def cli():
parser = argparse.ArgumentParser(
prog='python3 -m openpifpaf.train',
usage='%(prog)s [options]',
description=__doc__,
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument(
'--version',
action='version',
version='OpenPifPaf {version}'.format(version=__version__))
parser.add_argument('-o', '--output', default=None, help='output file')
parser.add_argument('--disable-cuda',
action='store_true',
help='disable CUDA')
parser.add_argument('--ddp',
default=False,
action='store_true',
help='[experimental] DistributedDataParallel')
parser.add_argument('--local_rank',
default=None,
type=int,
help='[experimental] for torch.distributed.launch')
parser.add_argument('--no-sync-batchnorm',
dest='sync_batchnorm',
default=True,
action='store_false',
help='[experimental] in ddp, to not use syncbatchnorm')
logger.cli(parser)
network.Factory.cli(parser)
network.losses.Factory.cli(parser)
network.Trainer.cli(parser)
encoder.cli(parser)
optimize.cli(parser)
datasets.cli(parser)
show.cli(parser)
visualizer.cli(parser)
args = parser.parse_args()
logger.configure(args, LOG)
if args.log_stats:
logging.getLogger('openpifpaf.stats').setLevel(logging.DEBUG)
# DDP with SLURM
slurm_process_id = os.environ.get('SLURM_PROCID')
if args.ddp and slurm_process_id is not None:
if torch.cuda.device_count() > 1:
LOG.warning(
'Expected one GPU per SLURM task but found %d. '
'Try with "srun --gpu-bind=closest ...". Still trying.',
torch.cuda.device_count())
# if there is more than one GPU available, assume that other SLURM tasks
# have access to the same GPUs and assign GPUs uniquely by slurm_process_id
args.local_rank = (int(slurm_process_id) % torch.cuda.device_count()
if torch.cuda.device_count() > 0 else 0)
os.environ['RANK'] = slurm_process_id
if not os.environ.get('WORLD_SIZE') and os.environ.get('SLURM_NTASKS'):
os.environ['WORLD_SIZE'] = os.environ.get('SLURM_NTASKS')
LOG.info('found SLURM process id: %s', slurm_process_id)
LOG.info(
'distributed env: master=%s port=%s rank=%s world=%s, '
'local rank (GPU)=%d', os.environ.get('MASTER_ADDR'),
os.environ.get('MASTER_PORT'), os.environ.get('RANK'),
os.environ.get('WORLD_SIZE'), args.local_rank)
# add args.device
args.device = torch.device('cpu')
args.pin_memory = False
if not args.disable_cuda and torch.cuda.is_available():
args.device = torch.device('cuda')
args.pin_memory = True
LOG.info('neural network device: %s (CUDA available: %s, count: %d)',
args.device, torch.cuda.is_available(), torch.cuda.device_count())
# output
if args.output is None:
args.output = default_output_file(args)
os.makedirs('outputs', exist_ok=True)
network.Factory.configure(args)
network.losses.Factory.configure(args)
network.Trainer.configure(args)
encoder.configure(args)
datasets.configure(args)
show.configure(args)
visualizer.configure(args)
return args
def cli():
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
# Subparser definition
subparsers = parser.add_subparsers(
help='Different parsers for main actions', dest='command')
predict_parser = subparsers.add_parser("predict")
prep_parser = subparsers.add_parser("prep")
training_parser = subparsers.add_parser("train")
eval_parser = subparsers.add_parser("eval")
# Preprocess input data
prep_parser.add_argument('--dir_ann',
help='directory of annotations of 2d joints',
required=True)
prep_parser.add_argument(
'--dataset',
help=
'datasets to preprocess: nuscenes, nuscenes_teaser, nuscenes_mini, kitti',
default='kitti')
prep_parser.add_argument('--dir_nuscenes',
help='directory of nuscenes devkit',
default='data/nuscenes/')
prep_parser.add_argument('--iou_min',
help='minimum iou to match ground truth',
type=float,
default=0.3)
prep_parser.add_argument('--variance', help='new', action='store_true')
prep_parser.add_argument('--activity', help='new', action='store_true')
prep_parser.add_argument('--monocular', help='new', action='store_true')
# Predict (2D pose and/or 3D location from images)
# General
predict_parser.add_argument('--mode',
help='pifpaf, mono, stereo',
default='stereo')
predict_parser.add_argument('images', nargs='*', help='input images')
predict_parser.add_argument(
'--glob', help='glob expression for input images (for many images)')
predict_parser.add_argument('-o',
'--output-directory',
help='Output directory')
predict_parser.add_argument(
'--output_types',
nargs='+',
default=['json'],
help='what to output: json keypoints skeleton for Pifpaf'
'json bird front or multi for MonStereo')
predict_parser.add_argument('--no_save',
help='to show images',
action='store_true')
predict_parser.add_argument('--dpi',
help='image resolution',
type=int,
default=150)
predict_parser.add_argument(
'--long-edge',
default=None,
type=int,
help='rescale the long side of the image (aspect ratio maintained)')
predict_parser.add_argument('--disable-cuda',
action='store_true',
help='disable CUDA')
predict_parser.add_argument(
'--focal',
help=
'focal length in mm for a sensor size of 7.2x5.4 mm. Default nuScenes sensor',
type=float,
default=5.7)
# Pifpaf parsers
decoder.cli(parser)
logger.cli(parser)
network.Factory.cli(parser)
show.cli(parser)
visualizer.cli(parser)
# Monoloco
predict_parser.add_argument(
'--net',
help='Choose network: monoloco, monoloco_p, monoloco_pp, monstereo')
predict_parser.add_argument('--model',
help='path of MonoLoco model to load',
required=True)
predict_parser.add_argument('--hidden_size',
type=int,
help='Number of hidden units in the model',
default=512)
predict_parser.add_argument(
'--path_gt',
help='path of json file with gt 3d localization',
default='data/arrays/names-kitti-200615-1022.json')
predict_parser.add_argument('--transform',
help='transformation for the pose',
default='None')
predict_parser.add_argument('--z_max',
type=int,
help='maximum meters distance for predictions',
default=100)
predict_parser.add_argument('--n_dropout',
type=int,
help='Epistemic uncertainty evaluation',
default=0)
predict_parser.add_argument('--dropout',
type=float,
help='dropout parameter',
default=0.2)
predict_parser.add_argument(
'--show_all',
help='only predict ground-truth matches or all',
action='store_true')
# Social distancing and social interactions
predict_parser.add_argument('--social_distance',
help='social',
action='store_true')
predict_parser.add_argument('--threshold_prob',
type=float,
help='concordance for samples',
default=0.25)
predict_parser.add_argument('--threshold_dist',
type=float,
help='min distance of people',
default=2.5)
predict_parser.add_argument('--radii',
type=tuple,
help='o-space radii',
default=(0.3, 0.5, 1))
# Training
training_parser.add_argument(
'--joints',
help='Json file with input joints',
default='data/arrays/joints-nuscenes_teaser-190513-1846.json')
training_parser.add_argument('--no_save',
help='to not save model and log file',
action='store_true')
training_parser.add_argument('-e',
'--epochs',
type=int,
help='number of epochs to train for',
default=500)
training_parser.add_argument('--bs',
type=int,
default=512,
help='input batch size')
training_parser.add_argument('--monocular',
help='whether to train monoloco',
action='store_true')
training_parser.add_argument('--dropout',
type=float,
help='dropout. Default no dropout',
default=0.2)
training_parser.add_argument('--lr',
type=float,
help='learning rate',
default=0.001)
training_parser.add_argument('--sched_step',
type=float,
help='scheduler step time (epochs)',
default=30)
training_parser.add_argument('--sched_gamma',
type=float,
help='Scheduler multiplication every step',
default=0.98)
training_parser.add_argument('--hidden_size',
type=int,
help='Number of hidden units in the model',
default=1024)
training_parser.add_argument('--n_stage',
type=int,
help='Number of stages in the model',
default=3)
training_parser.add_argument('--hyp',
help='run hyperparameters tuning',
action='store_true')
training_parser.add_argument('--multiplier',
type=int,
help='Size of the grid of hyp search',
default=1)
training_parser.add_argument(
'--r_seed',
type=int,
help='specify the seed for training and hyp tuning',
default=1)
training_parser.add_argument('--print_loss',
help='print training and validation losses',
action='store_true')
training_parser.add_argument(
'--auto_tune_mtl',
help='whether to use uncertainty to autotune losses',
action='store_true')
# Evaluation
eval_parser.add_argument('--dataset',
help='datasets to evaluate, kitti or nuscenes',
default='kitti')
eval_parser.add_argument('--geometric',
help='to evaluate geometric distance',
action='store_true')
eval_parser.add_argument('--generate',
help='create txt files for KITTI evaluation',
action='store_true')
eval_parser.add_argument(
'--dir_ann',
help='directory of annotations of 2d joints (for KITTI evaluation)')
eval_parser.add_argument('--model', help='path of MonoLoco model to load')
eval_parser.add_argument(
'--joints',
help='Json file with input joints to evaluate (for nuScenes evaluation)'
)
eval_parser.add_argument('--n_dropout',
type=int,
help='Epistemic uncertainty evaluation',
default=0)
eval_parser.add_argument('--dropout',
type=float,
help='dropout. Default no dropout',
default=0.2)
eval_parser.add_argument('--hidden_size',
type=int,
help='Number of hidden units in the model',
default=1024)
eval_parser.add_argument('--n_stage',
type=int,
help='Number of stages in the model',
default=3)
eval_parser.add_argument('--show',
help='whether to show statistic graphs',
action='store_true')
eval_parser.add_argument('--save',
help='whether to save statistic graphs',
action='store_true')
eval_parser.add_argument('--verbose',
help='verbosity of statistics',
action='store_true')
eval_parser.add_argument('--monocular',
help='whether to train using the baseline',
action='store_true')
eval_parser.add_argument('--new', help='new', action='store_true')
eval_parser.add_argument('--variance',
help='evaluate keypoints variance',
action='store_true')
eval_parser.add_argument('--activity',
help='evaluate activities',
action='store_true')
eval_parser.add_argument(
'--net',
help='Choose network: monoloco, monoloco_p, monoloco_pp, monstereo')
eval_parser.add_argument('--baselines',
help='whether to evaluate stereo baselines',
action='store_true')
eval_parser.add_argument(
'--generate_official',
help='whether to add empty txt files for official evaluation',
action='store_true')
args = parser.parse_args()
return args
def cli():
parser = argparse.ArgumentParser(
prog='python3 -m openpifpaf.predict',
usage='%(prog)s [options] images',
description=__doc__,
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument('--version', action='version',
version='OpenPifPaf {version}'.format(version=__version__))
decoder.cli(parser)
logger.cli(parser)
network.Factory.cli(parser)
show.cli(parser)
visualizer.cli(parser)
parser.add_argument('images', nargs='*',
help='input images')
parser.add_argument('--glob',
help='glob expression for input images (for many images)')
parser.add_argument('-o', '--image-output', default=None, nargs='?', const=True,
help='Whether to output an image, '
'with the option to specify the output path or directory')
parser.add_argument('--json-output', default=None, nargs='?', const=True,
help='Whether to output a json file, '
'with the option to specify the output path or directory')
parser.add_argument('--batch-size', default=1, type=int,
help='processing batch size')
parser.add_argument('--long-edge', default=None, type=int,
help='rescale the long side of the image (aspect ratio maintained)')
parser.add_argument('--loader-workers', default=None, type=int,
help='number of workers for data loading')
parser.add_argument('--precise-rescaling', dest='fast_rescaling',
default=True, action='store_false',
help='use more exact image rescaling (requires scipy)')
parser.add_argument('--disable-cuda', action='store_true',
help='disable CUDA')
args = parser.parse_args()
logger.configure(args, LOG) # logger first
# add args.device
args.device = torch.device('cpu')
args.pin_memory = False
if not args.disable_cuda and torch.cuda.is_available():
args.device = torch.device('cuda')
args.pin_memory = True
LOG.info('neural network device: %s (CUDA available: %s, count: %d)',
args.device, torch.cuda.is_available(), torch.cuda.device_count())
decoder.configure(args)
network.Factory.configure(args)
show.configure(args)
visualizer.configure(args)
if args.loader_workers is None:
args.loader_workers = args.batch_size
# glob
if args.glob:
args.images += glob.glob(args.glob)
if not args.images:
raise Exception("no image files given")
return args