-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathsampling.py
198 lines (170 loc) · 7.06 KB
/
sampling.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Python version: 3.6
import numpy as np
from torchvision import datasets, transforms
def mnist_iid(dataset, num_users):
"""
Sample I.I.D. client data from MNIST 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 mnist_noniid(dataset, num_users):
"""
Sample non-I.I.D client data from MNIST dataset
:param dataset:
:param num_users:
:return:
"""
# 60,000 training imgs --> 200 imgs/shard X 300 shards
num_shards, num_imgs = 200, 300
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()
# sort labels
idxs_labels = np.vstack((idxs, labels))
idxs_labels = idxs_labels[:, idxs_labels[1, :].argsort()]
idxs = idxs_labels[0, :]
# divide and assign 2 shards/client
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
def mnist_noniid_unequal(dataset, num_users):
"""
Sample non-I.I.D client data from MNIST dataset s.t clients
have unequal amount of data
:param dataset:
:param num_users:
:returns a dict of clients with each clients assigned certain
number of training imgs
"""
# 60,000 training imgs --> 50 imgs/shard X 1200 shards
num_shards, num_imgs = 1200, 50
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()
# sort labels
idxs_labels = np.vstack((idxs, labels))
idxs_labels = idxs_labels[:, idxs_labels[1, :].argsort()]
idxs = idxs_labels[0, :]
# Minimum and maximum shards assigned per client:
min_shard = 1
max_shard = 30
# Divide the shards into random chunks for every client
# s.t the sum of these chunks = num_shards
random_shard_size = np.random.randint(min_shard, max_shard+1,
size=num_users)
random_shard_size = np.around(random_shard_size /
sum(random_shard_size) * num_shards)
random_shard_size = random_shard_size.astype(int)
# Assign the shards randomly to each client
if sum(random_shard_size) > num_shards:
for i in range(num_users):
# First assign each client 1 shard to ensure every client has
# atleast one shard of data
rand_set = set(np.random.choice(idx_shard, 1, 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)
random_shard_size = random_shard_size-1
# Next, randomly assign the remaining shards
for i in range(num_users):
if len(idx_shard) == 0:
continue
shard_size = random_shard_size[i]
if shard_size > len(idx_shard):
shard_size = len(idx_shard)
rand_set = set(np.random.choice(idx_shard, shard_size,
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)
else:
for i in range(num_users):
shard_size = random_shard_size[i]
rand_set = set(np.random.choice(idx_shard, shard_size,
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)
if len(idx_shard) > 0:
# Add the leftover shards to the client with minimum images:
shard_size = len(idx_shard)
# Add the remaining shard to the client with lowest data
k = min(dict_users, key=lambda x: len(dict_users.get(x)))
rand_set = set(np.random.choice(idx_shard, shard_size,
replace=False))
idx_shard = list(set(idx_shard) - rand_set)
for rand in rand_set:
dict_users[k] = np.concatenate(
(dict_users[k], idxs[rand*num_imgs:(rand+1)*num_imgs]),
axis=0)
return dict_users
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[i][1] for i in range(len(dataset))]
# labels = np.array(dataset.train_labels)
# sort labels
idxs_labels = np.vstack((idxs, labels))
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
if __name__ == '__main__':
dataset_train = datasets.MNIST('./data/mnist/', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,),
(0.3081,))
]))
num = 100
d = mnist_noniid(dataset_train, num)