def init_weights(self, pretrained=None):
"""Initialize the weights of PointNet++ backbone."""
# Do not initialize the conv layers
# to follow the original implementation
if isinstance(pretrained, str):
from mmdet3d.utils import get_root_logger
logger = get_root_logger()
load_checkpoint(self, pretrained, strict=False, logger=logger)
def __init__(self,
info_path,
data_root,
rate,
prepare,
sample_groups,
classes=None,
points_loader=dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=[0, 1, 2, 3])):
super().__init__()
self.data_root = data_root
self.info_path = info_path
self.rate = rate
self.prepare = prepare
self.classes = classes
self.cat2label = {name: i for i, name in enumerate(classes)}
self.label2cat = {i: name for i, name in enumerate(classes)}
self.points_loader = mmcv.build_from_cfg(points_loader, PIPELINES)
db_infos = mmcv.load(info_path)
# filter database infos
from mmdet3d.utils import get_root_logger
logger = get_root_logger()
for k, v in db_infos.items():
logger.info(f'load {len(v)} {k} database infos')
for prep_func, val in prepare.items():
db_infos = getattr(self, prep_func)(db_infos, val)
logger.info('After filter database:')
for k, v in db_infos.items():
logger.info(f'load {len(v)} {k} database infos')
self.db_infos = db_infos
# load sample groups
# TODO: more elegant way to load sample groups
self.sample_groups = []
for name, num in sample_groups.items():
self.sample_groups.append({name: int(num)})
self.group_db_infos = self.db_infos # just use db_infos
self.sample_classes = []
self.sample_max_nums = []
for group_info in self.sample_groups:
self.sample_classes += list(group_info.keys())
self.sample_max_nums += list(group_info.values())
self.sampler_dict = {}
for k, v in self.group_db_infos.items():
self.sampler_dict[k] = BatchSampler(v, k, shuffle=True)
def __init__(self,
info_path,
data_root,
rate,
prepare,
sample_groups,
classes=None):
super().__init__()
self.data_root = data_root
self.info_path = info_path
self.rate = rate
self.prepare = prepare
self.classes = classes
self.cat2label = {name: i for i, name in enumerate(classes)}
self.label2cat = {i: name for i, name in enumerate(classes)}
with open(info_path, 'rb') as f:
db_infos = pickle.load(f)
# filter database infos
from mmdet3d.utils import get_root_logger
logger = get_root_logger()
for k, v in db_infos.items():
logger.info(f'load {len(v)} {k} database infos')
for prep_func, val in prepare.items():
db_infos = getattr(self, prep_func)(db_infos, val)
logger.info('After filter database:')
for k, v in db_infos.items():
logger.info(f'load {len(v)} {k} database infos')
self.db_infos = db_infos
# load sample groups
# TODO: more elegant way to load sample groups
self.sample_groups = []
for name, num in sample_groups.items():
self.sample_groups.append({name: int(num)})
self.group_db_infos = self.db_infos # just use db_infos
self.sample_classes = []
self.sample_max_nums = []
for group_info in self.sample_groups:
self.sample_classes += list(group_info.keys())
self.sample_max_nums += list(group_info.values())
self.sampler_dict = {}
for k, v in self.group_db_infos.items():
self.sampler_dict[k] = BatchSampler(v, k, shuffle=True)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# import modules from string list.
if cfg.get('custom_imports', None):
from mmcv.utils import import_modules_from_strings
import_modules_from_strings(**cfg['custom_imports'])
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.resume_from is not None:
cfg.resume_from = args.resume_from
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids
else:
cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * len(cfg.gpu_ids) / 8
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# re-set gpu_ids with distributed training mode
_, world_size = get_dist_info()
cfg.gpu_ids = range(world_size)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# dump config
cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
# init the logger before other steps
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
# add a logging filter
logging_filter = logging.Filter('mmdet')
logging_filter.filter = lambda record: record.find('mmdet') != -1
# init the meta dict to record some important information such as
# environment info and seed, which will be logged
meta = dict()
# log env info
env_info_dict = collect_env()
env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
dash_line = '-' * 60 + '\n'
logger.info('Environment info:\n' + dash_line + env_info + '\n' +
dash_line)
meta['env_info'] = env_info
meta['config'] = cfg.pretty_text
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
# set random seeds
if args.seed is not None:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
meta['exp_name'] = osp.basename(args.config)
model = build_detector(cfg.model,
train_cfg=cfg.get('train_cfg'),
test_cfg=cfg.get('test_cfg'))
logger.info(f'Model:\n{model}')
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
val_dataset = copy.deepcopy(cfg.data.val)
# in case we use a dataset wrapper
if 'dataset' in cfg.data.train:
val_dataset.pipeline = cfg.data.train.dataset.pipeline
else:
val_dataset.pipeline = cfg.data.train.pipeline
# set test_mode=False here in deep copied config
# which do not affect AP/AR calculation later
# refer to https://mmdetection3d.readthedocs.io/en/latest/tutorials/customize_runtime.html#customize-workflow # noqa
val_dataset.test_mode = False
datasets.append(build_dataset(val_dataset))
if cfg.checkpoint_config is not None:
# save mmdet version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmdet_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_detector(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
meta=meta)
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.options is not None:
cfg.merge_from_dict(args.options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.resume_from is not None:
cfg.resume_from = args.resume_from
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids
else:
cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * len(cfg.gpu_ids) / 8
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# init the logger before other steps
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
# add a logging filter
logging_filter = logging.Filter('mmdet')
logging_filter.filter = lambda record: record.find('mmdet') != -1
# init the meta dict to record some important information such as
# environment info and seed, which will be logged
meta = dict()
# log env info
env_info_dict = collect_env()
env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
dash_line = '-' * 60 + '\n'
logger.info('Environment info:\n' + dash_line + env_info + '\n' +
dash_line)
meta['env_info'] = env_info
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
# set random seeds
if args.seed is not None:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
model = build_detector(cfg.model)
logger.info(f'Model:\n{model}')
datasets = [
build_dataset(cfg.data.source_train),
build_dataset(cfg.data.target_train)
]
# if len(cfg.workflow) == 2:
# val_dataset = copy.deepcopy(cfg.data.val)
# val_dataset.pipeline = cfg.data.train.pipeline
# datasets.append(build_dataset(val_dataset))
if cfg.checkpoint_config is not None:
# save mmdet version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(mmdet_version=__version__,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_single_seg_detector(model,
datasets,
cfg,
distributed=distributed,
timestamp=timestamp,
meta=meta)
def main():
args = parse_args()
assert args.out or args.eval or args.format_only or args.show, \
('Please specify at least one operation (save/eval/format/show the '
'results) with the argument "--out", "--eval", "--format_only" '
'or "--show"')
if args.eval and args.format_only:
raise ValueError('--eval and --format_only cannot be both specified')
#if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
# raise ValueError('The output file must be a pkl file.')
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# set random seeds
if args.seed is not None:
set_random_seed(args.seed, deterministic=args.deterministic)
# build the dataloader
samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
dataset = build_dataset(cfg.data.test)
data_loader = build_dataloader(dataset,
samples_per_gpu=samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
if args.fuse_conv_bn:
model = fuse_module(model)
# old versions did not save class info in checkpoints, this walkaround is
# for backward compatibility
if 'CLASSES' in checkpoint['meta']:
model.CLASSES = checkpoint['meta']['CLASSES']
else:
model.CLASSES = dataset.CLASSES
if not distributed:
model = MMDataParallel(model, device_ids=[0])
outputs = single_gpu_test(model, data_loader, args.show, args.show_dir)
else:
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False)
outputs = multi_gpu_test(model, data_loader, args.tmpdir,
args.gpu_collect)
#pkl_saved_path = '/home/radmin/jk/code/seg/SelectiveSeg/work_dirs/20210322_pano_all_preds/results/output_pkl/results.pkl'
#outputs = mmcv.load(pkl_saved_path)
rank, _ = get_dist_info()
if rank == 0:
if args.out and args.need_pkl_res:
pkl_res_path = os.path.join(args.out, 'output_pkl')
mmcv.mkdir_or_exist(pkl_res_path)
pkl_res_path = os.path.join(pkl_res_path, 'results.pkl')
print(f'\nwriting results to {pkl_res_path}')
mmcv.dump(outputs, pkl_res_path)
if args.need_bin_res:
import torch
import numpy as np
bin_res_path = os.path.join(args.out, 'pred_label')
mmcv.mkdir_or_exist(bin_res_path)
box_res_path = os.path.join(args.out, 'box_label')
mmcv.mkdir_or_exist(box_res_path)
for i, res in enumerate(outputs):
sem_preds = res['sem_preds']
if 'ins_preds' not in res:
ins_preds = torch.zeros_like(sem_preds)
else:
ins_preds = res['ins_preds']
preds = torch.stack([sem_preds, ins_preds], dim=-1)
preds = preds.cpu().numpy()
preds = np.array(preds, dtype=np.uint8)
file_name = str(i).zfill(6)
postfix = '.bin'
preds.tofile(bin_res_path + '/' + file_name + postfix)
if 'pts_bbox' in res:
bbox_preds = res['pts_bbox']
bbox_3d = bbox_preds['boxes_3d'].tensor
dim = bbox_3d.size(1)
if dim == 3:
pseudo_size = bbox_3d.new_ones((bbox_3d.size(0), 3))
pseudo_theta = bbox_3d.new_zeros((bbox_3d.size(0), 1))
bbox_3d = torch.cat(
[bbox_3d, pseudo_size, pseudo_theta], dim=1)
else:
# check here
bbox_3d = torch.cat([
bbox_preds['boxes_3d'].gravity_center,
bbox_preds['boxes_3d'].tensor[:, 3:]
],
dim=1)
temp_label = bbox_preds['labels_3d'].view(-1, 1)
temp_score = bbox_preds['scores_3d'].view(-1, 1)
temp_id = torch.zeros_like(temp_score)
file_bbox_3d = torch.cat(
[temp_label, bbox_3d, temp_score, temp_id], dim=1)
file_bbox_3d = file_bbox_3d.numpy()
postfix = '.txt'
np.savetxt(box_res_path + '/' + file_name + postfix,
file_bbox_3d,
fmt='%.3f')
if 'seg' in args.eval:
mmcv.mkdir_or_exist(args.out)
dataset.evaluate_seg(outputs,
result_names=['sem_preds'],
out_dir=args.out)
elif 'pano' in args.eval:
import numpy as np
from selective_seg.util_tools.evaluate_panoptic import init_eval, printResults, eval_one_scan
#log_file = osp.join(args.out, f'{timestamp}.log')
log_file = os.path.join(args.out, 'pano_res.log')
logger = get_root_logger(log_file=log_file,
log_level=cfg.log_level)
gt_label_path = '/data/nuscenes_opendata/ordered_seg_label/val/seg_ins_mask'
mmcv.mkdir_or_exist(args.out)
min_points = 15 # 15 for nuscenes, 50 for semantickitti official param
evaluator = init_eval(dataset_type=cfg['dataset_type'],
min_points=min_points)
for i in range(len(outputs)):
gt_file_path = os.path.join(gt_label_path,
str(i).zfill(6) + '.bin')
gt_labels = np.fromfile(gt_file_path,
dtype=np.uint8).reshape(-1, 2)
gt_sem_labels = gt_labels[:, 0]
gt_ins_labels = gt_labels[:, 1]
pred_sem_labels = outputs[i]['sem_preds'].cpu().numpy()
pred_ins_labels = outputs[i]['ins_preds'].cpu().numpy()
eval_one_scan(evaluator, gt_sem_labels, gt_ins_labels,
pred_sem_labels, pred_ins_labels)
eval_results = printResults(evaluator, logger=logger)
'''
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
if args.cfg_options is not None:
cfg.merge_from_dict(args.cfg_options)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
# work_dir is determined in this priority: CLI > segment in file > filename
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.resume_from is not None:
cfg.resume_from = args.resume_from
if args.gpus is not None:
cfg.gpu_ids = range(1)
warnings.warn('`--gpus` is deprecated because we only support '
'single GPU mode in non-distributed training. '
'Use `gpus=1` now.')
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids[0:1]
warnings.warn('`--gpu-ids` is deprecated, please use `--gpu-id`. '
'Because we only support single GPU mode in '
'non-distributed training. Use the first GPU '
'in `gpu_ids` now.')
if args.gpus is None and args.gpu_ids is None:
cfg.gpu_ids = [args.gpu_id]
if args.autoscale_lr:
# apply the linear scaling rule (https://arxiv.org/abs/1706.02677)
cfg.optimizer['lr'] = cfg.optimizer['lr'] * len(cfg.gpu_ids) / 8
# init distributed env first, since logger depends on the dist info.
if args.launcher == 'none':
distributed = False
else:
distributed = True
init_dist(args.launcher, **cfg.dist_params)
# re-set gpu_ids with distributed training mode
_, world_size = get_dist_info()
cfg.gpu_ids = range(world_size)
# create work_dir
mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
# dump config
cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
# init the logger before other steps
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
# specify logger name, if we still use 'mmdet', the output info will be
# filtered and won't be saved in the log_file
# TODO: ugly workaround to judge whether we are training det or seg model
if cfg.model.type in ['EncoderDecoder3D']:
logger_name = 'mmseg'
else:
logger_name = 'mmdet'
logger = get_root_logger(log_file=log_file,
log_level=cfg.log_level,
name=logger_name)
# init the meta dict to record some important information such as
# environment info and seed, which will be logged
meta = dict()
# log env info
env_info_dict = collect_env()
env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
dash_line = '-' * 60 + '\n'
logger.info('Environment info:\n' + dash_line + env_info + '\n' +
dash_line)
meta['env_info'] = env_info
meta['config'] = cfg.pretty_text
# log some basic info
logger.info(f'Distributed training: {distributed}')
logger.info(f'Config:\n{cfg.pretty_text}')
# set random seeds
if args.seed is not None:
logger.info(f'Set random seed to {args.seed}, '
f'deterministic: {args.deterministic}')
set_random_seed(args.seed, deterministic=args.deterministic)
cfg.seed = args.seed
meta['seed'] = args.seed
meta['exp_name'] = osp.basename(args.config)
model = build_model(cfg.model,
train_cfg=cfg.get('train_cfg'),
test_cfg=cfg.get('test_cfg'))
model.init_weights()
logger.info(f'Model:\n{model}')
datasets = [build_dataset(cfg.data.train)]
if len(cfg.workflow) == 2:
val_dataset = copy.deepcopy(cfg.data.val)
# in case we use a dataset wrapper
if 'dataset' in cfg.data.train:
val_dataset.pipeline = cfg.data.train.dataset.pipeline
else:
val_dataset.pipeline = cfg.data.train.pipeline
# set test_mode=False here in deep copied config
# which do not affect AP/AR calculation later
# refer to https://mmdetection3d.readthedocs.io/en/latest/tutorials/customize_runtime.html#customize-workflow # noqa
val_dataset.test_mode = False
datasets.append(build_dataset(val_dataset))
if cfg.checkpoint_config is not None:
# save mmdet version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(
mmdet_version=mmdet_version,
mmseg_version=mmseg_version,
mmdet3d_version=mmdet3d_version,
config=cfg.pretty_text,
CLASSES=datasets[0].CLASSES,
PALETTE=datasets[0].PALETTE # for segmentors
if hasattr(datasets[0], 'PALETTE') else None)
# add an attribute for visualization convenience
model.CLASSES = datasets[0].CLASSES
train_model(model,
datasets,
cfg,
distributed=distributed,
validate=(not args.no_validate),
timestamp=timestamp,
meta=meta)
