utils.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import copy
import torch
from torchvision import datasets, transforms
import numpy as np

def get_dataset(args):
    """ Returns train and test datasets and a user group which is a dict where
    the keys are the user index and the values are the corresponding data for
    each of those users.
    """

    if args.dataset == 'cifar':
        data_dir = '../data/cifar/'
       
        train_transform = transforms.Compose(
            [transforms.ToTensor(),
             #transforms.RandomCrop(size=24),
             transforms.RandomApply(torch.nn.ModuleList([
                 transforms.ColorJitter(),]),p=0.5),
             transforms.RandomAutocontrast(),
             transforms.RandomHorizontalFlip(),
             transforms.Normalize((0.4914, 0.4822, 0.4465), (0.247, 0.243, 0.261))])

        test_transform = transforms.Compose(
                [transforms.ToTensor(),
                 #transforms.RandomCrop(size=24),
                 transforms.Normalize((0.4914,0.4822,0.4465),(0.247,0.243,0.261))])

        train_dataset = datasets.CIFAR10(data_dir, train=True, download=True,
                                       transform=train_transform)

        test_dataset = datasets.CIFAR10(data_dir, train=False, download=True,
                                      transform=test_transform)
        
        # sample training data amongst users
        if args.iid:
            # Sample IID user data from Mnist
            user_groups = cifar_iid(train_dataset, args.num_users)
        else:
            # Sample Non-IID user data from Mnist
            if args.unequal:
                # Chose uneuqal splits for every user
                raise NotImplementedError()
            else:
                # Chose euqal splits for every user
                user_groups = cifar_noniid(train_dataset, args.num_users)

    return train_dataset, test_dataset, user_groups

def average_weights(w):
    """
    Returns the average of the weights.
    """
    w_avg = copy.deepcopy(w[0])
    for key in w_avg.keys():
        for i in range(1, len(w)):
            w_avg[key] += w[i][key]
        w_avg[key] = torch.div(w_avg[key], len(w))
    return w_avg


def exp_details(args):
    print('\nExperimental details:')
    print(f'    Model     : {args.model}')
    print(f'    Optimizer : {args.optimizer}')
    print(f'    Learning  : {args.lr}')
    print(f'    Global Rounds   : {args.epochs}\n')

    print('    Federated parameters:')
    if args.iid:
        print('    IID')
    else:
        print('    Non-IID')
    print(f'    Fraction of users  : {args.frac}')
    print(f'    Local Batch size   : {args.local_bs}')
    print(f'    Local Epochs       : {args.local_ep}\n')
    return

def cifar_iid(dataset, num_users):
    """
    Sample I.I.D. client data from CIFAR10 dataset
    :param dataset:
    :param num_users:
    :return: dict of image index
    """
    num_items = int(len(dataset)/num_users)
    dict_users, all_idxs = {}, [i for i in range(len(dataset))]
    for i in range(num_users):
        dict_users[i] = set(np.random.choice(all_idxs, num_items,
                                             replace=False))
        all_idxs = list(set(all_idxs) - dict_users[i])
    return dict_users


def cifar_noniid(dataset, num_users):
    """
    Sample non-I.I.D client data from CIFAR10 dataset
    :param dataset:
    :param num_users:
    :return:
    """
    num_shards, num_imgs = 200, 250
    idx_shard = [i for i in range(num_shards)]
    dict_users = {i: np.array([]) for i in range(num_users)}
    idxs = np.arange(num_shards*num_imgs)
    # labels = dataset.train_labels.numpy()
    labels = np.array(dataset.targets)

    # sort labels
    idxs_labels = np.vstack((idxs, labels))
    #stack into two rows, sort the labels row
    idxs_labels = idxs_labels[:, idxs_labels[1, :].argsort()]
    idxs = idxs_labels[0, :]

    # divide and assign
    for i in range(num_users):
        rand_set = set(np.random.choice(idx_shard, 2, replace=False))
        idx_shard = list(set(idx_shard) - rand_set)
        for rand in rand_set:
            dict_users[i] = np.concatenate(
                (dict_users[i], idxs[rand*num_imgs:(rand+1)*num_imgs]), axis=0)
    return dict_users