Code Monkey home page Code Monkey logo

fdnas's Introduction

Federated Direct Neural Architecture Search

This repository accompanies the paper Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search and contains the basic code for replicating the training and computations in it. We will continue to add more details and code to this repository as we go along

Search

FDNAS:

nohup python federated_main.py  --gpu 2 --search --warmup --resume --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 128 --test_batch_size 128 --init_lr 0.025 --arch_algo grad --arch_lr 0.025 > 1.out 2>&1 &

Cluster FDNAS:

nohup python federated_main.py  --gpu 0 --search --resume --last_round 175 --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 128 --test_batch_size 128 --init_lr 0.025 --arch_algo grad --arch_lr 0.025 --target_hardware cpu --object_to_search cpu --grad_binary_mode two --grad_reg_loss_type add#linear --grad_reg_loss_lambda 0.05 > cls_cpu.out 2>&1 &


nohup python federated_main.py  --gpu 2 --search --resume --last_round 175 --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 128 --test_batch_size 128 --init_lr 0.025 --arch_algo grad --arch_lr 0.025 --target_hardware gpu8 --object_to_search gpu8 --grad_binary_mode two --grad_reg_loss_type add#linear --grad_reg_loss_lambda 0.05 > cls_gpu.out 2>&1 &

Derive normal model

nohup python convert_normal_architecture.py --gpu 0 --path output/exp_name/ --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ > cvt.out 2>&1 &

Train a derived model

nohup python retrain.py --path output/fednas-grad12,3,4,3,4,3/learned_net --gpu 3 --resume --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 256 --test_batch_size 256 --init_lr 0.05 > 2.out 2>&1 &

nohup python retrain.py --resume --path output/fednas-grad1cpu2,3,4,3,4,3/learned_net --object_to_retrain cpu --gpu 0  --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 128 --test_batch_size 128 --init_lr 0.025 --last_round 300 > 160to250round_cpu_retrain.out 2>&1 &

nohup python retrain.py --resume --path output/fednas-grad1gpu2,3,4,3,4,3/learned_net --object_to_retrain gpu8 --gpu 0  --dataset_location /home/grouplcheng/data/zch/dataset/cifar100/ --train_batch_size 128 --test_batch_size 128 --init_lr 0.025 --last_round 300 > 160to250round_gpu_retrain.out 2>&1 &

fdnas's People

Contributors

chunhuizng avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.