-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
169 lines (117 loc) · 6.4 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
import numpy as np
import torch
import torch.backends.cudnn as cudnn
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from nets.yolo import YoloBody
from nets.yolo_training import (YOLOLoss, get_lr_scheduler, set_optimizer_lr,
weights_init)
from utils.callbacks import LossHistory
from utils.dataloader import YoloDataset, yolo_dataset_collate
from utils.utils import get_classes
from utils.utils_fit import fit_one_epoch
if __name__ == "__main__":
Cuda = True
classes_path = 'model_data/cls_classes.txt'
model_path = ''
input_shape = [640, 640]
phi = 'nano'
mosaic = True
Init_Epoch = 0
Freeze_Epoch = 50
Freeze_batch_size = 16
UnFreeze_Epoch = 500
Unfreeze_batch_size = 16
Freeze_Train = False
Init_lr = 1e-2
Min_lr = Init_lr * 0.01
optimizer_type = "sgd"
momentum = 0.937
weight_decay = 5e-4
lr_decay_type = "cos"
save_period = 2
save_dir = 'logs'
num_workers = 4
train_annotation_path = '2007_train.txt'
val_annotation_path = '2007_val.txt'
class_names, num_classes = get_classes(classes_path)
model = YoloBody(num_classes, phi)
weights_init(model)
if model_path != '':
print('Load weights {}.'.format(model_path))
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_dict = model.state_dict()
pretrained_dict = torch.load(model_path, map_location = device)
pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
yolo_loss = YOLOLoss(num_classes)
loss_history = LossHistory(save_dir, model, input_shape=input_shape)
model_train = model.train()
if Cuda:
model_train = torch.nn.DataParallel(model)
cudnn.benchmark = True
model_train = model_train.cuda()
with open(train_annotation_path, encoding='utf-8') as f:
train_lines = f.readlines()
with open(val_annotation_path, encoding='utf-8') as f:
val_lines = f.readlines()
num_train = len(train_lines)
num_val = len(val_lines)
if True:
UnFreeze_flag = False
if Freeze_Train:
for param in model.backbone.parameters():
param.requires_grad = False
batch_size = Freeze_batch_size if Freeze_Train else Unfreeze_batch_size
nbs = 64
Init_lr_fit = max(batch_size / nbs * Init_lr, 3e-4)
Min_lr_fit = max(batch_size / nbs * Min_lr, 3e-6)
pg0, pg1, pg2 = [], [], []
for k, v in model.named_modules():
if hasattr(v, "bias") and isinstance(v.bias, nn.Parameter):
pg2.append(v.bias)
if isinstance(v, nn.BatchNorm2d) or "bn" in k:
pg0.append(v.weight)
elif hasattr(v, "weight") and isinstance(v.weight, nn.Parameter):
pg1.append(v.weight)
optimizer = {
'adam' : optim.Adam(pg0, Init_lr_fit, betas = (momentum, 0.999)),
'sgd' : optim.SGD(pg0, Init_lr_fit, momentum = momentum, nesterov=True)
}[optimizer_type]
optimizer.add_param_group({"params": pg1, "weight_decay": weight_decay})
optimizer.add_param_group({"params": pg2})
lr_scheduler_func = get_lr_scheduler(lr_decay_type, Init_lr_fit, Min_lr_fit, UnFreeze_Epoch)
epoch_step = num_train // batch_size
epoch_step_val = num_val // batch_size
if epoch_step == 0 or epoch_step_val == 0:
raise ValueError("数据集过小,无法继续进行训练,请扩充数据集。")
train_dataset = YoloDataset(train_lines, input_shape, num_classes, epoch_length = UnFreeze_Epoch, mosaic=mosaic, train = True)
val_dataset = YoloDataset(val_lines, input_shape, num_classes, epoch_length = UnFreeze_Epoch, mosaic=False, train = False)
gen = DataLoader(train_dataset, shuffle = True, batch_size = batch_size, num_workers = num_workers, pin_memory=True,
drop_last=True, collate_fn=yolo_dataset_collate)
gen_val = DataLoader(val_dataset , shuffle = True, batch_size = batch_size, num_workers = num_workers, pin_memory=True,
drop_last=True, collate_fn=yolo_dataset_collate)
for epoch in range(Init_Epoch, UnFreeze_Epoch):
if epoch >= Freeze_Epoch and not UnFreeze_flag and Freeze_Train:
batch_size = Unfreeze_batch_size
nbs = 64
Init_lr_fit = max(batch_size / nbs * Init_lr, 3e-4)
Min_lr_fit = max(batch_size / nbs * Min_lr, 3e-6)
lr_scheduler_func = get_lr_scheduler(lr_decay_type, Init_lr_fit, Min_lr_fit, UnFreeze_Epoch)
for param in model.backbone.parameters():
param.requires_grad = True
epoch_step = num_train // batch_size
epoch_step_val = num_val // batch_size
if epoch_step == 0 or epoch_step_val == 0:
raise ValueError("数据集过小,无法继续进行训练,请扩充数据集。")
gen = DataLoader(train_dataset, shuffle = True, batch_size = batch_size, num_workers = num_workers, pin_memory=True,
drop_last=True, collate_fn=yolo_dataset_collate)
gen_val = DataLoader(val_dataset , shuffle = True, batch_size = batch_size, num_workers = num_workers, pin_memory=True,
drop_last=True, collate_fn=yolo_dataset_collate)
UnFreeze_flag = True
gen.dataset.epoch_now = epoch
gen_val.dataset.epoch_now = epoch
set_optimizer_lr(optimizer, lr_scheduler_func, epoch)
fit_one_epoch(model_train, model, yolo_loss, loss_history, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, UnFreeze_Epoch, Cuda, save_period, save_dir)