import scipy.io
from transforms3d.quaternions import quat2mat
# start rendering
imdb.data_queue = Queue(maxsize=100)
meta_data = scipy.io.loadmat(roidb[0]['meta_data'])
intrinsic_matrix = meta_data['intrinsic_matrix'].astype(np.float32, copy=True)
if cfg.TRAIN.SYN_CLASS_INDEX >= 0:
t = threading.Thread(target=render_one, args=(imdb.data_queue, intrinsic_matrix, imdb._extents_all, imdb._points_all))
else:
t = threading.Thread(target=render, args=(imdb.data_queue, intrinsic_matrix, imdb._points_all))
t.start()
else:
imdb.data_queue = []
from networks.factory import get_network
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
if cfg.TRAIN.SEGMENTATION:
train_net(network, imdb, roidb, roidb_val, output_dir,
pretrained_model=pretrained_model,
pretrained_ckpt=args.pretrained_ckpt,
iters_train=iters[0],
iters_val=iters[1])
else:
train_net_det(network, imdb, roidb, output_dir,
pretrained_model=pretrained_model,
pretrained_ckpt=args.pretrained_ckpt,
max_iters=args.max_iters)
args=(imdb.data_queue, intrinsic_matrix,
imdb._extents_all, imdb._points_all))
else:
t = threading.Thread(target=render,
args=(imdb.data_queue, intrinsic_matrix,
imdb._points_all))
t.start()
else:
imdb.data_queue = []
from networks.factory import get_network
network = get_network(args.network_name)
print 'Use network `{:s}` in training'.format(args.network_name)
if cfg.TRAIN.SEGMENTATION:
train_net(network,
imdb,
roidb,
output_dir,
pretrained_model=pretrained_model,
pretrained_ckpt=args.pretrained_ckpt,
max_iters=args.max_iters)
else:
train_net_det(network,
imdb,
roidb,
output_dir,
pretrained_model=pretrained_model,
pretrained_ckpt=args.pretrained_ckpt,
max_iters=args.max_iters)
print('Called with args:')
print(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
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)
cfg.GPU_ID = args.gpu_id
print device_name
network = get_network(args.network_name, args.pretrained_model)
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)
