Comments (5)
@amirj nmt.py
in session 2 and session 3 should be identical. Synched them here, can you check that please? If it works i can merge it with the central.
from dl4mt-tutorial.
@orhanf I don't understand the relation between this link and the topic!
By the way, when I diff 'nmt.py' in session 2 and session 3 it seems that they are different to some extent. For example:
shared_vars = [tparams[_p(prefix, 'U')],
tparams[_p(prefix, 'Wc')],
- tparams[_p(prefix, 'Wd_att')],
+ tparams[_p(prefix, 'W_comb_att')],
tparams[_p(prefix, 'U_att')],
tparams[_p(prefix, 'c_tt')],
tparams[_p(prefix, 'Ux')],
- tparams[_p(prefix, 'Wcx')]]
+ tparams[_p(prefix, 'Wcx')],
+ tparams[_p(prefix, 'U_nl')],
+ tparams[_p(prefix, 'Ux_nl')],
+ tparams[_p(prefix, 'b_nl')],
+ tparams[_p(prefix, 'bx_nl')]]
It seems that the attention mechanism has been changed in session3.
from dl4mt-tutorial.
lol, sorry my bad, i meant this. Actually it was session2 that has changed, and session3 is not adapted for those changes.
from dl4mt-tutorial.
Is it means that learning with the current version of nmt.py in session3 leads to incorrect results?
On ۱ بهمن ۱۳۹۴ ه.ش., at ۲۰:۲۲, Orhan Firat [email protected] wrote:
lol, sorry my bad, i meant this orhanf@9199ac0. Actually it was session2 that has changed, and session3 is not adapted for those changes.
—
Reply to this email directly or view it on GitHub #29 (comment).
from dl4mt-tutorial.
Not incorrect results, actually the original version. Session2 implements an improved version tho.
from dl4mt-tutorial.
Related Issues (20)
- Why the grads have to be shared? HOT 2
- Cost is Nan after one epoch if maxlen > 50 HOT 3
- Where is dataset='/ichec/work/dl4mt_data/nec_files/wiki.tok.txt.gz'? HOT 2
- discrepancy between paper and code HOT 1
- NaN detected HOT 1
- L2 regularization on bias terms?
- Unnecessary bias term? HOT 1
- Asymmetry in read gate application
- dim == dim_nonlin and nin == nin_nonlin must be always true?
- How to build the dataset 'all.en.concat.gz.pkl' in session2/train_nmt_all.py? HOT 1
- Random Translations? HOT 5
- ValueError: unsupported pickle protocol: 3 HOT 2
- why convert the value of matrix to the type with astype('float32')? HOT 2
- a detailed description about param_init_gru and gru_layer HOT 2
- the value of TensorType(float32, 3D) HOT 2
- compute word probabilities HOT 2
- Maybe it's time to upgrade to Python 3 and ditch Python 2 support? HOT 1
- By condition what does it mean in this tutorial?
- Can anyone provide GPU version of translate.py? HOT 1
- TypeError
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 dl4mt-tutorial.