Comments (7)
We were getting comparable scores for cs-en when the initial pr was made, around august so the issues in NMT repo might be outdated. iirc the there were fixes at beam-search which uses the generate computational graph (same one we generate samples).
Have you checked whether the cost computational graphs are generating the same cost or not (using the same batch and initial parameters)?
from blocks-examples.
Thanks for your fast response,
we didn't try that yet. It's next on the list of things to try. Right now we are looking into something else, I let you know if we find something.
from blocks-examples.
Thanks, keep us posted
from blocks-examples.
Henry Choi told me that he was able to reproduce English to French results
with this implementation.
On 8 January 2016 at 15:32, Orhan Firat [email protected] wrote:
Thanks, keep us posted
—
Reply to this email directly or view it on GitHub
#71 (comment)
.
from blocks-examples.
@critias Hi, I am wondering did you reach the Groudhog performance. If you did, how did you reach that? I am trying the example as well and I cannot reach the performance.
from blocks-examples.
Hi,
yes and no. We got roughly equal results on the validation set during training, but not after reloading the saved model. Since we changed the code base a little to reload and translate the model I guess the error is on our side. It's still kinda unclear and we have to look into this in more detail, but were busy with other things last week.
Beside that we also try using orhanfs fork to see if his code to translate works better for us.
from blocks-examples.
It turned out the problem was on our side. We changed some minor parts of the code that caused a mismatch between the encoding used to create the vocabulary (just bytes) and the encoding used during training/translation (unicode).
We are now able to reproduce the GroundHog results and even slightly surpassed it (0.4% Bleu).
I'll close the issue. Thanks for your help and keep up the good work.
from blocks-examples.
Related Issues (20)
- How many iterations can the NMT example go through a day with GPU? HOT 7
- Fix target embedding? HOT 1
- Attention Matrix HOT 1
- What is the relationship between iteration and epoch?
- How to set up the Google 1 billion word dataset?
- Machine Translation : Deep Fusion HOT 2
- How to change beamsearch space of search?
- Ensemble multiple translation model in blocks HOT 1
- BatchNormalizedMLP problem with more than two dimensions
- Machine translation 'translation' mode giving "</S> </S> </S> </S> </S> </S> . </S> . . </S> </S>" HOT 2
- machine translation paper
- How do I get the BLEU scores from NMT training and why does "validation_out.txt" only contain .</S>
- What is the target BLEU score for machine translation HOT 13
- Cannot get the almost diagonal align map in the machine trainslation example HOT 2
- Machine translation crash: memory issue HOT 7
- continue training using a new corpus HOT 1
- Wrong eos idx in beam search of machine translation example HOT 1
- Save best model in machine translation HOT 3
- gpu out of memory HOT 8
- eos_idx in sampling.py 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 blocks-examples.