37 best test F1 84.44
NEW BEST: epoch 10 valid F1 89.97 best test F1 87.54
NEW BEST: epoch 11 valid F1 90.08 best test F1 86.97
NEW BEST: epoch 12 valid F1 91.11 best test F1 87.83
NEW BEST: epoch 13 valid F1 91.69 best test F1 89.24
NEW BEST: epoch 14 valid F1 91.92 best test F1 89.11
NEW BEST: epoch 15 valid F1 92.26 best test F1 89.77
[learning] epoch 16 >> 100.00% completed in 7.86 (sec) <<
NEW BEST: epoch 17 valid F1 92.95 best test F1 89.95
[learning] epoch 18 >> 100.00% completed in 8.61 (sec) <<
NEW BEST: epoch 19 valid F1 93.02 best test F1 90.17
NEW BEST: epoch 20 valid F1 93.19 best test F1 90.8
...
from is13.
The weights are not equal to Nan in my case.
from is13.
Turns out this only happens on one of my machines (i have 2 identical macbook 15) for some reason. I am investigating it.
Appreciate your speed response, learned a lot from your code!
from is13.
Related Issues (20)
- Some questions about the Dataset HOT 5
- problems with --- python code/rnnslu.py HOT 3
- OSError: [Errno 2] No such file or directory: 'conlleval.pl' HOT 4
- Using Theano in Word Embedding Method HOT 4
- Get word embeddings aligned with words HOT 3
- Cost function on last word in sentence HOT 2
- Is there any mini-batched is13 (rnn for sequence labeling task)? HOT 1
- rnnslu.py takes too long for nh=200
- rnnslu.py takes too longer than 40 seconds for nh=200 HOT 4
- i get different results than expected HOT 11
- A simple question about the ouput s_t of rnn HOT 1
- Appying CRF after elman network HOT 2
- Label Issue HOT 1
- code bug HOT 2
- Link for ATIS dataset not working HOT 1
- Code Error HOT 1
- intent labels HOT 4
- conlleval.pl OSError: [WinError 193] %1 is not a valid Win32 application, FileNotFoundError: [WinError 2] The system cannot find the file specified HOT 1
- Link for ATIS dataset not working again HOT 3
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 is13.