Code2seq

Re-implementation of "CODE2SEQ: GENERATING SEQUENCES FROM STRUCTURED REPRESENTATIONS OF CODE"

Generate Convert Improve

Install / Use

/learn @m3yrin/Code2seq

About this skill

Quality Score

0/100

README

code2seq [WIP]

A PyTorch re-implementation code for "code2seq: Generating Sequences from Structured Representations of Code"

Paper(Arxiv) : https://arxiv.org/abs/1808.01400
Official Github : https://github.com/tech-srl/code2seq

Requirements

Please see requirements.txt

Usage

notebooks/preparation.ipynb for downloading dataset, making some directories etc.
notebooks/code2seq.ipynb for training and evaluating the model.

Memo

Beam search is not implemented.
GCP AI Platform Notebooks is used to train model.
AI Platform Notebooks requires google_compute_engine api so please install this before installing other packages if you use AI Platform Notebooks.

Related Skills

node-connect

339.3k

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps

frontend-design

83.9k

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

openai-whisper-api

339.3k

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

commit-push-pr

83.9k

Commit, push, and open a PR