Home

Awesome

Π-NAS

This repository provides the evaluation code of our submitted paper: Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift.

Our Trained Models

Usage

1. Requirements

2. Evaluate our models

Training and Searching

This reimplementation is based on OpenSelfSup and MoCo. Please acknowledge their contribution.

cd OpenSelfSup && pip install -v -e .

1. Π-NAS Learning

bash tools/dist_train.sh configs/pinas_learning.py 8 --work_dir /path/to/save/logs/and/models

2. Extract supernet backbone weights

python tools/extract_backbone_weights.py /checkpoint/of/1. /extracted/weight/of/1.

3. Linear Training

bash tools/dist_train.sh configs/pinas_linear_training.py 8 --pretrained /extracted/weight/of/1. --work_dir /path/to/save/logs/and/models

4. Linear Evaluation

bash tools/dist_train.sh configs/pinas_linear_evaluation.py 8 --resume_from /checkpoint/of/3. --work_dir /path/to/save/logs/and/models