Cloud-CV/diverse-beam-search
:mag: :shipit: Decoding Diverse Solutions from Neural Sequence Models
When you're trying to get a computer to describe an image, translate text, or create a summary, standard methods often produce very similar, uninteresting results. This tool takes a neural network's output and helps it generate a wider range of distinct, yet still correct, descriptions or translations. It's for AI developers and researchers who build and refine these types of sequence generation models.
No commits in the last 6 months.
Use this if your neural sequence model is producing repetitive or too-similar outputs for ambiguous tasks like image captioning or machine translation, and you need more varied, correct options.
Not ideal if you are a non-technical end-user looking for a ready-to-use application, as this is a component for AI model development.
Stars
77
Forks
18
Language
Lua
License
—
Category
Last pushed
Aug 13, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Cloud-CV/diverse-beam-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
limix-ldm-ai/LimiX
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence...
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
google-research/plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets...
YalaLab/pillar-finetune
Finetuning framework for Pillar medical imaging models.
thuml/LogME
Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML...