Comments (8)
what is the script you are using to run this?
from pandora.
I am using this:
python3 main.py config_chrestien3_keras.txt --train data/chrestien3/train --dev data/chrestien3/dev --test data/chrestien3/test
with the current master version.
from pandora.
Great, it seems to work now.
from pandora.
It looks like the only place where predict(..., batch_size)
is being used is here https://github.com/hipster-philology/pandora/blob/master/pandora/tagger.py#L369 and then the value passed is just the default from the tagger class. Therefore, the current use. We might have a use for applying different bacth size during prediction (since then the batch size there doesn't have an influence in performance and it can be as large as the system can afford), so I am leaving the fix as it is.
from pandora.
In a side note, what are the reasons for having main.py
, unseen.py
and train.py
as different scripts? The first two are actually the same, as far as I can see.
from pandora.
from pandora.
train.py should be replaced by the content of main.py though
from pandora.
I reopened this as a separate issue #52, llet's move the discussion over there!
from pandora.
Related Issues (20)
- Single Label morph fails
- Error in annotating new data: Preprocessor' object has no attribute 'include_morph' HOT 4
- Probable bug with morph dev evaluation with single label ? HOT 4
- Allow for a learning rate parameter HOT 5
- Is PyTorch using the token embeddings ? HOT 8
- Develop a tuning toolkit HOT 4
- Allow for training without test set HOT 4
- Early Stopping HOT 3
- Pretrained embeddings is a 3D tensor HOT 2
- Add a linter for future work HOT 3
- Decoding should be part of the model
- Tagger.py fails with pytorch model HOT 2
- Share a Latin model ? HOT 2
- Feedback on predictions
- Scoring: distinctions between known form/known label
- Latest PR broke tests HOT 7
- Not lowercasing lemmata? HOT 1
- Generation broken? HOT 11
- Segmentation fault on travis
- Configuration of Optimizer (SGD or Adam) from configfile
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 pandora.