args = parse_args()
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:
np.random.seed(cfg.RNG_SEED)
imdb, roidb = get_roidb(args.imdb_name)
numAnnos = imdb.roidb_num_bboxes_at(-1)
print("\n\n-=-=-=-=-=-=-=-=-\n\n")
print("Report:\n\n")
print("number of classes: {}".format(imdb.num_classes))
print("number of images: {}".format(len(roidb)))
print("number of annotations: {}".format(numAnnos))
print("size of imdb in memory: {}kB".format(sys.getsizeof(imdb)/1024.))
print("size of roidb in memory: {}kB".format(len(roidb) * sys.getsizeof(roidb[0])/1024.))
print("example roidb:")
for k,v in roidb[0].items():
print("\t==> {},{}".format(k,type(v)))
print("\t\t{}".format(v))
print("computing bbox info...")
areas, widths, heights = get_bbox_info(roidb,numAnnos)
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
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
imdb, roidb = get_roidb(args.imdb_name)
print '{:d} roidb entries'.format(len(roidb))
print("num_classes", imdb.num_classes)
print(imdb.roidb_num_bboxes_at(-1))
print(roidb[0])
sys.exit()
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)