Comments (2)
Hi Alex,
Thank you for your interest in code2seq!
- We did not distribute training, just trained the model on a single Tesla V100 GPU for 52 epochs (a p3 instance in AWS).
- This took about 5 days for getting almost all scores, and a few extra days for the final minor increase in the scores.
- All code is released! The code and parameters in this repository are the same as in our training.
- For faster training with a minor score degradation, you can try the following changes (in
config.py
):
(a) SetRANDOM_CONTEXTS
tofalse
.
(b)USE_MOMENTUM
tofalse
(it uses Adam instead, which converges faster)
(c) In the filepreprocessing.sh
, take only 100MAX_CONTEXTS
instead of the default of 200.
(d) Decrease embedding sizes and vocabulary sizes. - You mentioned that you're trying to work on a python dataset: in our previous work, we noticed that python code is more difficult to learn (in general, not specifically for the code2seq task). We think that this is mainly because of the lack of type information; an additional cause is that Java code is usually cleaner in the top Github repositories in terms of naming conventions, having short and concise methods, etc.
Let me know how it works, and which hyperparameters gave you the most speed increase.
Best,
Uri
from code2seq.
Thanks for the help! After 5 epochs, the performance was at
Accuracy: 0.30012
Precision: 0.58042, recall: 0.48426, F1: 0.52799
which is most of the way to your performance after 52 epochs (~7 points off the results from the pretrained model). It's taking much longer than 5 days for me, but I think it's a result of network latency because the dataset is stored on a remote server. I'm going to try storing the dataset locally first, and if that is still slow (I guess because of hardware), I'll look into the modifications you suggest.
Will keep you posted on how it goes!
Alex
from code2seq.
Related Issues (20)
- Generating embeddings for Python and Java HOT 5
- Help with implementing local service with JavaExtractor HOT 10
- I can not preprocess Python dataset
- Error running prediction on Code2seq released model
- I got Out of Memory Error during Training
- Unable to get embeddings from the trained model for Java
- Extract Path Contexts Only HOT 5
- InvalidArgumentError in sess.run() HOT 3
- Visualize Python AST HOT 2
- Extract java files HOT 2
- Getting "was not completed in time" error when preprocessing dataset HOT 11
- code2seq for Python HOT 3
- Error processing property '_dropout_mask_cache' of <ContextValueCache> HOT 6
- Sampling k paths from AST tree HOT 11
- I am getting TimeError while using code2seq to predict long method HOT 2
- Generating code documentation with code2seq HOT 8
- Tensorflow out-of-bound error while trying to train the Code2Seq model on our own python dataset HOT 6
- Model is predicting empty string for custom python dataset HOT 8
- Exporting code vectors HOT 6
- Encountered error of preprocess data HOT 8
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 code2seq.