def train_main(data_dir, model_dir, train_steps, input_yaml):
cfg_from_file(input_yaml)
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain_model/VGG_imagenet.npy',
max_iters=int(cfg.TRAIN.max_steps),
restore=bool(int(cfg.TRAIN.restore)))
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(args.imdb_name)
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = args.output_dir # get_output_dir(imdb, None) ## benz
if not os.path.exists(output_dir): os.makedirs(output_dir)
os.system('cp ./lib/rpn_msr/generate_anchors.py %s' % (output_dir))
os.system('cp ./lib/fast_rcnn/config.py %s' % (output_dir))
os.system('cp ./experiments/cfgs/faster_rcnn_kitti.yml %s' % (output_dir))
log_dir = get_log_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
print 'Logs will be saved to `{:s}`'.format(log_dir)
device_name = '/gpu:{:d}'.format(args.gpu_id)
print device_name
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=args.pretrained_model,
max_iters=args.max_iters,
restore=bool(int(args.restore)))
if __name__ == '__main__':
# 将text.yml的配置与默认config中的默认配置进行合并
cfg_from_file('text.yml')
print('Using config:~~~~~~~~~~~~~~~~')
# 根据给定的名字，得到要加载的数据集
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
# 准备训练数据
roidb = get_training_roidb(imdb)
# 模型输出的路径
# output_dir = get_output_dir(imdb, None)
output_dir = './ckpt'
# summary的输出路径
log_dir = get_log_dir(imdb)
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(
network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='./pretrain_vggmodel/VGG_imagenet.npy',
# pretrained_model='/home/xiaofeng/data/ctpn/pretrainde_vgg',
# pretrained_model=None,
max_iters=180000,
restore=bool(int(1)))
from lib.fast_rcnn.train import get_training_roidb, train_net
from lib.fast_rcnn.config import cfg_from_file, get_output_dir, get_log_dir
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network, imdb, roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain_model/VGG_imagenet.npy',
max_iters=int(cfg.TRAIN.max_steps),
restore=bool(int(cfg.TRAIN.restore)))
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
# device_name = '/gpu:'+str(CUDA_VISIBLE_DEVICES)
# print(device_name)
# 用vgg16训练
training_flag = tf.placeholder(tf.bool)
network = get_network('VGGnet_train', training_flag)
pretrained_model = 'data/pretrain/VGG_imagenet.npy'
# 用densenet作为骨干网络，不加载预训练权重
# training_flag = tf.placeholder(tf.bool)
# network = get_network('Densenet_train', training_flag)
# pretrained_model = None
train_net(network,
training_flag,
imdb,
roidb,
imdb_test,
roidb_test,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=pretrained_model,
max_iters=int(cfg.TRAIN.max_steps),
restore=bool(int(cfg.TRAIN.restore)))
from lib.fast_rcnn.config import cfg_from_file, get_output_dir, get_log_dir
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('text.yml')
print('Using config:~~~~~~~~~~~~~~~~')
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=
'/home/zihao/Downloads/project/ctpn/ctpn/VGG_imagenet.npy',
max_iters=180000,
restore=bool(int(1)))
from lib.fast_rcnn.train import get_training_roidb, train_net
from lib.fast_rcnn.config import cfg_from_file, get_output_dir, get_log_dir
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network, imdb, roidb,
output_dir = output_dir,
log_dir = log_dir,
pretrained_model = 'VGG_imagenet.npy',
max_iters = 150000,
restore = bool(int(cfg.TRAIN.restore)))
# 将text.yml的配置与默认config中的默认配置进行合并
cfg_from_file('text.yml')
print('Using config:~~~~~~~~~~~~~~~~')
# 根据给定的名字，得到要加载的数据集
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
# 准备训练数据
roidb = get_training_roidb(imdb)
# 模型输出的路径
output_dir = get_output_dir(imdb, None)
# summary的输出路径
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(
network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=
'/Users/xiaofeng/Code/Github/dataset/CHINESE_OCR/ctpn/pretrain/VGG_imagenet.npy',
max_iters=180000,
restore=bool(int(0)))
print('Using config:~~~~~~~~~~~~~~~~')
# 根据给定的名字，得到要加载的数据集
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
# 准备训练数据
roidb = get_training_roidb(imdb)
# 模型输出的路径
output_dir = get_output_dir(imdb, None)
# summary的输出路径
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(
network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
# pretrained_model=
# '/Users/xiaofeng/Code/Github/dataset/CHINESE_OCR/ctpn/pretrain/VGG_imagenet.npy',
# pretrained_model='/home/xiaofeng/data/ctpn/pretrainde_vgg',
pretrained_model='/home/guyu/CHINESE-OCR/weight/VGG_imagenet.npy',
max_iters=180000,
restore=bool(int(1)))
cfg_from_list(args.set_cfgs)
cfg.GPU_ID = args.gpu_id
print('Using config:')
pprint.pprint(cfg)
if not args.randomize:
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
caffe.set_random_seed(cfg.RNG_SEED)
# set up caffe
if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
imdb, roidb = combined_roidb(args.imdb_name)
print '{:d} roidb entries'.format(len(roidb))
output_dir = get_output_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
train_net(args.solver,
roidb,
output_dir,
pretrained_model=args.pretrained_model,
max_iters=args.max_iters)
if __name__ == '__main__':
# 将text.yml的配置与默认config中的默认配置进行合并
cfg_from_file('text.yml')
print('Using config:~~~~~~~~~~~~~~~~')
# 根据给定的名字，得到要加载的数据集
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
# 准备训练数据
roidb = get_training_roidb(imdb)
# 模型输出的路径
output_dir = get_output_dir(imdb, None)
# summary的输出路径
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=None,
max_iters=180000,
restore=bool(int(1)))
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
print 'Logs will be saved to `{:s}`'.format(log_dir)
device_name = '/gpu:0'
print device_name
network = get_network('VGGnet_train')
train_net(network, imdb, roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain/VGG_imagenet.npy',
max_iters=180000,
restore=bool(int(0)))
if len(sys.argv) == 1:
parser.print_help()
sys.exit(1)
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(args.imdb_name)
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
print('total samples: {:d}'.format(len(roidb)))
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
print 'Logs will be saved to `{:s}`'.format(log_dir)
print 'use device /gpu:0' # always use gpu 0
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=args.pretrained_model,
restore=args.restore)
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:1'
print(device_name)
network = get_network('VGGnet_train')
train_net(
network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=
'/home/alex/source/text-detection-ctpn/data/pretrain/VGG_imagenet.npy', # data/pretrain/VGG_imagenet.npy
max_iters=int(cfg.TRAIN.max_steps),
restore=bool(int(cfg.TRAIN.restore)))
print('Using config:')
imdb = get_imdb('voc_2007_train')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, 'textline_v4')
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
pprint.pprint(cfg)
# print(bool(int(cfg.TRAIN.restore)))
# print(cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS)
# print(cfg.TRAIN.restore)
# assert 0
train_net(
network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain/VGG_imagenet.npy',
max_iters=int(cfg.TRAIN.max_steps),
pretrained_dir=
'/home/CORP/yaqi.wang/pycharm/detection/text-detection-ctpn/model/textline_v4',
restore=bool(int(cfg.TRAIN.restore)))
this_dir = os.path.dirname(__file__)
from lib.fast_rcnn.train import get_training_roidb, train_net
from lib.fast_rcnn.config import cfg_from_file, get_output_dir, get_log_dir
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
# print('Using config:')
# pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval', cfg.DATA_DIR + '/template_generative')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
network = get_network('VGGnet_train')
train_net(network, imdb, roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain/VGG_imagenet.npy',
max_iters=int(cfg.TRAIN.max_steps),
restore=cfg.TRAIN.restore)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
if not args.randomize:
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(args.imdb_name)
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
print 'Output will be saved to `{:s}`'.format(output_dir)
device_name = '/gpu:{:d}'.format(args.gpu_id)
print device_name
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
train_net(network,
imdb,
roidb,
output_dir,
pretrained_model=args.pretrained_model,
max_iters=args.max_iters)
from lib.datasets.factory import get_imdb
from lib.networks.factory import get_network
from lib.fast_rcnn.config import cfg
if __name__ == '__main__':
cfg_from_file('ctpn/text.yml')
print('Using config:')
pprint.pprint(cfg)
imdb = get_imdb('voc_2007_trainval')
print('Loaded dataset `{:s}` for training'.format(imdb.name))
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print('Output will be saved to `{:s}`'.format(output_dir))
print('Logs will be saved to `{:s}`'.format(log_dir))
device_name = '/gpu:0'
print(device_name)
network = get_network('VGGnet_train')
train_net(network,
imdb,
roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model='data/pretrain/VGG_imagenet.npy',
max_iters=180000,
restore=bool(int(0)))
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
if not args.randomize:
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
imdb = get_imdb(args.imdb_name)
print 'Loaded dataset `{:s}` for training'.format(imdb.name)
roidb = get_training_roidb(imdb)
output_dir = get_output_dir(imdb, None)
log_dir = get_log_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
print 'Logs will be saved to `{:s}`'.format(log_dir)
device_name = '/gpu:{:d}'.format(args.gpu_id)
print device_name
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
train_net(network, imdb, roidb,
output_dir=output_dir,
log_dir=log_dir,
pretrained_model=args.pretrained_model,
max_iters=args.max_iters,
restore=bool(int(args.restore)))
