/
train.py
136 lines (114 loc) · 5.95 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
import os
import math
import argparse
import torch
import torch.optim as optim
import torch.optim.lr_scheduler as lr_scheduler
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
from my_dataset import MyDataSet
from vit_model_res18 import vit_base_patch16_224_in21k as create_model
from utils import train_one_epoch, evaluate
import pandas as pd
import random
import numpy as np
def seed_reproducer(seed=2022):
random.seed(seed)
os.environ["PYTHONHASHSEED"] = str(seed)
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.enabled = True
def main(args):
seed_reproducer(9)
device = torch.device(args.device if torch.cuda.is_available() else "cpu")
if os.path.exists(args.where) is False:
os.makedirs(args.where)
tb_writer = SummaryWriter(args.where[2:])
#train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)
data_transform = {
"train": transforms.Compose([#transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485,0.456,0.406],[0.229,0.224,0.225])]),
"val": transforms.Compose([#transforms.Resize(256),
#transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485,0.456,0.406],[0.229,0.224,0.225])])}
train_dataset = MyDataSet(data=pd.read_csv('./train_split5.csv'),
#images_class=train_images_label,
transforms=data_transform['train'])
val_dataset = MyDataSet(data=pd.read_csv('./test_split5.csv'),
#images_class=val_images_label,
transforms=data_transform['val'])
batch_size = args.batch_size
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
pin_memory=True,
num_workers=nw,)
val_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=batch_size,
shuffle=False,
pin_memory=True,
num_workers=nw,)
model = create_model(num_classes=2, has_logits=False).to(device)
if args.weights != "":
assert os.path.exists(args.weights), "weights file: '{}' not exist.".format(args.weights)
weights_dict = torch.load(args.weights, map_location=device)
del_keys = ['head.weight', 'head.bias'] if model.has_logits \
else ['pre_logits.fc.weight', 'pre_logits.fc.bias', 'head.weight', 'head.bias']
for k in del_keys:
del weights_dict[k]
print(model.load_state_dict(weights_dict, strict=False))
if args.freeze_layers:
for name, para in model.named_parameters():
if "head" not in name and "pre_logits" not in name:
para.requires_grad_(False)
else:
print("training {}".format(name))
pg = [p for p in model.parameters() if p.requires_grad]
optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=5E-5)
lf = lambda x: ((1 + math.cos(x * math.pi / args.epochs)) / 2) * (1 - args.lrf) + args.lrf # cosine
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
for epoch in range(args.epochs):
# train
train_loss, train_acc = train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_loader,
device=device,
epoch=epoch)
scheduler.step()
# validate
val_loss, val_acc = evaluate(model=model,
data_loader=val_loader,
device=device,
epoch=epoch)
tags = ["train_loss", "train_acc", "val_loss", "val_acc", "learning_rate"]
tb_writer.add_scalar(tags[0], train_loss, epoch)
tb_writer.add_scalar(tags[1], train_acc, epoch)
tb_writer.add_scalar(tags[2], val_loss, epoch)
tb_writer.add_scalar(tags[3], val_acc, epoch)
tb_writer.add_scalar(tags[4], optimizer.param_groups[0]["lr"], epoch)
torch.save(model.state_dict(), args.where+"/model-{}.pth".format(epoch))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes', type=int, default=2)
parser.add_argument('--epochs', type=int, default=100)
parser.add_argument('--batch-size', type=int, default=10)
parser.add_argument('--lr', type=float, default=0.00005)
parser.add_argument('--lrf', type=float, default=0.1)
parser.add_argument('--model-name', default='', help='create model name')
parser.add_argument('--weights', type=str, default='',
help='initial weights path')
parser.add_argument('--freeze-layers', type=bool, default=False)
parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')
parser.add_argument('--where', default="./ckpts", help='device id (i.e. 0 or 0,1 or cpu)')
opt = parser.parse_args()
main(opt)