AdaptNAS
Architecture adapter
An approach to improve neural architecture search by adapting architectures between domains to improve generalization performance on new datasets.
A PyTorch implementation of "Adapting Neural Architectures Between Domains" in NeurIPS 2020.
7 stars
1 watching
1 forks
Language: Python
last commit: almost 4 years ago
Linked from 1 awesome list
cifar-10digitsdomain-adaptationimagenetneural-architecture-search
Related projects:
Repository | Description | Stars |
---|---|---|
| Automates the search for optimal neural network configurations in deep learning applications | 468 |
| An instance segmentation network that adapts to varying object densities and complexities | 336 |
| An implementation of Neural Architecture Search using Reinforcement Learning with a Controller RNN. | 433 |
| An open-source framework for adapting representation models to various tasks and industries | 1,743 |
| An implementation of a neural network architecture search algorithm optimized for mobile devices. | 271 |
| An implementation of a knowledge aggregation method for adapting to multiple domains using a graph-based framework. | 69 |
| A Golang adapter for Inertia.js that enables server-side rendering with the Fiber framework. | 11 |
| A Python library for implementing and training various neural network architectures | 40 |
| This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. | 851 |
| An implementation of a Neural Architecture Search agent using Monte Carlo Tree Search and a predictive model for efficient search of neural network architectures on the NASBench-101 dataset. | 167 |
| An implementation of DARTS, a method for automatically designing neural network architectures. | 443 |
| A PyTorch implementation of a ShuffleNet-v2 neural network architecture for image classification. | 431 |
| A collection of implementations of algorithms to adapt deep learning models from one domain to another | 898 |
| An autoML tool that searches and optimizes neural network architectures using tensorflow and keras. | 30 |
| A scalable system for serving thousands of concurrent parameter-efficient fine-tuning adapters | 1,766 |