Skip to content

linusericsson/einspace

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

einspace: Searching for Neural Architectures from Fundamental Operations

Accepted to NeurIPS 2024

[paper] [project page]

This is the official codebase for einspace, a new expressive search space for neural architecture search.

image

Diverse architectures can be represented in our expressive space as shown above for ConvNets, transformers and MLP-only networks.

Follow the instructions below to set up the environment, data, and then run an example script.

Environment Setup

We provide a sample setting up script as following:

conda create -n einspace python=3.10 -y
conda activate einspace
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 -f https://download.pytorch.org/whl/torch_stable.html
pip install --no-build-isolation git+https://github.com/zhouzx17/zero-cost-nas.git
pip install tqdm scipy einops positional_encodings seaborn sympy h5py librosa
pip install -r requirements.txt
pip install -e .

Data Setup

Please follow the official instructions of UnseenNAS and NASBench360 to setup the dataset, after which you can place the files using the following arrangement.

einspace/
data/
|--adinst
|  |__metadata, test_x.npy, test_y.npy ...
|--language
|  |__metadata, test_x.npy, test_y.npy ...
|--multnist
|  |__metadata, test_x.npy, test_y.npy ...
|--cifartile
|  |__metadata, test_x.npy, test_y.npy ...
|--gutenberg
|  |__metadata, test_x.npy, test_y.npy ...
|--isabella
|  |__metadata, test_x.npy, test_y.npy ...
|--geoclassing
|  |__metadata, test_x.npy, test_y.npy ...
|--chesseract
|  |__metadata, test_x.npy, test_y.npy ...
|--cifar100
|   |--cifar100_train.indices
|   |--cifar100_valid.indices
|   |__cifar-100-python
|      |--meta
|      |--train
|      |__test
|--NinaPro
|   |__label_test.npy, label_train.npy, label_val.npy, ninapro_test.npy, ninapro_train.npy, ninapro_val.npy
|--Spherical
|   |__s2_cifar100.gz, spherical_train.indices, spherical_valid.indices
|--darcyflow
|   |__piececonst_r421_N1024_smooth1.mat, piececonst_r421_N1024_smooth2.mat
|--cosmic
|   |--cosmic_test.pt
|   |--cosmic_train.pt
|   |--cosmic_valid.pt
|   |--npy_test  
|   |--npy_train  
|   |--test_dirs.npy  
|   |__train_dirs.npy
|_ ...

Running Experiments

python einspace/main.py --config $config --device $GPU

For example, to execute the RE(RN18) experiment on the Language dataset, you can run

python einspace/main.py --config configs/language/re_language.yaml --device cuda:0

Cite us!

@inproceedings{ericsson2024einspace,
    title={einspace: Searching for Neural Architectures from Fundamental Operations}, 
    author={Linus Ericsson and Miguel Espinosa and Chenhongyi Yang and Antreas Antoniou and Amos Storkey and Shay B. Cohen and Steven McDonagh and Elliot J. Crowley},
    year={2024},
    booktitle={NeurIPS},
    eprint={2405.20838},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

About

Official code for our NeurIPS 2024 paper "einspace: Searching for Neural Architectures from Fundamental Operations"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages