45 lines
2.5 KiB
Bash
45 lines
2.5 KiB
Bash
# -*- coding: utf-8 -*-
|
|
# @Author: Weisen Pan
|
|
|
|
# Load necessary system modules for the environment
|
|
source /etc/profile.d/modules.sh
|
|
module load gcc/11.2.0 # Load GCC compiler version 11.2.0
|
|
module load openmpi/4.1.3 # Load OpenMPI version 4.1.3 for parallel processing
|
|
module load cuda/11.5/11.5.2 # Load CUDA version 11.5.2 for GPU acceleration
|
|
module load cudnn/8.3/8.3.3 # Load cuDNN version 8.3.3 for deep learning libraries
|
|
module load nccl/2.11/2.11.4-1 # Load NCCL version 2.11.4-1 for multi-GPU communication
|
|
module load python/3.10/3.10.4 # Load Python version 3.10.4
|
|
|
|
# Activate the virtual environment for PyTorch and Horovod
|
|
source ~/venv/pytorch1.11+horovod/bin/activate
|
|
|
|
# Set up the log directory and remove any previous log records
|
|
LOG_OUTPUT="/home/projadmin/Federated_Learning/project_EdgeFLite/records/${JOB_NAME}_${JOB_ID}"
|
|
rm -rf ${LOG_OUTPUT} # Clean previous logs
|
|
mkdir -p ${LOG_OUTPUT} # Create new log directory
|
|
|
|
# Prepare local storage for the dataset
|
|
LOCAL_DATA_DIR="${SGE_LOCALDIR}/${JOB_ID}/" # Set local storage path
|
|
cp -r ../summit2024/simpleFL/performance_test/cifar100/data ${LOCAL_DATA_DIR} # Copy CIFAR-100 data to local storage
|
|
|
|
# Move to the project directory
|
|
cd EdgeFLite
|
|
|
|
# Run the federated learning experiment with the specified parameters
|
|
python run_gkt.py \
|
|
--is_fed=1 \ # Enable federated learning
|
|
--fixed_cluster=0 \ # Use dynamic clustering
|
|
--split_factor=1 \ # Set split factor
|
|
--num_clusters=20 \ # Number of clusters in the federation
|
|
--num_selected=20 \ # Number of selected clients per round
|
|
--arch=resnet_model_110sl \ # Model architecture: ResNet-110 small layer
|
|
--dataset=cifar100 \ # Dataset: CIFAR-100
|
|
--num_classes=100 \ # Number of classes in the dataset
|
|
--is_single_branch=0 \ # Enable multi-branch model
|
|
--is_amp=0 \ # Disable automatic mixed precision
|
|
--num_rounds=650 \ # Total number of federated learning rounds
|
|
--fed_epochs=1 \ # Number of local epochs per round
|
|
--cifar100_non_iid="quantity_skew" \ # Specify non-IID scenario: quantity skew
|
|
--spid="FGKT_R110_20c_skew" \ # Experiment identifier
|
|
--data=${LOCAL_DATA_DIR} # Path to the local dataset
|