def train_mask_rcnn(queue=None, imdb_name=None, init_model=None, solver=None,
max_iters=None, cfg=None, rpn_file=None):
"""Train a Mask R-CNN using proposals generated by an RPN.
"""
cfg.TRAIN.HAS_RPN = False # not generating prosals on-the-fly
cfg.TRAIN.PROPOSAL_METHOD = 'rpn' # use pre-computed RPN proposals instead
cfg.TRAIN.IMS_PER_BATCH = 1
print 'Init model: {}'.format(init_model)
print 'RPN proposals: {}'.format(rpn_file)
print('Using config:')
pprint.pprint(cfg)
import caffe
# _init_caffe(cfg)
roidb, imdb = get_roidb(imdb_name, rpn_file=rpn_file)
output_dir = get_output_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
# Train Mask R-CNN
model_paths = train_net_multi_gpu(solver, roidb, output_dir,
pretrained_model=init_model,
max_iters=max_iters,
gpus=cfg.GPU_ID)
# Cleanup all but the final model
# for i in model_paths[:-1]:
# os.remove(i)
mask_rcnn_model_path = model_paths[-1]
# Send Mask R-CNN model path over the multiprocessing queue
queue.put({'model_path': mask_rcnn_model_path})
def train_rpn(queue=None, imdb_name=None, init_model=None, solver=None,
max_iters=None, cfg=None):
"""Train a Region Proposal Network in a separate training process.
"""
# Not using any proposals, just ground-truth boxes
cfg.TRAIN.HAS_RPN = True
cfg.TRAIN.BBOX_REG = False # applies only to Mask R-CNN bbox regression
cfg.TRAIN.PROPOSAL_METHOD = 'gt'
cfg.TRAIN.IMS_PER_BATCH = 1
print 'Init model: {}'.format(init_model)
print('Using config:')
pprint.pprint(cfg)
import caffe
# _init_caffe(cfg)
roidb, imdb = get_roidb(imdb_name)
print 'roidb len: {}'.format(len(roidb))
output_dir = get_output_dir(imdb)
print 'Output will be saved to `{:s}`'.format(output_dir)
model_paths = train_net_multi_gpu(solver, roidb, output_dir,
pretrained_model=init_model,
max_iters=max_iters,
gpus=cfg.GPU_ID)
# Cleanup all but the final model
# for i in model_paths[:-1]:
# os.remove(i)
rpn_model_path = model_paths[-1]
# Send final model path through the multiprocessing queue
queue.put({'model_path': rpn_model_path})
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)
gpu_id = args.gpu_id
gpu_list = gpu_id.split(',')
gpus = [int(i) for i in gpu_list]
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)
# set up caffe
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_multi_gpu(args.solver,
roidb,
output_dir,
pretrained_model=args.pretrained_model,
max_iter=args.max_iters,
gpus=gpus)
print(args)
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)
gpu_id = args.gpu_id
gpu_list = gpu_id.split(',')
gpus = [int(i) for i in gpu_list]
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
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_multi_gpu(args.solver, roidb, output_dir,
pretrained_model=args.pretrained_model,
max_iter=args.max_iters, gpus=gpus)
