CownowAn/DaSS
Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)
This project helps machine learning engineers and researchers efficiently find the best performing student neural network architecture for a given teacher model and dataset. Instead of time-consuming trial-and-error training, it takes information about your teacher model and target dataset and predicts how well a potential student architecture will perform with knowledge distillation, enabling faster identification of optimal student networks. The primary users are ML engineers or researchers working on model compression and optimization.
No commits in the last 6 months.
Use this if you need to quickly find an efficient student neural network that performs well when learning from a larger, more complex teacher model on a new, unseen dataset.
Not ideal if you are training models from scratch without using knowledge distillation from a pre-existing teacher model.
Stars
26
Forks
2
Language
Python
License
—
Category
Last pushed
Mar 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CownowAn/DaSS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
IDEALLab/EngiBench
Benchmarks for automated engineering design
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...