Comments (4)
daniel-kukiela
commented on June 23, 2024
You should probably do not touch batch_size.
Instead of that you can increase num_layers and num_units. The other thing you want to play with is vocab_size (100k+ using BBE/WPM tokenizer and even higher for standard tokenizer).
from nmt-chatbot.
adamshamsudeen
commented on June 23, 2024
Great, will try it out. Btw why is my bleu score constantly at zero?
from nmt-chatbot.
daniel-kukiela
commented on June 23, 2024
Because it is not straight conversion from one language to another. We are using NMT to translate from english to english, and the more sentences in corpus, the more response will be way different than in training pair (even if still correct), and BLEU is calculated by comparison NMT output and response (sentence from to file).
from nmt-chatbot.
adamshamsudeen
commented on June 23, 2024
So that means we have to manually evaluate a model by feeding in questions.
Thank you for your time 👍
from nmt-chatbot.
Related Issues (20)
- Chatbot only produces 1 answer despite beam width being 20 HOT 4
- Can't run train.py HOT 7
- Train.py says it's finished training after 1 second. HOT 2
- ERROR: cannot import name 'nmt' from 'nmt' HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: 'data//corpus_size'
- nmt: [ deleted ] while training
- Trained Model ? HOT 1
- does this work with tensorflow 2.0?
- is it supposed to just be stopped on this
- 2021-05-06 22:03:17.947802: I tensorflow/core/kernels/shuffle_dataset_op.cc:121] Shuffle buffer filled.
- decoding to output F:\Nebula0.0.5\nmt-chatbot\model\output_dev.
- from nmt import nmt : error
- TypeError: 'encoding' is an invalid keyword argument for this function HOT 1
- Inference returning the same empty answer to everything i type HOT 1
- bot producing only one translation per input
- Cannot Downgrade Tensorflow 1.x on Google Colab
- how do i make it train more epoch like 10000
- cannot import name 'nmt' from 'nmt'
- Issue with tensorflow api and pip installation candidate missing before 2.x
- cannot import name 'lookup_ops' from 'tensorflow.python.ops'
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 nmt-chatbot.