help="train and val sets together for training, "
"val set alone for validation")
parser.add_argument('--batch-id', type=str, default='2018-03-26-16:21:21')
parser.add_argument('--num-instances',
type=int,
default=4,
help="each minibatch consist of "
"(batch_size // num_instances) identities, and "
"each identity has num_instances instances, "
"default: 4")
# model
parser.add_argument('-a',
'--arch',
type=str,
default='resnet50',
choices=models.names())
parser.add_argument('--features', type=int, default=128)
parser.add_argument('--dropout', type=float, default=0)
# loss
parser.add_argument('--margin',
type=float,
default=0.5,
help="margin of the triplet loss, default: 0.5")
# optimizer
parser.add_argument('--lr',
type=float,
default=0.0002,
help="learning rate of all parameters")
parser.add_argument('--weight-decay', type=float, default=5e-4)
# training configs
parser.add_argument('--resume', type=str, default='', metavar='PATH')
def __init__(self):
self.parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
self.parser.add_argument('--stage',
type=int,
default=1,
help='training stage [1|2]')
self.parser.add_argument('-d',
'--dataset',
type=str,
default='market1501',
choices=datasets.names())
self.parser.add_argument('-t',
'--target',
type=str,
default='dukemtmc',
choices=datasets.names())
self.parser.add_argument('-s',
'--source',
type=str,
default='market1501',
choices=datasets.names())
# paths
self.parser.add_argument(
'--dataroot',
type=str,
default='./datasets/',
help=
'root path to datasets (should have subfolders market1501, dukemtmc, cuhk03, etc)'
)
self.parser.add_argument('--checkpoints',
type=str,
default='./checkpoints/',
help='root path to save models')
self.parser.add_argument('--name',
type=str,
default='FD-GAN',
help='directory to save models')
self.parser.add_argument(
'--netE-pretrain',
type=str,
default='pretrained model path for net_E in stage 2')
self.parser.add_argument(
'--netG-pretrain',
type=str,
default='pretrained model path for net_G in stage 2')
self.parser.add_argument(
'--tar-netG-pretrain',
type=str,
default='pretrained model path for net_G in stage 2')
self.parser.add_argument(
'--netDp-pretrain',
type=str,
default='pretrained model path for net_Dp in stage 2')
self.parser.add_argument(
'--tar-netDi-pretrain',
type=str,
default='pretrained model path for net_Di in stage 2')
self.parser.add_argument(
'--netDi-pretrain',
type=str,
default='pretrained model path for net_Di in stage 2')
# model structures
self.parser.add_argument('--arch',
type=str,
default='resnet50',
choices=models.names())
self.parser.add_argument(
'--norm',
type=str,
default='batch',
help='instance normalization or batch normalization')
self.parser.add_argument('--drop',
type=float,
default=0.2,
help='dropout for the netG')
self.parser.add_argument('--connect-layers',
type=int,
default=0,
help='skip connections num for netG')
self.parser.add_argument(
'--fuse-mode',
type=str,
default='cat',
help='method to fuse reid feature and pose feature [cat|add]')
self.parser.add_argument('--pose-feature-size',
type=int,
default=128,
help='length of feature vector for pose')
self.parser.add_argument('--noise-feature-size',
type=int,
default=256,
help='length of feature vector for noise')
self.parser.add_argument('--pose-aug',
type=str,
default='no',
help='posemap augmentation [no|erase|gauss]')
# dataloader setting
self.parser.add_argument('-b',
'--batch-size',
type=int,
default=16,
help='input batch size')
self.parser.add_argument('-j',
'--workers',
default=4,
type=int,
help='num threads for loading data')
self.parser.add_argument('--width',
type=int,
default=128,
help='input image width')
self.parser.add_argument('--height',
type=int,
default=256,
help='input image height')
# optimizer setting
self.parser.add_argument('--niter',
type=int,
default=50,
help='# of iter at starting learning rate')
self.parser.add_argument(
'--niter-decay',
type=int,
default=50,
help='# of iter to linearly decay learning rate to zero')
self.parser.add_argument('--lr',
type=float,
default=0.001,
help='initial learning rate')
self.parser.add_argument(
'--save-step',
type=int,
default=2,
help='frequency of saving checkpoints at the end of epochs')
self.parser.add_argument(
'--eval-step',
type=int,
default=10,
help='frequency of evaluate checkpoints at the end of epochs')
# visualization setting
self.parser.add_argument('--display-port',
type=int,
default=6006,
help='visdom port of the web display')
self.parser.add_argument(
'--display-id',
type=int,
default=1,
help='window id of the web display, set 0 for non-usage of visdom')
self.parser.add_argument('--display-winsize',
type=int,
default=256,
help='display window size')
self.parser.add_argument(
'--display-freq',
type=int,
default=10,
help='frequency of showing training results on screen')
self.parser.add_argument(
'--display-single-pane-ncols',
type=int,
default=0,
help=
'if positive, display all images in a single visdom web panel with certain number of images per row.'
)
self.parser.add_argument(
'--update-html-freq',
type=int,
default=100,
help='frequency of saving training results to html')
self.parser.add_argument(
'--no_html',
action='store_true',
help=
'do not save intermediate training results to [opt.checkpoints]/name/web/'
)
self.parser.add_argument(
'--print-freq',
type=int,
default=10,
help='frequency of showing training results on console')
# training schedule
self.parser.add_argument('--lambda-recon',
type=float,
default=1.0,
help='loss weight of loss_r')
self.parser.add_argument('--lambda-veri',
type=float,
default=1.0,
help='loss weight of loss_v')
self.parser.add_argument('--lambda-sp',
type=float,
default=1.0,
help='loss weight of loss_sp')
self.parser.add_argument('--lambda-mmd',
type=float,
default=1.0,
help='loss weight of loss_mmd')
self.parser.add_argument('--lambda-tri',
type=float,
default=10.0,
help='loss weight of loss_tri')
self.parser.add_argument('--smooth-label',
action='store_true',
help='smooth label or not for GANloss')
self.parser.add_argument('--tri-margin',
type=float,
default=0.5,
help='margin for Tripletloss')
self.opt = self.parser.parse_args()
self.show_opt()
parser.add_argument('--ev', type=int, default=1)
# parser.add_argument('--clock', type=bool, default=True) # 是否记时
# parser.add_argument('--is_baseline', type=bool, default=False) # 默认不是baseline
# the key parameters is following
parser.add_argument('--total_step', type=int, default=5) # 默认总的五次迭代.
# parser.add_argument('--train_tagper_step', type=float, default=3) # 用于训练 tagper的 step 数
parser.add_argument('--epoch', type=int, default=70)
parser.add_argument('--step_size', type=int, default=55)
parser.add_argument('-b', '--batch_size', type=int, default=16)
'''new'''
parser.add_argument('--p', type=int, default=1) # 采样曲线的指数
parser.add_argument('--baba', type=float,
default=2) # tagper的训练数量reid的baba倍数,感觉2应该是上线了.
# 下面是暂时不知道用来做什么的参数
parser.add_argument('-a',
'--arch',
type=str,
default='avg_pool',
choices=models.names()) # eug model_name
parser.add_argument('-i', '--iter-step', type=int, default=5)
parser.add_argument('-g', '--gamma', type=float, default=0.3)
parser.add_argument('-l', '--l', type=float)
parser.add_argument('--continuous', action="store_true")
main(parser.parse_args())
'''
python3.6 atm06.py --total_step 5 --exp_order 6
python3.6 atm06.py --total_step 6 --exp_order 7 --p 1 --baba 1.5
python3.6 atm06.py --total_step 6 --exp_order 8 --p 1 --baba 2 --max_frames 400
'''
default='.', help='path to reid dataset')
parser.add_argument('-s', '--source', type=str, default='dukemtmc',
choices=datasets.names())
parser.add_argument('-t', '--target', type=str, default='market1501',
choices=datasets.names())
parser.add_argument('-m', '--mte', type=str, default='personx',
choices=datasets.names())
parser.add_argument('--batch_size', type=int, default=64, required=True,
help='number of examples/minibatch')
parser.add_argument('--num_batches', type=int, required=False,
help='number of batches (default entire dataset)')
parser.add_argument('--resume', type=str, default='', metavar='PATH')
parser.add_argument('-a', '--arch', type=str, default='resnet50', choices=models.names())
parser.add_argument('--split', type=int, default=0)
parser.add_argument('--height', type=int, default=256,
help="input height, default: 256 for resnet*, "
"144 for inception")
parser.add_argument('--width', type=int, default=128,
help="input width, default: 128 for resnet*, "
"56 for inception")
parser.add_argument('--num-instances', type=int, default=8,
help="each minibatch consist of "
"(batch_size // num_instances) identities, and "
"each identity has num_instances instances, "
"default: 4")
parser.add_argument('--combine-trainval', action='store_true',
help="train and val sets together for training, "
BuMain.evaluate(dataset_all.query, dataset_all.gallery)
# get new train data for the next iteration
print('----------------------------------------bottom-up clustering------------------------------------------------')
cluster_id_labels, new_train_data = BuMain.get_new_train_data(cluster_id_labels, nums_to_merge, size_penalty=args.size_penalty)
print('\n\n')
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='bottom-up clustering')
parser.add_argument('-d', '--dataset', type=str, default='custom',
choices=datasets.names())
parser.add_argument('-b', '--batch-size', type=int, default=16)
parser.add_argument('-f', '--fea', type=int, default=2048)
parser.add_argument('-a', '--arch', type=str, default='avg_pool',choices=models.names())
working_dir = os.path.dirname(os.path.abspath(__file__))
parser.add_argument('--data_dir', type=str, metavar='PATH',
default=os.path.join(working_dir,'data'))
parser.add_argument('--logs_dir', type=str, metavar='PATH',
default=os.path.join(working_dir,'logs'))
parser.add_argument('--max_frames', type=int, default=900)
parser.add_argument('--loss', type=str, default='ExLoss')
parser.add_argument('-m', '--momentum', type=float, default=0.5)
parser.add_argument('-s', '--step_size', type=int, default=55)
parser.add_argument('--size_penalty',type=float, default=0.005)
parser.add_argument('-mp', '--merge_percent',type=float, default=0.05)
main(parser.parse_args())
help="input height, default: 256 for resnet*, "
"144 for inception")
parser.add_argument('--width', type=int,
help="input width, default: 128 for resnet*, "
"56 for inception")
parser.add_argument('--combine-trainval', action='store_true',
help="train and val sets together for training, "
"val set alone for validation")
parser.add_argument('--num-instances', type=int, default=4,
help="each minibatch consist of "
"(batch_size // num_instances) identities, and "
"each identity has num_instances instances, "
"default: 4")
# model
parser.add_argument('-a', '--arch', type=str, default='resnet50',
choices=models.names())
parser.add_argument('--features', type=int, default=128)
parser.add_argument('--dropout', type=float, default=0)
# loss
parser.add_argument('--margin', type=float, default=0.5,
help="margin of the triplet loss, default: 0.5")
# optimizer
parser.add_argument('--lr', type=float, default=0.0001,
help="learning rate of all parameters")
parser.add_argument('--weight-decay', type=float, default=5e-4)
# training configs
parser.add_argument('--resume', type=str, default='', metavar='PATH')
parser.add_argument('--resume_from_trip', type=str, default='', metavar='PATH')
parser.add_argument('--evaluate', action='store_true',
help="evaluation only")
parser.add_argument('--only_train_metric', action='store_true',
