forked from weiaicunzai/pytorch-cifar100
-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
180 lines (141 loc) · 5.84 KB
/
train.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
# train.py
#!/usr/bin/env python3
""" train network using pytorch
author baiyu
"""
import os
import sys
import argparse
import time
from datetime import datetime
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from conf import settings
from utils import get_network, get_training_dataloader, get_test_dataloader, WarmUpLR
def train(epoch):
start = time.time()
net.train()
for batch_index, (images, labels) in enumerate(cifar100_training_loader):
if epoch <= args.warm:
warmup_scheduler.step()
if args.gpu:
labels = labels.cuda()
images = images.cuda()
optimizer.zero_grad()
outputs = net(images)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
n_iter = (epoch - 1) * len(cifar100_training_loader) + batch_index + 1
last_layer = list(net.children())[-1]
for name, para in last_layer.named_parameters():
if 'weight' in name:
writer.add_scalar('LastLayerGradients/grad_norm2_weights', para.grad.norm(), n_iter)
if 'bias' in name:
writer.add_scalar('LastLayerGradients/grad_norm2_bias', para.grad.norm(), n_iter)
print('Training Epoch: {epoch} [{trained_samples}/{total_samples}]\tLoss: {:0.4f}\tLR: {:0.6f}'.format(
loss.item(),
optimizer.param_groups[0]['lr'],
epoch=epoch,
trained_samples=batch_index * args.b + len(images),
total_samples=len(cifar100_training_loader.dataset)
))
#update training loss for each iteration
writer.add_scalar('Train/loss', loss.item(), n_iter)
for name, param in net.named_parameters():
layer, attr = os.path.splitext(name)
attr = attr[1:]
writer.add_histogram("{}/{}".format(layer, attr), param, epoch)
finish = time.time()
print('epoch {} training time consumed: {:.2f}s'.format(epoch, finish - start))
@torch.no_grad()
def eval_training(epoch):
start = time.time()
net.eval()
test_loss = 0.0 # cost function error
correct = 0.0
for (images, labels) in cifar100_test_loader:
if args.gpu:
images = images.cuda()
labels = labels.cuda()
outputs = net(images)
loss = loss_function(outputs, labels)
test_loss += loss.item()
_, preds = outputs.max(1)
correct += preds.eq(labels).sum()
finish = time.time()
if args.gpu:
print('GPU INFO.....')
print(torch.cuda.memory_summary(), end='')
print('Evaluating Network.....')
print('Test set: Average loss: {:.4f}, Accuracy: {:.4f}, Time consumed:{:.2f}s'.format(
test_loss / len(cifar100_test_loader.dataset),
correct.float() / len(cifar100_test_loader.dataset),
finish - start
))
print()
#add informations to tensorboard
writer.add_scalar('Test/Average loss', test_loss / len(cifar100_test_loader.dataset), epoch)
writer.add_scalar('Test/Accuracy', correct.float() / len(cifar100_test_loader.dataset), epoch)
return correct.float() / len(cifar100_test_loader.dataset)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('-net', type=str, required=True, help='net type')
parser.add_argument('-gpu', action='store_true', default=False, help='use gpu or not')
parser.add_argument('-b', type=int, default=128, help='batch size for dataloader')
parser.add_argument('-warm', type=int, default=1, help='warm up training phase')
parser.add_argument('-lr', type=float, default=0.1, help='initial learning rate')
args = parser.parse_args()
net = get_network(args)
#data preprocessing:
cifar100_training_loader = get_training_dataloader(
settings.CIFAR100_TRAIN_MEAN,
settings.CIFAR100_TRAIN_STD,
num_workers=4,
batch_size=args.b,
shuffle=True
)
cifar100_test_loader = get_test_dataloader(
settings.CIFAR100_TRAIN_MEAN,
settings.CIFAR100_TRAIN_STD,
num_workers=4,
batch_size=args.b,
shuffle=True
)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4)
train_scheduler = optim.lr_scheduler.MultiStepLR(optimizer, milestones=settings.MILESTONES, gamma=0.2) #learning rate decay
iter_per_epoch = len(cifar100_training_loader)
warmup_scheduler = WarmUpLR(optimizer, iter_per_epoch * args.warm)
checkpoint_path = os.path.join(settings.CHECKPOINT_PATH, args.net, settings.TIME_NOW)
#use tensorboard
if not os.path.exists(settings.LOG_DIR):
os.mkdir(settings.LOG_DIR)
writer = SummaryWriter(log_dir=os.path.join(
settings.LOG_DIR, args.net, settings.TIME_NOW))
input_tensor = torch.Tensor(1, 3, 32, 32).cuda()
writer.add_graph(net, input_tensor)
#create checkpoint folder to save model
if not os.path.exists(checkpoint_path):
os.makedirs(checkpoint_path)
checkpoint_path = os.path.join(checkpoint_path, '{net}-{epoch}-{type}.pth')
best_acc = 0.0
for epoch in range(1, settings.EPOCH):
if epoch > args.warm:
train_scheduler.step(epoch)
train(epoch)
acc = eval_training(epoch)
#start to save best performance model after learning rate decay to 0.01
if epoch > settings.MILESTONES[1] and best_acc < acc:
torch.save(net.state_dict(), checkpoint_path.format(net=args.net, epoch=epoch, type='best'))
best_acc = acc
continue
if not epoch % settings.SAVE_EPOCH:
torch.save(net.state_dict(), checkpoint_path.format(net=args.net, epoch=epoch, type='regular'))
writer.close()