Skip to content

pnnl/SuperSAM

Repository files navigation

SuperSAM: Crafting a SAM supernetwork via structured pruning and unstructured parameter prioritization

This is the official implementation for the paper:

Usage

Train supernet on SA1B dataset.

python nas.py --dataset=sa1b \
--epochs=5 --batch_size=8 --trainable=em \
--lr=1e-5 --weight_decay=0 --train_subset=400 \
--test_subset=100 --train_prompt=p \
--test_prompt=p --loss=dice --sandwich=lsm \
--no_verbose --save_interval=4 \

Anonymous

Citation

If you find our work is helpful, please kindly support our efforts by citing our paper:


under review

Acknowledgement

The experiments of this work is sponsored by [anonymous institution] and [anonymous institution].