def processing_train(image, pts, image_h, image_w, down_ratio, aug_label,
img_id):
# filter pts ----------------------------------------------------
h, w, c = image.shape
# pts = filter_pts(pts, w, h)
# ---------------------------------------------------------------
data_aug = {
'train':
transform.Compose([
transform.ConvertImgFloat(),
transform.PhotometricDistort(),
transform.Expand(max_scale=1.5, mean=(0, 0, 0)),
transform.RandomMirror_w(),
transform.Resize(h=image_h, w=image_w)
]),
'val':
transform.Compose([
transform.ConvertImgFloat(),
transform.Resize(h=image_h, w=image_w)
])
}
if aug_label:
out_image, pts = data_aug['train'](image.copy(), pts)
else:
out_image, pts = data_aug['val'](image.copy(), pts)
out_image = np.clip(out_image, a_min=0., a_max=255.)
out_image = np.transpose(out_image / 255. - 0.5, (2, 0, 1))
pts = rearrange_pts(pts)
pts2 = transform.rescale_pts(pts, down_ratio=down_ratio)
return np.asarray(out_image, np.float32), pts2
def __init__(self, root, mode='train'):
self.samples = []
lines = os.listdir(os.path.join(root, 'GT'))
for line in lines:
rgbpath = os.path.join(root, 'RGB', line[:-4] + '.jpg')
tpath = os.path.join(root, 'T', line[:-4] + '.jpg')
maskpath = os.path.join(root, 'GT', line)
self.samples.append([rgbpath, tpath, maskpath])
if mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean1=mean_rgb,
mean2=mean_t,
std1=std_rgb,
std2=std_t), transform.Resize(400, 400),
transform.RandomHorizontalFlip(), transform.ToTensor())
elif mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean1=mean_rgb,
mean2=mean_t,
std1=std_rgb,
std2=std_t), transform.Resize(400, 400),
transform.ToTensor())
else:
raise ValueError
def Img_transform(self, name, size, split='train'):
assert (isinstance(size, tuple) and len(size) == 2)
if name in ['CS', 'IDD', 'MAP', 'ADE', 'IDD20K']:
if split == 'train':
t = [ #transforms.RandomScale(1.1),
#transforms.RandomRotate(3),
#transforms.Resize((640,640)),
#RandomAffine(1,(0.04,0.04),None,1,resample=Image.NEAREST,fillcolor=255),
#Resize((512,512),Image.NEAREST),
#RandomHorizontalFlip(),
#ToTensor()
transforms.Resize(size),
#transforms.RandomCrop((512,512)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
if split == 'train':
t = [
transforms.Resize(size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
def Img_transform(self, name, size, split='train'):
# if len(args.crop_size) == 1:
# crop_size = (args.crop_size[0] , args.crop_size[0]) ## W x H
# else:
# crop_size = (args.crop_size[1] , args.crop_size[0])
assert (isinstance(size, tuple) and len(size) == 2)
if name in ['CS', 'IDD']:
if split == 'train':
t = [
transforms.Resize(size),
transforms.RandomCrop((512, 512)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
if split == 'train':
t = [
transforms.Resize(size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
def __init__(self, data, labels, is_train=True):
super(Cifar10, self).__init__()
self.data, self.labels = data, labels
self.is_train = is_train
assert len(self.data) == len(self.labels)
mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616)
if is_train:
self.trans_weak = T.Compose([
T.Resize((32, 32)),
T.PadandRandomCrop(border=4, cropsize=(32, 32)),
T.RandomHorizontalFlip(p=0.5),
T.Normalize(mean, std),
T.ToTensor(),
])
self.trans_strong = T.Compose([
T.Resize((32, 32)),
T.PadandRandomCrop(border=4, cropsize=(32, 32)),
T.RandomHorizontalFlip(p=0.5),
RandomAugment(2, 10),
T.Normalize(mean, std),
T.ToTensor(),
])
else:
self.trans = T.Compose([
T.Resize((32, 32)),
T.Normalize(mean, std),
T.ToTensor(),
])
def load_PD_dataset():
tr = t.Transforms(
(t.MagPhase(), t.PickChannel(0), t.Resize((1, 256, 256, 60, 8))),
apply_to='image')
tr = MultiModule((tr, t.ToTensor()))
test = Split2d(PdDataset('../data/PD', transform=tr))
return test
def __init__(self,
imgs_dir,
masks_dir,
scale=1,
size=96,
mask_suffix='_segmentation'):
print(imgs_dir)
print(masks_dir)
self.imgs_dir = imgs_dir
self.masks_dir = masks_dir
self.scale = scale
self.mask_suffix = mask_suffix
self.size = size
assert 0 < scale <= 1, 'Scale must be between 0 and 1'
self.ids = [
splitext(file)[0] for file in listdir(imgs_dir)
if not file.startswith('.') and file.endswith('.jpg')
]
logging.info(f'Creating dataset with {len(self.ids)} examples')
self.transform = transform.Compose([
# transforms.RandomHorizontalFlip(),
# transform.RandomRotation(degrees=20),
# transforms.RandomGrayscale(p=0.1),
# transform.RandomResizedCrop(scale=(0.75, 1.25), size=size),
transform.Resize([size, size]),
# transforms.ToTensor(),
# transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[1.0, 1.0, 1.0])
])
def __init__(self, cfg):
self.cfg = cfg
if self.cfg.mode == 'train':
self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(size=512),
transform.RandomRotate(-15, 15),
transform.RandomCrop(448, 448),
transform.RandomHorizontalFlip(),
transform.RandomMask(),
transform.ToTensor())
elif self.cfg.mode == 'val' or self.cfg.mode == 'test':
self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(size=512),
transform.ToTensor())
else:
raise ValueError
def __init__(self, cfg):
with open(cfg.datapath + '/' + cfg.mode + '.txt', 'r') as lines:
self.samples = []
for line in lines:
imagepath = cfg.datapath + '/image/' + line.strip() + '.jpg'
maskpath = cfg.datapath + '/scribble/' + line.strip() + '.png'
self.samples.append([imagepath, maskpath])
if cfg.mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.RandomHorizontalFlip(),
transform.RandomCrop(320, 320), transform.ToTensor())
elif cfg.mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.ToTensor())
else:
raise ValueError
def __init__(self, device="cuda:1"):
picfile = str(time.strftime("%Y%m%d"))
self.todaypath = os.path.join('/workspace/nologopics', picfile)
if not os.path.exists(self.todaypath):
os.mkdir(self.todaypath)
self.device = torch.device(device)
# logo检测模型
backbone = Backbone()
self.ssdmodel = SSD300(backbone=backbone, num_classes=2)
modelpath = './weights/ssd300-best.pth'
weights_dict = torch.load(modelpath, map_location=device)
self.ssdmodel.load_state_dict(weights_dict, strict=False)
json_file = open('./pascal_voc_classes.json', 'r')
class_dict = json.load(json_file)
self.category_index = {v: k for k, v in class_dict.items()}
self.data_transforms = transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
# 水印字体
self.font = ImageFont.truetype("./src/msyh.TTF", 24, encoding="utf-8")
# 爬虫网址
self.spiderurl = {
#clear_log
2: {
'url': 'http://adsoc.qknode.com/adagent/material/material?',
'topic': ["清理", "日历", "天气"]
},
0: {
'url': 'http://adsoc.qknode.com/adagent/material/center/rank?',
'topic': ["清理", "日历", "天气", "教育"]
},
# 排行榜
1: {
'url': 'http://adsoc.qknode.com/adagent/material/material?',
'topic': ["清理", "日历", "天气"]
}
# 素材洞察
}
# 推送地址
self.finalurl = 'http://adsoc.qknode.com/adagent/material/center/push'
# self.cnniqamodel = CNNIQAnet(ker_size=7, n_kers=50, n1_nodes=800, n2_nodes=800)
# self.cnniqamodel.load_state_dict(torch.load('./weights/CNNIQA-LIVE.pth',map_location=device))
if device != 'cpu':
# self.cnniqamodel = self.cnniqamodel.to(self.device)
# self.cnniqamodel.eval()
self.ssdmodel = self.ssdmodel.to(self.device)
self.ssdmodel.eval()
def __init__(self, cfg):
with open(os.path.join(cfg.datapath, cfg.mode + '.txt'), 'r') as lines:
self.samples = []
for line in lines:
imagepath = os.path.join(cfg.datapath, 'image',
line.strip() + '.jpg')
maskpath = os.path.join(cfg.datapath, 'mask',
line.strip() + '.png')
self.samples.append([imagepath, maskpath])
if cfg.mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.RandomHorizontalFlip(),
transform.RandomCrop(288, 288), transform.ToTensor())
elif cfg.mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.ToTensor())
else:
raise ValueError
def __init__(self, root, mode='train'):
self.samples = []
lines = os.listdir(os.path.join(root, mode + '_images'))
self.mode = mode
for line in lines:
rgbpath = os.path.join(root, mode + '_images', line)
tpath = os.path.join(root, mode + '_depth', line[:-4] + '.png')
maskpath = os.path.join(root, mode + '_masks', line[:-4] + '.png')
self.samples.append([rgbpath, tpath, maskpath])
if mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean1=mean_rgb, std1=std_rgb),
transform.Resize(256, 256), transform.RandomHorizontalFlip(),
transform.ToTensor())
elif mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean1=mean_rgb, std1=std_rgb),
transform.Resize(256, 256), transform.ToTensor())
else:
raise ValueError
def __init__(self, data, labels, is_train=True):
super(Cifar10, self).__init__()
self.data, self.labels = data, labels
self.is_train = is_train
assert len(self.data) == len(self.labels)
mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616)
# mean, std = (-0.0172, -0.0356, -0.1069), (0.4940, 0.4869, 0.5231) # [-1, 1]
if is_train:
self.trans_reg = transforms.Compose([
transforms.RandomResizedCrop(32),
transforms.RandomHorizontalFlip(p=0.5),
transforms.RandomApply(
[transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)], p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
transforms.Normalize([0.4914, 0.4822, 0.4465],
[0.2023, 0.1994, 0.2010])
])
self.trans_weak = T.Compose([
T.Resize((32, 32)),
T.PadandRandomCrop(border=4, cropsize=(32, 32)),
T.RandomHorizontalFlip(p=0.5),
T.Normalize(mean, std),
T.ToTensor(),
])
self.trans_strong = T.Compose([
T.Resize((32, 32)),
T.PadandRandomCrop(border=4, cropsize=(32, 32)),
T.RandomHorizontalFlip(p=0.5),
RandomAugment(2, 10),
T.Normalize(mean, std),
T.ToTensor(),
])
else:
self.trans = T.Compose([
T.Resize((32, 32)),
T.Normalize(mean, std),
T.ToTensor(),
])
def __init__(self, data, labels, n_guesses=1, is_train=True):
super(Cifar10, self).__init__()
self.data, self.labels = data, labels
self.n_guesses = n_guesses
assert len(self.data) == len(self.labels)
assert self.n_guesses >= 1
# mean, std = (0.4914, 0.4822, 0.4465), (0.2471, 0.2435, 0.2616) # [0, 1]
mean, std = (-0.0172, -0.0356, -0.1069), (0.4940, 0.4869, 0.5231
) # [-1, 1]
if is_train:
self.trans = T.Compose([
T.Resize((32, 32)),
T.PadandRandomCrop(border=4, cropsize=(32, 32)),
T.RandomHorizontalFlip(p=0.5),
T.Normalize(mean, std),
T.ToTensor(),
])
else:
self.trans = T.Compose([
T.Resize((32, 32)),
T.Normalize(mean, std),
T.ToTensor(),
])
def main(args):
print(args)
# mp.spawn(main_worker, args=(args,), nprocs=args.world_size, join=True)
init_distributed_mode(args)
device = torch.device(args.device)
results_file = "results{}.txt".format(
datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
# Data loading code
print("Loading data")
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
VOC_root = args.data_path
# check voc root
if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False:
raise FileNotFoundError(
"VOCdevkit dose not in path:'{}'.".format(VOC_root))
# load train data set
train_data_set = VOC2012DataSet(VOC_root,
data_transform["train"],
train_set='train.txt')
# load validation data set
val_data_set = VOC2012DataSet(VOC_root,
data_transform["val"],
train_set='val.txt')
print("Creating data loaders")
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(
train_data_set)
test_sampler = torch.utils.data.distributed.DistributedSampler(
val_data_set)
else:
train_sampler = torch.utils.data.RandomSampler(train_data_set)
test_sampler = torch.utils.data.SequentialSampler(val_data_set)
if args.aspect_ratio_group_factor >= 0:
# 统计所有图像比例在bins区间中的位置索引
group_ids = create_aspect_ratio_groups(
train_data_set, k=args.aspect_ratio_group_factor)
train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids,
args.batch_size)
else:
train_batch_sampler = torch.utils.data.BatchSampler(train_sampler,
args.batch_size,
drop_last=True)
data_loader = torch.utils.data.DataLoader(
train_data_set,
batch_sampler=train_batch_sampler,
num_workers=args.workers,
collate_fn=train_data_set.collate_fn)
data_loader_test = torch.utils.data.DataLoader(
val_data_set,
batch_size=1,
sampler=test_sampler,
num_workers=args.workers,
collate_fn=train_data_set.collate_fn)
print("Creating model")
model = create_model(num_classes=args.num_classes + 1, device=device)
model_without_ddp = model
if args.distributed:
model = torch.nn.parallel.DistributedDataParallel(
model, device_ids=[args.gpu])
model_without_ddp = model.module
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=args.lr_step_size,
gamma=args.lr_gamma)
# lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=args.lr_steps, gamma=args.lr_gamma)
# 如果传入resume参数，即上次训练的权重地址，则接着上次的参数训练
if args.resume:
# If map_location is missing, torch.load will first load the module to CPU
# and then copy each parameter to where it was saved,
# which would result in all processes on the same machine using the same set of devices.
checkpoint = torch.load(
args.resume, map_location='cpu') # 读取之前保存的权重文件(包括优化器以及学习率策略)
model_without_ddp.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
args.start_epoch = checkpoint['epoch'] + 1
if args.test_only:
utils.evaluate(model, data_loader_test, device=device)
return
train_loss = []
learning_rate = []
val_map = []
print("Start training")
start_time = time.time()
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
mean_loss, lr = utils.train_one_epoch(model, optimizer, data_loader,
device, epoch, args.print_freq)
# only first process to save training info
if args.rank in [-1, 0]:
train_loss.append(mean_loss.item())
learning_rate.append(lr)
# update learning rate
lr_scheduler.step()
# evaluate after every epoch
coco_info = utils.evaluate(model, data_loader_test, device=device)
if args.rank in [-1, 0]:
# write into txt
with open(results_file, "a") as f:
result_info = [
str(round(i, 4))
for i in coco_info + [mean_loss.item(), lr]
]
txt = "epoch:{} {}".format(epoch, ' '.join(result_info))
f.write(txt + "\n")
val_map.append(coco_info[1]) # pascal mAP
if args.output_dir:
# 只在主节点上执行保存权重操作
save_on_master(
{
'model': model_without_ddp.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'args': args,
'epoch': epoch
}, os.path.join(args.output_dir, 'model_{}.pth'.format(epoch)))
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))
if args.rank in [-1, 0]:
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
def main(parser_data):
device = torch.device(
parser_data.device if torch.cuda.is_available() else "cpu")
print(device)
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
night_root = parser_data.data_path
train_dataset = NightDataSet(night_root,
data_transform['train'],
train_set='train.txt')
# aa = train_dataset[1]
# 注意训练时，batch_size必须大于1
train_data_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=8,
shuffle=True,
num_workers=4,
collate_fn=utils.collate_fn)
val_dataset = NightDataSet(night_root,
data_transform['val'],
train_set='val.txt')
# bb = val_dataset[2]
val_data_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=4,
shuffle=False,
num_workers=0,
collate_fn=utils.collate_fn)
model = create_model(num_classes=3, device=device)
print(model)
model.to(device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.005,
momentum=0.9,
weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.5)
# 如果指定了上次训练保存的权重文件地址，则接着上次结果接着训练
if parser_data.resume != "":
checkpoint = torch.load(parser_data.resume)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
parser_data.start_epoch = checkpoint['epoch'] + 1
print("the training process from epoch{}...".format(
parser_data.start_epoch))
train_loss = []
learning_rate = []
val_map = []
train_val_map = []
val_data = None
# 如果电脑内存充裕，可提前加载验证集数据，以免每次验证时都要重新加载一次数据，节省时间
# val_data = get_coco_api_from_dataset(val_data_loader.dataset)
for epoch in range(parser_data.start_epoch, parser_data.epochs):
utils.train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_data_loader,
device=device,
epoch=epoch,
print_freq=50,
train_loss=train_loss,
train_lr=learning_rate)
lr_scheduler.step()
if epoch >= 20 or epoch == 10:
utils.evaluate(model=model,
data_loader=val_data_loader,
device=device,
data_set=val_data,
mAP_list=val_map)
# save weights
save_files = {
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch
}
torch.save(save_files, "./save_weights/ssd512-{}.pth".format(epoch))
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
import transform as T
import numpy as np
import torchvision
import torch
print(torch.__version__)
print(torchvision.__version__)
normalize = T.Normalize(mean=[0.43216, 0.394666, 0.37645],
std=[0.22803, 0.22145, 0.216989])
# def normalize(tensor):
# # Subtract the mean, and scale to the interval [-1,1]
# tensor_minusmean = tensor - tensor.mean()
# return tensor_minusmean/tensor_minusmean.abs().max()
transform_video = torchvision.transforms.Compose([
T.ToFloatTensorInZeroOne(),
T.Resize((128, 171)),
T.RandomHorizontalFlip(), normalize,
T.RandomCrop((112, 112))
])
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
root = ET.parse(
'/root/yangsen-data/LIRIS-ACCEDE-movies/ACCEDEmovies.xml').getroot()
movie_length = {}
def get_sec(time_str: str) -> int:
"""Get Seconds from time."""
h, m, s = time_str.split(':')
return int(h) * 3600 + int(m) * 60 + int(s)
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend='gloo',
init_method='env://')
synchronize()
device = 'cuda'
train_trans = transform.Compose([
transform.RandomResize(args.train_min_size_range, args.train_max_size),
transform.RandomHorizontalFlip(0.5),
transform.ToTensor(),
transform.Normalize(args.pixel_mean, args.pixel_std)
])
valid_trans = transform.Compose([
transform.Resize(args.test_min_size, args.test_max_size),
transform.ToTensor(),
transform.Normalize(args.pixel_mean, args.pixel_std)
])
train_set = COCODataset(args.path, 'train', train_trans)
valid_set = COCODataset(args.path, 'val', valid_trans)
# backbone = vovnet39(pretrained=True)
# backbone = vovnet57(pretrained=True)
# backbone = resnet18(pretrained=True)
backbone = resnet50(pretrained=True)
#backbone = resnet101(pretrained=True)
model = ATSS(args, backbone)
model = model.to(device)
def main(parser_data):
device = torch.device(
parser_data.device if torch.cuda.is_available() else "cpu")
print(device)
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
XRay_root = parser_data.data_path
train_dataset = XRayDataset(XRay_root,
data_transform['train'],
train_set='train.txt')
# Note that the batch_size must be greater than 1
train_data_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=8,
shuffle=True,
num_workers=4,
collate_fn=utils.collate_fn)
val_dataset = XRayDataset(XRay_root,
data_transform['val'],
train_set='val.txt')
val_data_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=1,
shuffle=False,
num_workers=0,
collate_fn=utils.collate_fn)
model = create_model(num_classes=6, device=device)
model.to(device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.0005,
momentum=0.9,
weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.3)
# If the address of the weight file saved by the last training is specified, the training continues with the last result
if parser_data.resume != "":
checkpoint = torch.load(parser_data.resume)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
parser_data.start_epoch = checkpoint['epoch'] + 1
print("the training process from epoch{}...".format(
parser_data.start_epoch))
train_loss = []
learning_rate = []
val_map = []
val_data = None
# If your computer has sufficient memory, you can save time by loading the validation set data in advance to avoid having to reload the data each time you validate
# val_data = get_coco_api_from_dataset(val_data_loader.dataset)
for epoch in range(parser_data.start_epoch, parser_data.epochs):
utils.train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_data_loader,
device=device,
epoch=epoch,
print_freq=50,
train_loss=train_loss,
train_lr=learning_rate)
lr_scheduler.step()
utils.evaluate(model=model,
data_loader=val_data_loader,
device=device,
data_set=val_data,
mAP_list=val_map)
# save weights
save_files = {
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch
}
torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch))
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
# read class_indict
category_index = {}
try:
json_file = open('./pascal_voc_classes.json', 'r')
class_dict = json.load(json_file)
category_index = {v: k for k, v in class_dict.items()}
except Exception as e:
print(e)
exit(-1)
# load image
original_img = Image.open("./test/test21.jpeg")
# from pil image to tensor, do not normalize image
data_transform = transform.Compose([transform.Resize(),
transform.ToTensor(),
transform.Normalization()])
img, _ = data_transform(original_img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
model.eval()
with torch.no_grad():
predictions = model(img.to(device))[0] # bboxes_out, labels_out, scores_out
predict_boxes = predictions[0].to("cpu").numpy()
predict_boxes[:, [0, 2]] = predict_boxes[:, [0, 2]] * original_img.size[0]
predict_boxes[:, [1, 3]] = predict_boxes[:, [1, 3]] * original_img.size[1]
predict_classes = predictions[1].to("cpu").numpy()
predict_scores = predictions[2].to("cpu").numpy()
def main(args):
print(args)
# mp.spawn(main_worker, args=(args,), nprocs=args.world_size, join=True)
utils.init_distributed_mode(args)
device = torch.device(args.device)
# Data loading code
print("Loading data")
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
# transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
VOC_root = args.data_path
# load train data set
train_data_set = VOC2012DataSet(VOC_root, data_transform["train"], True)
# load validation data set
val_data_set = VOC2012DataSet(VOC_root, data_transform["val"], False)
print("Creating data loaders")
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(
train_data_set)
test_sampler = torch.utils.data.distributed.DistributedSampler(
val_data_set)
else:
train_sampler = torch.utils.data.RandomSampler(train_data_set)
test_sampler = torch.utils.data.SequentialSampler(val_data_set)
if args.aspect_ratio_group_factor >= 0:
# 统计所有图像比例在bins区间中的位置索引
group_ids = create_aspect_ratio_groups(
train_data_set, k=args.aspect_ratio_group_factor)
train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids,
args.batch_size)
else:
train_batch_sampler = torch.utils.data.BatchSampler(train_sampler,
args.batch_size,
drop_last=True)
data_loader = torch.utils.data.DataLoader(
train_data_set,
batch_sampler=train_batch_sampler,
num_workers=args.workers,
collate_fn=utils.collate_fn)
data_loader_test = torch.utils.data.DataLoader(val_data_set,
batch_size=4,
sampler=test_sampler,
num_workers=args.workers,
collate_fn=utils.collate_fn)
print("Creating model")
model = create_model(num_classes=21)
model.to(device)
model_without_ddp = model
if args.distributed:
model = torch.nn.parallel.DistributedDataParallel(
model, device_ids=[args.gpu])
model_without_ddp = model.module
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=args.lr_step_size,
gamma=args.lr_gamma)
# lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=args.lr_steps, gamma=args.lr_gamma)
# 如果传入resume参数，即上次训练的权重地址，则接着上次的参数训练
if args.resume:
# If map_location is missing, torch.load will first load the module to CPU
# and then copy each parameter to where it was saved,
# which would result in all processes on the same machine using the same set of devices.
checkpoint = torch.load(
args.resume, map_location='cpu') # 读取之前保存的权重文件(包括优化器以及学习率策略)
model_without_ddp.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
args.start_epoch = checkpoint['epoch'] + 1
if args.test_only:
utils.evaluate(model, data_loader_test, device=device)
return
print("Start training")
start_time = time.time()
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
utils.train_one_epoch(model, optimizer, data_loader, device, epoch,
args.print_freq)
lr_scheduler.step()
if args.output_dir:
# 只在主节点上执行保存权重操作
utils.save_on_master(
{
'model': model_without_ddp.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'args': args,
'epoch': epoch
}, os.path.join(args.output_dir, 'model_{}.pth'.format(epoch)))
# evaluate after every epoch
utils.evaluate(model, data_loader_test, device=device)
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))
def main():
# get devices
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
# create model
# 目标检测数 + 背景
num_classes = 20 + 1
model = create_model(num_classes=num_classes)
# load train weights
train_weights = "./save_weights/ssd300-14.pth"
train_weights_dict = torch.load(train_weights,
map_location=device)['model']
model.load_state_dict(train_weights_dict)
model.to(device)
# read class_indict
json_path = "./pascal_voc_classes.json"
assert os.path.exists(json_path), "file '{}' dose not exist.".format(
json_path)
json_file = open(json_path, 'r')
class_dict = json.load(json_file)
category_index = {v: k for k, v in class_dict.items()}
# load image
original_img = Image.open("./test.jpg")
# from pil image to tensor, do not normalize image
data_transform = transform.Compose(
[transform.Resize(),
transform.ToTensor(),
transform.Normalization()])
img, _ = data_transform(original_img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
model.eval()
with torch.no_grad():
# initial model
init_img = torch.zeros((1, 3, 300, 300), device=device)
model(init_img)
time_start = time_synchronized()
predictions = model(
img.to(device))[0] # bboxes_out, labels_out, scores_out
time_end = time_synchronized()
print("inference+NMS time: {}".format(time_end - time_start))
predict_boxes = predictions[0].to("cpu").numpy()
predict_boxes[:,
[0, 2]] = predict_boxes[:, [0, 2]] * original_img.size[0]
predict_boxes[:,
[1, 3]] = predict_boxes[:, [1, 3]] * original_img.size[1]
predict_classes = predictions[1].to("cpu").numpy()
predict_scores = predictions[2].to("cpu").numpy()
if len(predict_boxes) == 0:
print("没有检测到任何目标!")
draw_box(original_img,
predict_boxes,
predict_classes,
predict_scores,
category_index,
thresh=0.5,
line_thickness=5)
plt.imshow(original_img)
plt.show()
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
data_transform = {
"train": transform.Compose([transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()]),
"val": transform.Compose([transform.Resize(),
transform.ToTensor(),
transform.Normalization()])
}
voc_path = "../"
train_dataset = VOC2012DataSet(voc_path, data_transform['train'], True)
# 注意训练时，batch_size必须大于1
train_data_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=8,
shuffle=True,
num_workers=0,
collate_fn=utils.collate_fn)
val_dataset = VOC2012DataSet(voc_path, data_transform['val'], False)
val_data_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=1,
shuffle=False,
num_workers=0,
collate_fn=utils.collate_fn)
model = create_model(num_classes=21, device=device)
model.to(device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.002,
momentum=0.9, weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.3)
train_loss = []
learning_rate = []
val_map = []
val_data = None
# 如果电脑内存充裕，可提前加载验证集数据，以免每次验证时都要重新加载一次数据，节省时间
# val_data = get_coco_api_from_dataset(val_data_loader.dataset)
for epoch in range(20):
utils.train_one_epoch(model=model, optimizer=optimizer,
data_loader=train_data_loader,
device=device, epoch=epoch,
print_freq=50, train_loss=train_loss,
train_lr=learning_rate, warmup=True)
lr_scheduler.step()
utils.evaluate(model=model, data_loader=val_data_loader,
device=device, data_set=val_data, mAP_list=val_map)
# save weights
save_files = {
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch}
torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch))
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
def main(parser_data):
device = torch.device(
parser_data.device if torch.cuda.is_available() else "cpu")
print("Using {} device training.".format(device.type))
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
results_file = "results{}.txt".format(
datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
VOC_root = parser_data.data_path
# check voc root
if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False:
raise FileNotFoundError(
"VOCdevkit dose not in path:'{}'.".format(VOC_root))
train_dataset = VOC2012DataSet(VOC_root,
data_transform['train'],
train_set='train.txt')
# 注意训练时，batch_size必须大于1
batch_size = parser_data.batch_size
assert batch_size > 1, "batch size must be greater than 1"
# 防止最后一个batch_size=1，如果最后一个batch_size=1就舍去
drop_last = True if len(train_dataset) % batch_size == 1 else False
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using %g dataloader workers' % nw)
train_data_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=nw,
collate_fn=train_dataset.collate_fn,
drop_last=drop_last)
val_dataset = VOC2012DataSet(VOC_root,
data_transform['val'],
train_set='val.txt')
val_data_loader = torch.utils.data.DataLoader(
val_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
model = create_model(num_classes=args.num_classes + 1, device=device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.0005,
momentum=0.9,
weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.3)
# 如果指定了上次训练保存的权重文件地址，则接着上次结果接着训练
if parser_data.resume != "":
checkpoint = torch.load(parser_data.resume)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
parser_data.start_epoch = checkpoint['epoch'] + 1
print("the training process from epoch{}...".format(
parser_data.start_epoch))
train_loss = []
learning_rate = []
val_map = []
# 提前加载验证集数据，以免每次验证时都要重新加载一次数据，节省时间
val_data = get_coco_api_from_dataset(val_data_loader.dataset)
for epoch in range(parser_data.start_epoch, parser_data.epochs):
mean_loss, lr = utils.train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_data_loader,
device=device,
epoch=epoch,
print_freq=50)
train_loss.append(mean_loss.item())
learning_rate.append(lr)
# update learning rate
lr_scheduler.step()
coco_info = utils.evaluate(model=model,
data_loader=val_data_loader,
device=device,
data_set=val_data)
# write into txt
with open(results_file, "a") as f:
result_info = [
str(round(i, 4)) for i in coco_info + [mean_loss.item(), lr]
]
txt = "epoch:{} {}".format(epoch, ' '.join(result_info))
f.write(txt + "\n")
val_map.append(coco_info[1]) # pascal mAP
# save weights
save_files = {
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch
}
torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch))
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
def main(parser_data):
device = torch.device(
parser_data.device if torch.cuda.is_available() else "cpu")
print("Using {} device training.".format(device.type))
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
data_transform = {
"train":
transform.Compose([
transform.SSDCropping(),
transform.Resize(),
transform.ColorJitter(),
transform.ToTensor(),
transform.RandomHorizontalFlip(),
transform.Normalization(),
transform.AssignGTtoDefaultBox()
]),
"val":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
VOC_root = parser_data.data_path
# check voc root
if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False:
raise FileNotFoundError(
"VOCdevkit dose not in path:'{}'.".format(VOC_root))
train_dataset = VOC2012DataSet(VOC_root,
data_transform['train'],
train_set='train.txt')
# 注意训练时，batch_size必须大于1
batch_size = parser_data.batch_size
assert batch_size > 1, "batch size must be greater than 1"
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0,
8]) # number of workers
print('Using %g dataloader workers' % nw)
train_data_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
val_dataset = VOC2012DataSet(VOC_root,
data_transform['val'],
train_set='val.txt')
val_data_loader = torch.utils.data.DataLoader(
val_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
model = create_model(num_classes=21, device=device)
model.to(device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.0005,
momentum=0.9,
weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.3)
# 如果指定了上次训练保存的权重文件地址，则接着上次结果接着训练
if parser_data.resume != "":
checkpoint = torch.load(parser_data.resume)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
parser_data.start_epoch = checkpoint['epoch'] + 1
print("the training process from epoch{}...".format(
parser_data.start_epoch))
train_loss = []
learning_rate = []
val_map = []
val_data = None
# 如果电脑内存充裕，可提前加载验证集数据，以免每次验证时都要重新加载一次数据，节省时间
# val_data = get_coco_api_from_dataset(val_data_loader.dataset)
for epoch in range(parser_data.start_epoch, parser_data.epochs):
utils.train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_data_loader,
device=device,
epoch=epoch,
print_freq=50,
train_loss=train_loss,
train_lr=learning_rate)
lr_scheduler.step()
utils.evaluate(model=model,
data_loader=val_data_loader,
device=device,
data_set=val_data,
mAP_list=val_map)
# save weights
save_files = {
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'lr_scheduler': lr_scheduler.state_dict(),
'epoch': epoch
}
torch.save(save_files, "./save_weights/ssd300-{}.pth".format(epoch))
# plot loss and lr curve
if len(train_loss) != 0 and len(learning_rate) != 0:
from plot_curve import plot_loss_and_lr
plot_loss_and_lr(train_loss, learning_rate)
# plot mAP curve
if len(val_map) != 0:
from plot_curve import plot_map
plot_map(val_map)
# read class_indict
category_index = {}
try:
json_file = open('./pascal_voc_classes.json', 'r')
class_dict = json.load(json_file)
category_index = {v: k for k, v in class_dict.items()}
except Exception as e:
print(e)
exit(-1)
# load image
original_img = Image.open("./test.jpg")
# from pil image to tensor, do not normalize image
data_transform = transform.Compose(
[transform.Resize(),
transform.ToTensor(),
transform.Normalization()])
img, _ = data_transform(original_img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
model.eval()
with torch.no_grad():
predictions = model(
img.to(device))[0] # bboxes_out, labels_out, scores_out
predict_boxes = predictions[0].to("cpu").numpy()
predict_boxes[:, [0, 2]] = predict_boxes[:, [0, 2]] * original_img.size[0]
predict_boxes[:, [1, 3]] = predict_boxes[:, [1, 3]] * original_img.size[1]
predict_classes = predictions[1].to("cpu").numpy()
predict_scores = predictions[2].to("cpu").numpy()
def __init__(self, cfg):
# NJUD: depth:*.jpg, gt:*.png, rgb:*.jpg
# NLPR: depth:*.jpg, gt:*.jpg, rgb:*.jpg
self.samples = []
self.mode = cfg.mode
if cfg.mode == "train":
with open(osp.join(cfg.datapath, "NLPR_score.pkl"), "rb") as fin:
nlpr_data = pickle.load(fin)
with open(osp.join(cfg.datapath, "NJUD_score.pkl"), "rb") as fin:
njud_data = pickle.load(fin)
with open(osp.join(cfg.datapath, "NLPR", cfg.mode + '.txt'),
'r') as lines:
for line in lines:
line = line.strip()
image_name = osp.join(cfg.datapath, "NLPR/rgb",
line + ".jpg")
depth_name = osp.join(cfg.datapath, "NLPR/depth",
line + ".jpg")
ostu_rgb_name = osp.join(cfg.datapath, "NLPR/ostu_rgb",
line + ".jpg")
mask_name = osp.join(cfg.datapath, "NLPR/gt",
line + ".jpg")
#self.samples.append([image_name, ostu_rgb_name, mask_name])
key = nlpr_data[line]['f_beta']
self.samples.append(
[key, image_name, depth_name, mask_name])
with open(osp.join(cfg.datapath, "NJUD", cfg.mode + '.txt'),
'r') as lines:
for line in lines:
line = line.strip()
image_name = osp.join(cfg.datapath, "NJUD/rgb",
line + ".jpg")
depth_name = osp.join(cfg.datapath, "NJUD/depth",
line + ".jpg")
ostu_rgb_name = osp.join(cfg.datapath, "NJUD/ostu_rgb",
line + ".jpg")
mask_name = osp.join(cfg.datapath, "NJUD/gt",
line + ".png")
#self.samples.append([image_name, ostu_rgb_name, mask_name])
key = njud_data[line]['f_beta']
self.samples.append(
[key, image_name, depth_name, mask_name])
"""
with open(osp.join(cfg.datapath, "train.txt"), "r") as fin:
for line in fin:
line = line.strip()
image_name = osp.join(cfg.datapath, "input_train", line+".jpg")
depth_name = osp.join(cfg.datapath, "depth_train", line+".png")
mask_name = osp.join(cfg.datapath, "gt_train", line+".png")
self.samples.append([image_name, depth_name, mask_name])
"""
print("train mode: len(samples):%s" % (len(self.samples)))
else:
#LFSD,NJUD,NLPR,STEREO797
#image, depth: *.jpg, mask:*.png
def read_test(name):
samples = []
with open(osp.join(cfg.datapath, "test.txt"), "r") as lines:
for line in lines:
line = line.strip()
image_name = osp.join(cfg.datapath, "image",
line + ".jpg")
depth_name = osp.join(cfg.datapath, "depth",
line + ".jpg")
ostu_rgb_name = osp.join(cfg.datapath, "ostu_rgb",
line + ".jpg")
mask_name = osp.join(cfg.datapath, "mask",
line + ".png")
samples.append(
[line, image_name, depth_name, mask_name])
return samples
db_name = cfg.datapath.rstrip().split("/")[-1]
self.samples = read_test(db_name)
print("test mode name:%s, len(samples):%s" %
(db_name, len(self.samples)))
if cfg.mode == 'train':
if cfg.train_scales is None:
cfg.train_scales = [224, 256, 320]
print("Train_scales:", cfg.train_scales)
self.transform = transform.Compose(
transform.MultiResize(cfg.train_scales),
transform.MultiRandomHorizontalFlip(),
transform.MultiNormalize(), transform.MultiToTensor())
elif cfg.mode == 'test':
self.transform = transform.Compose(
transform.Resize((256, 256)),
transform.Normalize(mean=cfg.mean,
std=cfg.std,
d_mean=cfg.d_mean,
d_std=cfg.d_std),
transform.ToTensor(depth_gray=True))
else:
raise ValueError
def main(parser_data):
device = torch.device(
parser_data.device if torch.cuda.is_available() else "cpu")
print(device)
if not os.path.exists("save_weights"):
os.mkdir("save_weights")
data_transform = {
"test":
transform.Compose([
transform.Resize(),
transform.ToTensor(),
transform.Normalization()
])
}
night_root = parser_data.data_path
test_dataset = NightDataSet(night_root,
data_transform['test'],
train_set='test.txt')
test_data_loader = torch.utils.data.DataLoader(test_dataset,
batch_size=4,
shuffle=False,
num_workers=0,
collate_fn=utils.collate_fn)
model = create_model(num_classes=3, device=device)
print(model)
model.to(device)
# define optimizer
params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params,
lr=0.005,
momentum=0.9,
weight_decay=0.0005)
# learning rate scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=0.5)
# 如果指定了上次训练保存的权重文件地址，则接着上次结果接着训练
if parser_data.resume != "":
checkpoint = torch.load(parser_data.resume)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
parser_data.start_epoch = checkpoint['epoch'] + 1
print("the training process from epoch{}...".format(
parser_data.start_epoch))
test_val_map = []
val_data = None
for epoch in range(parser_data.start_epoch, parser_data.epochs):
utils.evaluate(model=model,
data_loader=test_data_loader,
device=device,
data_set=val_data,
mAP_list=test_val_map)
def main():
#数据集加载
dataset = Market1501()
#训练数据处理器
transform_train = T.Compose([
T.Random2DTransform(height, width), #尺度统一，随机裁剪
T.RandomHorizontalFlip(), #水平翻转
T.ToTensor(), #图片转张量
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224,
0.225]), #归一化，参数固定
])
#测试数据处理器
transform_test = T.Compose([
T.Resize((height, width)), #尺度统一
T.ToTensor(), #图片转张量
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224,
0.225]), #归一化，参数固定
])
#train数据集吞吐器
train_data_loader = DataLoader(
ImageDataset(dataset.train,
transform=transform_train), #自定义的数据集，使用训练数据处理器
batch_size=train_batch_size, #一个批次的大小（一个批次有多少个图片张量）
drop_last=True, #丢弃最后无法称为一整个批次的数据
)
print("train_data_loader inited")
#query数据集吞吐器
query_data_loader = DataLoader(
ImageDataset(dataset.query,
transform=transform_test), #自定义的数据集，使用测试数据处理器
batch_size=test_batch_size, #一个批次的大小（一个批次有多少个图片张量）
shuffle=False, #不重排
drop_last=True, #丢弃最后无法称为一整个批次的数据
)
print("query_data_loader inited")
#gallery数据集吞吐器
gallery_data_loader = DataLoader(
ImageDataset(dataset.gallery,
transform=transform_test), #自定义的数据集，使用测试数据处理器
batch_size=test_batch_size, #一个批次的大小（一个批次有多少个图片张量）
shuffle=False, #不重排
drop_last=True, #丢弃最后无法称为一整个批次的数据
)
print("gallery_data_loader inited\n")
#加载模型
model = ReIDNet(num_classes=751,
loss={'softmax'}) #指定分类的数量，与使用的损失函数以便决定模型输出何种计算结果
print("=>ReIDNet loaded")
print("Model size: {:.5f}M\n".format(
sum(p.numel() for p in model.parameters()) / 1000000.0))
#损失函数
criterion_class = nn.CrossEntropyLoss()
"""
优化器
参数1，待优化的参数
参数2，学习率
参数3，权重衰减
"""
optimizer = torch.optim.SGD(model.parameters(),
lr=train_lr,
weight_decay=5e-04)
"""
动态学习率
参数1，指定使用的优化器
参数2，mode，可选择‘min’（min表示当监控量停止下降的时候，学习率将减小）或者‘max’（max表示当监控量停止上升的时候，学习率将减小）
参数3，factor，代表学习率每次降低多少
参数4，patience，容忍网路的性能不提升的次数，高于这个次数就降低学习率
参数5，min_lr，学习率的下限
"""
scheduler = lr_scheduler.ReduceLROnPlateau(optimizer,
mode='min',
factor=dy_step_gamma,
patience=10,
min_lr=0.0001)
#如果是测试
if evaluate:
test(model, query_data_loader, gallery_data_loader)
return 0
#如果是训练
print('————model start training————\n')
bt = time.time() #训练的开始时间
for epoch in range(start_epoch, end_epoch):
model.train(True)
train(epoch, model, criterion_class, optimizer, scheduler,
train_data_loader)
et = time.time() #训练的结束时间
print('**模型训练结束, 保存最终参数到{}**\n'.format(final_model_path))
torch.save(model.state_dict(), final_model_path)
print('————训练总用时{:.2f}小时————'.format((et - bt) / 3600.0))
print("-------------------")
return 0
if __name__ == '__main__':
# 使用局部对齐模型
model = ReIDNet(num_classes=751, loss={'softmax, metric'}, aligned=True)
# 加载局部对齐模型最优参数
model.load_state_dict(
torch.load('./model/param/aligned_trihard_net_params_best.pth'))
# 指定数据集
dataset = Market1501()
# query数据与gallery数据处理器
transform = T.Compose([
T.Resize((height, width)), # 尺度统一
T.ToTensor(), # 图片转张量
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224,
0.225]), # 归一化，参数固定
])
# query集吞吐器
query_data_loader = DataLoader(
ImageDataset(dataset.query, transform=transform), # 自定义的数据集，指定使用数据处理器
batch_size=batch_size, # 一个批次的大小（一个批次有多少个图片张量）
drop_last=True, # 丢弃最后无法称为一整个批次的数据
)
# gallery集吞吐器
gallery_data_loader = DataLoader(
ImageDataset(dataset.gallery,
transform=transform), # 自定义的数据集，指定使用数据处理器
batch_size=batch_size, # 一个批次的大小（一个批次有多少个图片张量）
