Comments (6)
Did you modify training files? It looks like number of lines in your tst2012 and/or tst2013 files between "from" and "to" files doesn't match. You have to have pairs, and that means number of lines in tst2012.from file must match number of lines in tst2012.to. Same for tst2013.(from|to).
Doublecheck that please.
from nmt-chatbot.
okay i'll recheck that.
can you tell me what vocab size should i use? my gpu has 2gb vram.
from nmt-chatbot.
With 2GB of VRAM try to lower 'num_units' to 256 and leave vocab as is.
If you get OOM error try to lower vocab by 2k, and try again. You can change 'vocab_size' in settings and run prepare_data.py again.
If you are doing any changes in hparams section of settings, remember to either set 'override_loaded_hparams' or remove everything inside 'model' folder (as settings are saved within model after first run of train.py).
from nmt-chatbot.
no no i am not doing any changes in anything..
i just ran it in default settings and this index error keeps coming up.
from nmt-chatbot.
So do a clean clone, change 'num_units' to 256 and do everything step by step once more.
from nmt-chatbot.
okay brother.
i'll do that and let you know.
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.