Comments (4)
- In the TermEncoder class, we calculate the node embeddings from bottom to top.
- In the GallinaTermParser class, we use lark to parse the S-expressions of Coq terms into ASTs.
from coqgym.
- In the TermEncoder class, we calculate the node embeddings from bottom to top.
- In the GallinaTermParser class, we use lark to parse the S-expressions of Coq terms into ASTs.
Thanks! Also, do you embed individual symbols? (e.g. characters?) There are 128 chars so what is the point of embedding those? Asking after reading the paper, will attach relevant parts that are unclear to me:
from coqgym.
so do you embed symbols or use one hot vectors for them is basically my question.
from coqgym.
We use embeddings. See
CoqGym/ASTactic/models/tactic_decoder.py
Line 80 in 05fa457
where the embedding dimension is 256:
Line 40 in 05fa457
from coqgym.
Related Issues (20)
- What is the train, val, test splits? HOT 1
- How is the mapping of individual words (or symbols) to vectors is done HOT 3
- How to efficiently process a batch of terms in one go for Tree Neural Networks HOT 2
- Hidden states in TermEncoder accessed before initialized HOT 2
- discussion feature from github for CoqGym HOT 1
- Parsing error HOT 4
- Embeddings for tactics HOT 3
- CoqExn Error when starting next proof HOT 2
- line 6: unrecognized keyword ignored: db_pagesize HOT 1
- extract_steps doesn't work if you change location of the data HOT 3
- A little question about CoqGym HOT 3
- A bug in the dataset of CoqGym HOT 5
- Usage of pre-trained model HOT 1
- ASTactic/extract_proof_steps.py process killed after 17% HOT 5
- ASTactic/extract_proof_steps.py not working with --filter flag HOT 6
- Version of pytorch missing from `coq_gym.yml` HOT 1
- Documentation for how to reproduce benchmark HOT 1
- Testing fails with EOF on test folder HOT 5
- License Compatibility Review Suggested for Dataset
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 coqgym.