-
Notifications
You must be signed in to change notification settings - Fork 3
/
train_imagenet.py
223 lines (167 loc) · 6.5 KB
/
train_imagenet.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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
'''Train CIFAR10 with PyTorch.'''
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import torch.backends.cudnn as cudnn
import torchvision
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import os
import argparse
# from models.vgg_cif10 import VGG
from models.wideresidual import WideResNet, WideBasic
from utils import progress_bar
import pdb
print("Train ImageNet ")
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('--lr', default=0.1, type=float, help='learning rate')
parser.add_argument('--data', default='/home/lorenzp/datasets/ImageNet', help='path to dataset')
parser.add_argument('--resume', '-r', action='store_true', help='resume from checkpoint')
parser.add_argument('-b', '--batch-size', default=16, type=int,
metavar='N',
help='mini-batch size (default: 256), this is the total '
'batch size of all GPUs on the current node when '
'using Data Parallel or Distributed Data Parallel')
args = parser.parse_args()
print("args", args)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
best_acc = 0 # best test accuracy
start_epoch = 0 # start from epoch 0 or last checkpoint epoch
# Data
print('==> Preparing data..')
train_sampler = None
# Data loading code
traindir = os.path.join(args.data, 'train')
valdir = os.path.join(args.data, 'val')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform_train = transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
# normalize,
])
train_dataset = datasets.ImageFolder(
traindir,
transform_train
)
trainloader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size, shuffle=True,
num_workers=4, pin_memory=True, sampler=train_sampler)
# trainset = torchvision.datasets.ImageNet(
# root=args.data, train=True, download=False, transform=transform_train)
# train_loader = torch.utils.data.DataLoader(
# trainset, batch_size=128, shuffle=True, num_workers=4)
val_transform = transforms.Compose([
# transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
# normalize,
])
valloader = torch.utils.data.DataLoader(
datasets.ImageFolder(valdir, val_transform),
batch_size=args.batch_size, shuffle=False,
num_workers=4)
# testset = torchvision.datasets.ImageNet(
# root=args.data, train=False, download=False, transform=test_transform)
# test_loader = torch.utils.data.DataLoader(
# testset, batch_size=128, shuffle=True, num_workers=4)
# transform_train = transforms.Compose([
# transforms.RandomCrop(32, padding=4),
# transforms.RandomHorizontalFlip(),
# transforms.ToTensor(),
# # transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
# ])
# transform_test = transforms.Compose([
# transforms.ToTensor(),
# # transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
# ])
# trainset = torchvision.datasets.CIFAR10(
# root='./data', train=True, download=True, transform=transform_train)
# trainloader = torch.utils.data.DataLoader(
# trainset, batch_size=128, shuffle=True, num_workers=2)
# testset = torchvision.datasets.CIFAR10(
# root='./data', train=False, download=True, transform=transform_test)
# testloader = torch.utils.data.DataLoader(
# testset, batch_size=100, shuffle=False, num_workers=2)
# classes = ('plane', 'car', 'bird', 'cat', 'deer',
# 'dog', 'frog', 'horse', 'ship', 'truck')
# Model
print('==> Building model..')
# net = VGG('VGG16')
depth=34
widen_factor=10
print("depth: ", depth, ", widen_factor", widen_factor)
net = WideResNet(num_classes=1000, block=WideBasic, depth=depth, widen_factor=widen_factor)
net = net.to(device)
if device == 'cuda':
net = torch.nn.DataParallel(net)
cudnn.benchmark = True
if args.resume:
# Load checkpoint.
print('==> Resuming from checkpoint..')
assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
checkpoint = torch.load('./checkpoint/ckpt.pth')
net.load_state_dict(checkpoint['net'])
best_acc = checkpoint['acc']
start_epoch = checkpoint['epoch']
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=args.lr,
momentum=0.9, weight_decay=5e-4)
# Training
def train(epoch):
print('\nEpoch: %d' % epoch)
net.train()
train_loss = 0
correct = 0
total = 0
for batch_idx, (inputs, targets) in enumerate(trainloader):
inputs, targets = inputs.to(device), targets.to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()
train_loss += loss.item()
_, predicted = outputs.max(1)
total += targets.size(0)
correct += predicted.eq(targets).sum().item()
if batch_idx 100 == 0:
progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
% (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
def test(epoch):
global best_acc
net.eval()
test_loss = 0
correct = 0
total = 0
with torch.no_grad():
for batch_idx, (inputs, targets) in enumerate(testloader):
inputs, targets = inputs.to(device), targets.to(device)
outputs = net(inputs)
loss = criterion(outputs, targets)
test_loss += loss.item()
_, predicted = outputs.max(1)
total += targets.size(0)
correct += predicted.eq(targets).sum().item()
if batch_idx % 100 == 0:
progress_bar(batch_idx, len(testloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
% (test_loss/(batch_idx+1), 100.*correct/total, correct, total))
# Save checkpoint.
acc = 100.*correct/total
if acc > best_acc:
print('Saving..')
state = {
'net': net.state_dict(),
'acc': acc,
'epoch': epoch,
}
path = 'checkpoint/wideresnet_' + str(depth) + str(widen_factor)
if not os.path.isdir(path):
os.mkdir(path)
torch.save(state, './' + path + '/wide_resnet_imagenet_ckpt.pth')
best_acc = acc
for epoch in range(start_epoch, start_epoch+50):
train(epoch)
test(epoch)