def read_config(self):
config_path = self.config_path
cfg_from_yaml_file(self.config_path, cfg)
self.logger = common_utils.create_logger()
self.demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(
"/home/muzi2045/Documents/project/OpenPCDet/data/kitti/velodyne/000001.bin"
),
ext='.bin')
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.net = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.demo_dataset)
self.net.load_params_from_file(filename=self.model_path,
logger=self.logger,
to_cpu=True)
self.net = self.net.to(self.device).eval()
# nuscenes dataset
lidar2imu_t = np.array([0.985793, 0.0, 1.84019])
lidar2imu_r = Quaternion(
[0.706749235, -0.01530099378, 0.0173974518, -0.7070846])
self.lidar2imu = transform_matrix(lidar2imu_t,
lidar2imu_r,
inverse=True)
self.imu2lidar = transform_matrix(lidar2imu_t,
lidar2imu_r,
inverse=False)
def main():
args, cfg = parse_config()
logger.info(
'-----------------Quick Demo 3D of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
# print instructions
print("To navigate:")
print("\tb: back (previous scan)")
print("\tn: next (next scan)")
print("\tq: quit (exit program)")
# run the visualizer
vis = VisualizeDets(model, demo_dataset)
vis.run()
logger.info('Demo done.')
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info('-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), ext=args.ext, logger=logger
)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
V.draw_scenes(
points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
)
if not OPEN3D_FLAG:
mlab.show(stop=True)
logger.info('Demo done.')
def main():
args, cfg = parse_config()
if args.launcher == 'none':
dist_test = False
else:
args.batch_size, cfg.LOCAL_RANK = getattr(common_utils, 'init_dist_%s' % args.launcher)(
args.batch_size, args.tcp_port, args.local_rank, backend='nccl'
)
dist_test = True
output_dir = cfg.ROOT_DIR / 'output' / cfg.EXP_GROUP_PATH / cfg.TAG / args.extra_tag
output_dir.mkdir(parents=True, exist_ok=True)
eval_output_dir = output_dir / 'eval'
if not args.eval_all:
num_list = re.findall(r'\d+', args.ckpt) if args.ckpt is not None else []
epoch_id = num_list[-1] if num_list.__len__() > 0 else 'no_number'
eval_output_dir = eval_output_dir / ('epoch_%s' % epoch_id) / cfg.DATA_CONFIG.DATA_SPLIT['test']
else:
eval_output_dir = eval_output_dir / 'eval_all_default'
if args.eval_tag is not None:
eval_output_dir = eval_output_dir / args.eval_tag
eval_output_dir.mkdir(parents=True, exist_ok=True)
log_file = eval_output_dir / ('log_eval_%s.txt' % datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
logger = common_utils.create_logger(log_file, rank=cfg.LOCAL_RANK)
# log to file
logger.info('**********************Start logging**********************')
gpu_list = os.environ['CUDA_VISIBLE_DEVICES'] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys() else 'ALL'
logger.info('CUDA_VISIBLE_DEVICES=%s' % gpu_list)
if dist_test:
total_gpus = dist.get_world_size()
logger.info('total_batch_size: %d' % (total_gpus * args.batch_size))
for key, val in vars(args).items():
logger.info('{:16} {}'.format(key, val))
log_config_to_file(cfg, logger=logger)
ckpt_dir = args.ckpt_dir if args.ckpt_dir is not None else output_dir / 'ckpt'
test_set, test_loader, sampler = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=dist_test, workers=args.workers, logger=logger, training=False
)
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=test_set)
with torch.no_grad():
if args.eval_all:
repeat_eval_ckpt(model, test_loader, args, eval_output_dir, logger, ckpt_dir, dist_test=dist_test)
else:
eval_single_ckpt(model, test_loader, args, eval_output_dir, logger, epoch_id, dist_test=dist_test)
def load_model(self):
model = build_network(model_cfg=self.cfg.MODEL,
num_class=len(self.cfg.CLASS_NAMES),
dataset=self.preprocesiing)
model.load_params_from_file(filename=self.args.ckpt,
logger=self.logger,
to_cpu=True)
model.cuda()
model.eval()
return model
def initialize_model():
"""Method that will be called by the evaluation script to load the model and weights.
"""
global model
model = build_network(model_cfg=model_cfg.MODEL,
num_class=len(model_cfg.CLASS_NAMES),
dataset=dataset_processor)
model.load_params_from_file(MODEL_WEIGHTS, logger=logger, to_cpu=False)
model.cuda()
model.eval()
def main():
args, cfg = parse_config()
log_file = 'log_inference_%s.txt' % datetime.datetime.now().strftime(
'%Y%m%d-%H%M%S')
logger = common_utils.create_logger(log_file, rank=0)
logger.info(
'-----------------Inference of OpenPCDet-------------------------')
test_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(test_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=test_dataset)
model.load_params_from_file(filename=args.ckpt,
logger=logger,
to_cpu=False)
model.cuda()
model.eval()
if args.save_video_path is not None:
fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(os.path.join(args.save_video_path, 'result.avi'),
fourcc, 10.0, (400, 1600))
bev_range = [-5, -20, -2, 155, 20, 5]
with torch.no_grad():
for idx, data_dict in tqdm(enumerate(test_dataset)):
data_dict = test_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
if args.save_video_path is not None:
boxes = pred_dicts[0]['pred_boxes'].cpu().detach().numpy()
boxes = boxes[:, np.newaxis, :].repeat(3, axis=1)
gt_boxes = None
if test_dataset.split == 'val':
gt_boxes = test_dataset.val_data_list[idx]['annos'][
'gt_boxes_lidar']
gt_boxes = gt_boxes[:, np.newaxis, :].repeat(3, axis=1)
image = plot_multiframe_boxes(
data_dict['points'][:, 1:].cpu().numpy(),
boxes,
bev_range,
gt_boxes=gt_boxes)
cv2.imshow('show_result', image)
cv2.waitKey(1)
out.write(image)
out.release()
def inference_with_info():
demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
with torch.no_grad():
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
for idx, data_dict in tqdm(enumerate(demo_dataset)):
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
det_boxes = pred_dicts[0]['pred_boxes'].cpu().detach().numpy()
scores = pred_dicts[0]['pred_scores'].cpu().numpy()
labels = pred_dicts[0]['pred_labels'].cpu().numpy()
gt_boxes = demo_dataset.val_data_list[idx]['annos']['gt_boxes_lidar']
# Evaluate current frame
info = ''
for iou_idx in range(len(ious)):
for dist_range_idx in range(len(dist_ranges)):
tp, num_valid_det, num_valid_gt, dist_err = get_metrics(gt_boxes, det_boxes,
dist_ranges[dist_range_idx],
ious[iou_idx])
total_num_tp[iou_idx, dist_range_idx] += tp
total_num_valid_det[iou_idx, dist_range_idx] += num_valid_det
total_num_valid_gt[iou_idx, dist_range_idx] += num_valid_gt
total_dist_err[iou_idx, dist_range_idx] += dist_err
info += 'tp: {}, dt: {}, gt: {}\n'.format(tp, num_valid_det, num_valid_gt)
det_boxes = det_boxes[:, np.newaxis, :].repeat(3, axis=1)
gt_boxes = gt_boxes[:, np.newaxis, :].repeat(3, axis=1)
image = plot_multiframe_boxes(data_dict['points'][:, 1:].cpu().numpy(),
det_boxes, cfg.DATA_CONFIG.POINT_CLOUD_RANGE, gt_boxes=gt_boxes,
scores=scores, labels=labels)
info = info.split("\n")
fontScale = 0.6
thickness = 1
fontFace = cv2.FONT_HERSHEY_SIMPLEX
text_size, baseline = cv2.getTextSize(str(info), fontFace, fontScale, thickness)
for i, text in enumerate(info):
if text:
draw_point = (10, 10 + (text_size[1] + 2 + baseline) * i)
cv2.putText(image, text, draw_point, fontFace=fontFace,
fontScale=fontScale, color=(0, 255, 0), thickness=thickness)
[bag_name, _, frame] = demo_dataset.val_data_list[idx]['point_cloud']['lidar_idx'].split('/')
image_file = os.path.join(save_path, bag_name + '_' + frame[:-4] + '.png')
cv2.imwrite(image_file, image)
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info('-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), ext=args.ext, logger=logger
)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
points=data_dict['points'][:, 1:]
ref_boxes=pred_dicts[0]['pred_boxes']
ref_scores=pred_dicts[0]['pred_scores']
ref_labels=pred_dicts[0]['pred_labels']
points_cp=points.cpu()
points_nu=points_cp.numpy()
ref_boxes_cp=ref_boxes.cpu()
ref_boxes_nu=ref_boxes_cp.numpy()
ref_scores_cp=ref_scores.cpu()
ref_scores_nu=ref_scores_cp.numpy()
ref_labels_cp=ref_labels.cpu()
ref_labels_nu=ref_labels_cp.numpy()
print(points.shape,ref_boxes.shape)
print(ref_scores.shape,ref_labels.shape)
#with open('./save1.npy', 'wb') as f:
# np.save(f,points_nu)
#with open('./save2.npy', 'wb') as f:
# np.save(f,ref_boxes_nu)
#with open('./save3.npy', 'wb') as f:
# np.save(f,ref_scores_nu)
#with open('./save4.npy', 'wb') as f:
# np.save(f,ref_labels_nu)
#np.array(points.shape).tofile(f)
#points.tofile(f)
# V.draw_scenes(
# points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
# ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
# )
# mlab.show(stop=True)
logger.info('Demo done.')
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info('-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), ext=args.ext, logger=logger
)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
if args.saved_pred == "":
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
with open('../saved_pred/curr_pickle.pkl', 'wb+') as f:
data_ = {
"data_dict": data_dict['points'][:, 1:],
"pred_dicts": pred_dicts
}
pkl.dump(data_, f)
else:
with open('../saved_pred/curr_pickle.pkl', 'rb') as f:
data_ = pkl.load(f)
data_dict = data_["data_dict"]
pred_dicts = data_["pred_dicts"]
vdisplay = Xvfb(width=1920, height=1080)
vdisplay.start()
V.draw_scenes(
points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
)
vdisplay.stop()
mlab.show(stop=True)
mlab.savefig("./test_eg.png")
logger.info('Demo done.')
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
data_name_list = demo_dataset.sample_file_list
# print(data_name_list)
print('evaluation data size=', len(data_name_list))
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
# logger.info(f'Visualized sample index: \t{idx + 1}')
logger.info(f'Detecte sample: \t{data_name_list[idx]}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
print(pred_dicts)
# print(data_dict)
# print(type(pred_dicts[0]['pred_boxes']))
# print(pred_dicts[0]['pred_boxes'])
res = pred_dicts[0]['pred_boxes'].cpu().numpy().round(8)
save_filename = str(data_name_list[idx])
np.savetxt('evaluation/' +
save_filename[save_filename.rfind('/') + 1:].replace(
'.bin', '.txt'),
res,
fmt='%.08f')
# test_f.writelines(pred_dicts[0]['pred_boxes'])
V.draw_scenes(points=data_dict['points'][:, 1:],
ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'],
ref_labels=pred_dicts[0]['pred_labels'])
mlab.show(stop=True)
logger.info('Demo done.')
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, (data_dict, data_path) in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
logger.info("Process: %s" % data_path)
pred_s = dict()
pred_s["data_path"] = data_path
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
pred_s['pred_boxes'] = pred_dicts[0]['pred_boxes'].cpu().numpy(
).tolist()
pred_s['pred_scores'] = pred_dicts[0]['pred_scores'].cpu().numpy(
).tolist()
pred_s['pred_labels'] = pred_dicts[0]['pred_labels'].cpu().numpy(
).tolist()
json_path = os.path.splitext(data_path)[0] + ".json"
with open(json_path, 'w') as fp:
json.dump(pred_s, fp)
# exit(1)
# V.draw_scenes(
# points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
# ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
# )
#
# mlab.show(stop=True)
logger.info('Demo done.')
def setup_model(self):
cfg_from_yaml_file(self.detector_config, cfg)
self.logger = common_utils.create_logger()
self.dataset = DummyDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES)
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.net = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.dataset)
self.net.load_params_from_file(filename=self.model_path,
logger=self.logger,
to_cpu=True)
self.net = self.net.to(self.device).eval()
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
# display = Display(visible=0, size =(1280, 1024))
# display.start()
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
# V.draw_scenes(
# points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
# ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
# )
boxes_file = open(args.save + '_boxes', 'wb')
scores_file = open(args.save + '_scores', 'wb')
labels_file = open(args.save + '_labels', 'wb')
pickle.dump(pred_dicts[0]['pred_boxes'].cpu().numpy(),
boxes_file,
protocol=4)
pickle.dump(pred_dicts[0]['pred_scores'].cpu().numpy(),
scores_file,
protocol=4)
pickle.dump(pred_dicts[0]['pred_labels'].cpu().numpy(),
labels_file,
protocol=4)
boxes_file.close()
scores_file.close()
labels_file.close()
logger.info('Demo done.')
def main():
for sweep in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]:
lines = open(
'cfgs/dataset_configs/nuscenes_dataset.yaml').read().splitlines()
lines[4] = 'MAX_SWEEPS: ' + str(sweep)
open('cfgs/dataset_configs/nuscenes_dataset.yaml',
'w').write('\n'.join(lines))
args, cfg = parse_config()
logger = common_utils.create_logger()
demo_dataset = NuScenesDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
logger=logger)
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt,
logger=logger,
to_cpu=True)
model.cuda()
model.eval()
times = []
for i in range(args.frames):
with torch.no_grad():
data_dict = demo_dataset[i]
start = time.time()
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
end = time.time()
times.append(end - start)
print("sweeps", sweep)
print("min", 1 / min(times))
print("1st_quantile", 1 / np.quantile(times, .25))
print("median", 1 / statistics.median(times))
print("1st_quantile", 1 / np.quantile(times, .75))
print("max", 1 / max(times))
print()
def __init__(self, input_dict):
# pvrcnn cfg
cfg_from_yaml_file(input_dict.cfg_file, cfg)
# create logger
log_dir = Path(str(input_dict.output_dir)) / 'log'
log_dir.mkdir(parents=True, exist_ok=True)
self.logger = common_utils.create_logger(
log_dir /
('log_%s.txt' % datetime.datetime.now().strftime('%Y%m%d-%H%M%S')),
rank=cfg.LOCAL_RANK)
# build dataset and network
self.demo_dataset = DemoDataset( # dummy dataset for preprocess inputdata
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=input_dict.dummy_cloud,
ext='.bin',
logger=self.logger)
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.demo_dataset)
self.model.load_params_from_file(filename=input_dict.ckpt_file,
logger=self.logger,
to_cpu=self.device == "cpu")
self.model.to(self.device)
self.model.eval()
self.score_threshold = input_dict.score_threashold
# for ROS
self.action_server = actionlib.SimpleActionServer(
"excavator/lidar_perception/ros_pvrcnn_action",
detector3dAction,
execute_cb=self.execute_cb,
auto_start=False)
self.action_server.start()
self.mk_pub = rospy.Publisher("ros_pvrcnn", MarkerArray, queue_size=1)
self.cls_list = [String(cls) for cls in cfg.CLASS_NAMES]
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info('-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), ext=args.ext, logger=logger
)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
avg_time = 0
avg_fps = 0
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: {idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
start = time()
pred_dicts, _ = model.forward(data_dict)
end = time()
time_forward = (end - start) * 1000
if idx > 0:
avg_time += time_forward
avg_fps += 1000 / time_forward
logger.info(f'Time in ms for sample index: {idx + 1} is {"{:.2f}".format(time_forward)} ms')
logger.info(f'FPS for sample index: {idx + 1} is {"{:.2f}".format(1000 / time_forward)} frame per second')
V.draw_scenes(
points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
)
mlab.show(stop=True)
avg_time /= len(demo_dataset) - 1
avg_fps /= len(demo_dataset) - 1
logger.info(f'Average Time in ms for {paper.type}: is {"{:.2f}".format(avg_time)} ms')
logger.info(f'Average FPS for {paper.type}: is {"{:.2f}".format(avg_fps)} frame per second')
logger.info('Demo done.')
def main():
args, cfg = parse_config()
logger = common_utils.create_logger() #logger记录日志
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
#建立一个DemoDataset类，其中储存关于输入数据的所有信息，包含六个参数
# dataset_cfg=cfg.DATA_CONFIG # 数据参数
# 包含数据集 / 数据路径 / 信息路径 / 数据处理器 / 数据增强器等
# class_names=cfg.CLASS_NAMES # 类别名
# training=False # 是否训练
# root_path=Path(args.data_path) # 数据路径
# ext=args.ext # 扩展
# logger=logger # 日志
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad(): #目的是使得其中的数据不需要计算梯度，也不会进行反向传播
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
V.draw_scenes(points=data_dict['points'][:, 1:],
ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'],
ref_labels=pred_dicts[0]['pred_labels'])
mlab.show(stop=True)
logger.info('Demo done.')
def read_config(self):
config_path = self.config_path
cfg_from_yaml_file(self.config_path, cfg)
self.logger = common_utils.create_logger()
self.demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path("/none"),
ext='.bin')
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.net = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.demo_dataset)
print("Model path: ", self.model_path)
self.net.load_params_from_file(filename=self.model_path,
logger=self.logger,
to_cpu=True)
self.net = self.net.to(self.device).eval()
def main():
# 1 输入参数
args, cfg = parse_config() # cfg的参数在tools/cfg/kitti_models/pv-rcnn.yaml
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
# 2 调用的这些包就是pcdet/models/detectors下的各个py文件，
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
# 3 参数加载
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
# cuda( ) 和 eval( ) 都是数据处理
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}') # 样本数
# 4. collate_batch
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict) # 传递数据给gpu的
pred_dicts, _ = model.forward(
data_dict
) # 在神经网络中向前传递数据data_dict，得到预测数据pred_dicts 定位到forward，因为是PVRCNN类下的函数，先看__init__ /home/hcq/pointcloud/PCDet/pcdet/models/detectors/pv_rcnn.py
# 可视化V
V.draw_scenes(points=data_dict['points'][:, 1:],
ref_boxes=pred_dicts[0]['pred_boxes'],
ref_scores=pred_dicts[0]['pred_scores'],
ref_labels=pred_dicts[0]['pred_labels'])
mlab.show(stop=True)
logger.info('Demo done.')
def read_config(self):
config_path = self.config_path
cfg_from_yaml_file(self.config_path, cfg)
self.logger = common_utils.create_logger()
self.demo_dataset = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(
"/home/muzi2045/Documents/project/OpenPCDet/data/kitti/velodyne/000001.bin"
),
ext='.bin')
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
self.net = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.demo_dataset)
self.net.load_params_from_file(filename=self.model_path,
logger=self.logger,
to_cpu=True)
self.net = self.net.to(self.device).eval()
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Inference of OpenPCDet-------------------------'
)
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.data_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Run inference of sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, recall_dicts, batch_dict = model.forward(data_dict)
#visualization
if args.vis:
V.visualize_voxel_prediction(batch_dict)
#evaluate point predictions
if args.point:
E.save_prediction_point_argoverse(batch_dict,
save_gt=args.save_gt)
logger.info('Quick inference done.')
def read_config(self):
print(self.config_path)
config_path = self.config_path
cfg_from_yaml_file(self.config_path, cfg)
self.logger = common_utils.create_logger()
self.demo_datasets = DemoDataset(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(
'/home/syang/Data/RS_datasets/datasets/ruby119_longzhudadao_1200423181920/npy/ruby119_longzhudadao_1200423181920_755.npy'
),
ext='.npy')
self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")
print(self.device)
self.net = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=self.demo_datasets)
self.net.load_params_from_file(filename=self.model_path,
logger=self.logger,
to_cpu=True)
self.net = self.net.to(self.device).eval()
def main():
args, cfg = parse_config()
if args.launcher == 'none':
dist_test = False
total_gpus = 1
else:
total_gpus, cfg.LOCAL_RANK = getattr(common_utils, 'init_dist_%s' %
args.launcher)(args.tcp_port,
args.local_rank,
backend='nccl')
dist_test = True
assert not dist_test and args.batch_size == 1
if args.batch_size is None:
args.batch_size = cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU
else:
assert args.batch_size % total_gpus == 0, 'Batch size should match the number of gpus'
args.batch_size = args.batch_size // total_gpus
output_dir = cfg.ROOT_DIR / 'output' / cfg.EXP_GROUP_PATH / cfg.TAG / args.extra_tag
output_dir.mkdir(parents=True, exist_ok=True)
eval_output_dir = Path('deploy/eval')
if args.eval_tag is not None:
eval_output_dir = eval_output_dir / args.eval_tag
eval_output_dir.mkdir(parents=True, exist_ok=True)
log_file = eval_output_dir / (
'log_eval_%s.txt' % datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
logger = common_utils.create_logger(log_file, rank=cfg.LOCAL_RANK)
# log to file
logger.info('**********************Start logging**********************')
gpu_list = os.environ[
'CUDA_VISIBLE_DEVICES'] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(
) else 'ALL'
logger.info('CUDA_VISIBLE_DEVICES=%s' % gpu_list)
if dist_test:
logger.info('total_batch_size: %d' % (total_gpus * args.batch_size))
for key, val in vars(args).items():
logger.info('{:16} {}'.format(key, val))
log_config_to_file(cfg, logger=logger)
test_set, test_loader, sampler = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=dist_test,
workers=args.workers,
logger=logger,
training=False)
if args.pruned_model is not None:
tag = 'pruned_model'
model = torch.load(args.pruned_model, map_location=torch.device('cpu'))
elif args.pretrained_model is not None:
tag = 'large_model'
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=test_set)
model.load_params_from_file(filename=args.pretrained_model,
logger=logger,
to_cpu=dist_test)
else:
raise RuntimeError('error: please input weights.')
model = model.cuda()
model.eval()
ExportModel = OnnxModelPointPillars(model)
ExportModel.eval()
ExportModel = ExportModel.cuda()
points = np.fromfile(args.pcs_for_export, dtype=np.float32).reshape(-1, 4)
points = torch.from_numpy(points).float().cuda()
points = torch.autograd.Variable(points.contiguous())
valid = torch.Tensor([len(points)]).int().cuda()
dummy_input = torch.zeros((25000, 4)).float().cuda()
dummy_input[:len(points)] = points
torch.onnx.export(
ExportModel, (dummy_input, valid),
"pointpillars_%s.onnx" % tag,
verbose=True,
training=False,
operator_export_type=torch.onnx.OperatorExportTypes.ONNX_ATEN_FALLBACK,
opset_version=10,
input_names=['points', 'valid'],
output_names=['pointpillars_output1', 'pointpillars_output2'])
if args.eval_onnx_model:
with torch.no_grad():
eval_single_ckpt_onnx(ExportModel,
test_loader,
args,
eval_output_dir,
logger,
tag,
dist_test=dist_test)
def main():
args, cfg = parse_config()
dist_test = False
total_gpus = 1
if args.batch_size is None:
args.batch_size = cfg.OPTIMIZATION.BATCH_SIZE_PER_GPU
else:
assert args.batch_size % total_gpus == 0, 'Batch size should match the number of gpus'
args.batch_size = args.batch_size // total_gpus
output_dir = cfg.ROOT_DIR / 'output' / cfg.EXP_GROUP_PATH / cfg.TAG / args.extra_tag
output_dir.mkdir(parents=True, exist_ok=True)
eval_output_dir = output_dir / 'eval'
epoch_id = '110'
eval_output_dir = eval_output_dir / (
'epoch_%s' % epoch_id) / cfg.DATA_CONFIG.DATA_SPLIT['test']
eval_tag = 'play'
eval_output_dir = eval_output_dir / eval_tag
eval_output_dir.mkdir(parents=True, exist_ok=True)
log_file = eval_output_dir / (
'log_eval_%s.txt' % datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
logger = common_utils.create_logger(log_file, rank=cfg.LOCAL_RANK)
# log to file
logger.info('**********************Start logging**********************')
gpu_list = os.environ[
'CUDA_VISIBLE_DEVICES'] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(
) else 'ALL'
logger.info('CUDA_VISIBLE_DEVICES=%s' % gpu_list)
if dist_test:
logger.info('total_batch_size: %d' % (total_gpus * args.batch_size))
for key, val in vars(args).items():
logger.info('{:16} {}'.format(key, val))
log_config_to_file(cfg, logger=logger)
test_set, test_loader, sampler = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=dist_test,
workers=args.workers,
logger=logger,
training=False)
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=test_set)
with torch.no_grad():
eval_single_ckpt(model,
test_loader,
args,
output_dir,
eval_output_dir,
logger,
epoch_id,
dist_test=dist_test)
def main():
args, cfg = parge_config()
if args.launcher == 'none':
dist_train = False
else:
args.batch_size, cfg.LOCAL_RANK = getattr(
common_utils, 'init_dist_%s' % args.launcher)(args.batch_size,
args.tcp_port,
args.local_rank,
backend='nccl')
dist_train = True
if args.fix_random_seed:
common_utils.set_random_seed(666)
output_dir = cfg.ROOT_DIR / 'output' / cfg.TAG / args.extra_tag
output_dir.mkdir(parents=True, exist_ok=True)
ckpt_dir = output_dir / 'ckpt'
ckpt_dir.mkdir(parents=True, exist_ok=True)
log_file = output_dir / ('log_train_%s.txt' %
datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
logger = common_utils.create_logger(log_file, rank=cfg.LOCAL_RANK)
# log to file
logger.info('**********************Start logging**********************')
gpu_list = os.environ[
'CUDA_VISIBLE_DEVICES'] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(
) else 'ALL'
logger.info('CUDA_VISIBLE_DEVICES=%s' % gpu_list)
if dist_train:
total_gpus = dist.get_world_size()
logger.info('total_batch_size: %d' % (total_gpus * args.batch_size))
for key, val in vars(args).items():
logger.info('{:16} {}'.format(key, val))
log_config_to_file(cfg, logger=logger)
tb_log = SummaryWriter(
log_dir=str(output_dir /
'tensorboard')) if cfg.LOCAL_RANK == 0 else None
if args.local_rank == 0:
wandb.init(project='BEVSEG-PCDet',
sync_tensorboard=True,
name=args.extra_tag,
config={
**vars(args),
**cfg
})
# -----------------------create dataloader & network & optimizer---------------------------
train_set, train_loader, train_sampler = build_dataloader(
cfg.DATA_CONFIG.DATA_DIR,
args.batch_size,
dist_train,
workers=args.workers,
logger=logger,
training=True)
model = build_network(train_set)
if args.sync_bn:
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
model.cuda()
optimizer = build_optimizer(model, cfg.MODEL.TRAIN.OPTIMIZATION)
# load checkpoint if it is possible
start_epoch = it = 0
last_epoch = -1
if args.pretrained_model is not None:
model.load_params_from_file(filename=args.pretrained_model,
to_cpu=dist,
logger=logger)
if args.ckpt is not None:
it, start_epoch = model.load_params_with_optimizer(args.ckpt,
to_cpu=dist,
optimizer=optimizer,
logger=logger)
last_epoch = start_epoch + 1
else:
ckpt_list = glob.glob(str(ckpt_dir / '*checkpoint_epoch_*.pth'))
if len(ckpt_list) > 0:
ckpt_list.sort(key=os.path.getmtime)
it, start_epoch = model.load_params_with_optimizer(
ckpt_list[-1], to_cpu=dist, optimizer=optimizer, logger=logger)
last_epoch = start_epoch + 1
model.train(
) # before wrap to DistributedDataParallel to support fixed some parameters
if dist_train:
model = nn.parallel.DistributedDataParallel(
model,
device_ids=[cfg.LOCAL_RANK % torch.cuda.device_count()],
find_unused_parameters=
True # uncomment this line to debug unused params
)
logger.info(model)
lr_scheduler, lr_warmup_scheduler = build_scheduler(
optimizer,
total_iters_each_epoch=len(train_loader),
total_epochs=args.epochs,
last_epoch=last_epoch,
optim_cfg=cfg.MODEL.TRAIN.OPTIMIZATION)
# -----------------------start training---------------------------
logger.info(
'**********************Start training %s(%s)**********************' %
(cfg.TAG, args.extra_tag))
train_model(model,
optimizer,
train_loader,
model_func=model_fn_decorator(),
lr_scheduler=lr_scheduler,
optim_cfg=cfg.MODEL.TRAIN.OPTIMIZATION,
start_epoch=start_epoch,
total_epochs=args.epochs,
start_iter=it,
rank=cfg.LOCAL_RANK,
tb_log=tb_log,
ckpt_save_dir=ckpt_dir,
train_sampler=train_sampler,
lr_warmup_scheduler=lr_warmup_scheduler,
ckpt_save_interval=args.ckpt_save_interval,
max_ckpt_save_num=args.max_ckpt_save_num)
logger.info('**********************End training**********************')
'''
def main():
args, cfg = parse_config()
curr_seq = args.seq_path.split("/")[-1]
logger = common_utils.create_logger()
logger.info(
'-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = DemoDataset(dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
training=False,
root_path=Path(args.seq_path),
ext=args.ext,
logger=logger)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
# Removing existing csv file
csv_file_path = '%s/%s.csv' % (args.output_dir, curr_seq)
if os.path.exists(csv_file_path):
os.remove(csv_file_path)
# Loading the ground truth from kitti-odometry
gt_path = "/".join(
args.seq_path.split("/")[0:-2]) + "/label_02/" + curr_seq + ".txt"
gt_data = np.genfromtxt(gt_path,
dtype=str)[:, [0, 2, 13, 14, 15, 10, 11, 12, 16]]
gt_data = gt_data[np.logical_or(
gt_data[:, 1] == 'Car',
np.logical_or(gt_data[:,
1] == 'Cyclist', gt_data[:,
1] == 'Pedestrian')), :]
gt_data = gt_data[:, [0, 2, 3, 4, 5, 6, 7, 8]]
# Converting to floats
gt_data = gt_data.astype(np.float)
with torch.no_grad():
for idx, data_dict in enumerate(demo_dataset):
logger.info(f'Visualized sample index: \t{idx + 1}')
data_dict = demo_dataset.collate_batch([data_dict])
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
# Creating output dir if it does not already exist
Path(args.output_dir).mkdir(parents=True, exist_ok=True)
relevant_gt_boxes = gt_data[gt_data[:, 0] == idx][:, 1:]
data_ = {
"data_dict": data_dict['points'][:, 1:].cpu().detach().numpy(),
"pred_boxes":
pred_dicts[0]["pred_boxes"].cpu().detach().numpy(),
"pred_labels":
pred_dicts[0]["pred_labels"].cpu().detach().numpy(),
"pred_scores":
pred_dicts[0]["pred_scores"].cpu().detach().numpy(),
"gt_boxes": relevant_gt_boxes
}
with open('%s/curr_pickle_%s.pkl' % (args.output_dir, str(idx)),
'wb+') as f:
pkl.dump(data_, f)
# Writing to text file in kitti format for tracking step
frame_data = np.zeros((data_["pred_labels"].shape[0], 15))
frame_data[:, 0] = idx # Frame ID
frame_data[:, 1] = data_["pred_labels"] # Labels
frame_data[:, 2:6] = 0 # 2d bounding boxes
frame_data[:, 6] = data_["pred_scores"] # 2d bounding boxes
frame_data[:, 7:10] = data_["pred_boxes"][:, 3:6]
frame_data[:, 10:13] = data_["pred_boxes"][:, 0:3]
frame_data[:, 13] = data_["pred_boxes"][:, -1]
frame_data[:, 14] = 0 # Alpha
with open('%s/%s.csv' % (args.output_dir, curr_seq), 'a') as f:
np.savetxt(f, frame_data, delimiter=",")
def main():
args, cfg = parse_config()
logger = common_utils.create_logger()
logger.info('-----------------Quick Demo of OpenPCDet-------------------------')
demo_dataset = NuScenesDataset(
dataset_cfg=cfg.DATA_CONFIG, class_names=cfg.CLASS_NAMES, training=False,
root_path=Path(args.data_path), logger=logger
)
logger.info(f'Total number of samples: \t{len(demo_dataset)}')
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=demo_dataset)
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=True)
model.cuda()
model.eval()
start = time.time()
with torch.no_grad():
data_dict = demo_dataset[args.idx]
print(type(data_dict))
print(data_dict)
logger.info(f'Visualized sample index: \t{args.idx}')
data_dict = demo_dataset.collate_batch([data_dict])
# print(type(data_dict))
# print(data_dict)
load_data_to_gpu(data_dict)
pred_dicts, _ = model.forward(data_dict)
# for bb in pred_dicts[0]['pred_boxes']:
# for x in bb:
# print(float(x), end=" ")
# print()
# pred_dicts[0]['pred_boxes'][:,0] = 1
# pred_dicts[0]['pred_boxes'][:,1] = 0
# pred_dicts[0]['pred_boxes'][:,2] = 1
# pred_dicts[0]['pred_boxes'][:,3] = 1
# pred_dicts[0]['pred_boxes'][:,4] = 1
# pred_dicts[0]['pred_boxes'][:,5] = 1
# pred_dicts[0]['pred_boxes'][:,6] = 0
# pred_dicts[0]['pred_boxes'] = pred_dicts[0]['pred_boxes'].cpu().numpy()
# foo = np.zeros((len(pred_dicts[0]['pred_boxes']), 2), dtype=pred_dicts[0]['pred_boxes'].dtype)
# pred_dicts[0]['pred_boxes'] = np.concatenate((pred_dicts[0]['pred_boxes'], foo), axis=1)
# pred_dicts[0]['pred_boxes'][:,7] = 0
# pred_dicts[0]['pred_boxes'][:,8] = 0
mask = (pred_dicts[0]['pred_scores']>0.3).float()
indices = torch.nonzero(mask)
V.draw_scenes(
points=data_dict['points'][:, 1:],
ref_boxes=pred_dicts[0]['pred_boxes'][indices].reshape(-1, 9),
ref_scores=pred_dicts[0]['pred_scores'][indices].reshape(-1), ref_labels=pred_dicts[0]['pred_labels'][indices].reshape(-1)
)
# mask = (pred_dicts[0]['pred_scores']>0.5).float()
# indices = torch.nonzero(mask)
# V.draw_scenes(
# points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'][indices].reshape(-1, 7),
# ref_scores=pred_dicts[0]['pred_scores'][indices].reshape(-1), ref_labels=pred_dicts[0]['pred_labels'][indices].reshape(-1)
# )
# print(pred_dicts[0]['pred_boxes'][indices])
# V.draw_scenes(
# points=data_dict['points'][:, 1:], ref_boxes=pred_dicts[0]['pred_boxes'],
# ref_scores=pred_dicts[0]['pred_scores'], ref_labels=pred_dicts[0]['pred_labels']
# )
mlab.show(stop=True)
end = time.time()
print(end-start)
logger.info('Demo done.')
def main():
args, cfg = parse_config()
if args.launcher == 'none':
dist_train = False
else:
args.batch_size, cfg.LOCAL_RANK = getattr(
common_utils, 'init_dist_%s' % args.launcher)(args.batch_size,
args.tcp_port,
args.local_rank,
backend='nccl')
dist_train = True
if args.fix_random_seed:
common_utils.set_random_seed(666)
output_dir = cfg.ROOT_DIR / 'output' / cfg.EXP_GROUP_PATH / cfg.TAG / args.extra_tag
ckpt_dir = output_dir / 'ckpt'
output_dir.mkdir(parents=True, exist_ok=True)
ckpt_dir.mkdir(parents=True, exist_ok=True)
log_file = output_dir / ('log_train_%s.txt' %
datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
logger = common_utils.create_logger(log_file, rank=cfg.LOCAL_RANK)
# log to file
logger.info('**********************Start logging**********************')
gpu_list = os.environ[
'CUDA_VISIBLE_DEVICES'] if 'CUDA_VISIBLE_DEVICES' in os.environ.keys(
) else 'ALL'
logger.info('CUDA_VISIBLE_DEVICES=%s' % gpu_list)
if dist_train:
total_gpus = dist.get_world_size()
logger.info('total_batch_size: %d' % (total_gpus * args.batch_size))
for key, val in vars(args).items():
logger.info('{:16} {}'.format(key, val))
log_config_to_file(cfg, logger=logger)
if cfg.LOCAL_RANK == 0:
os.system('cp %s %s' % (args.cfg_file, output_dir))
tb_log = SummaryWriter(
log_dir=str(output_dir /
'tensorboard')) if cfg.LOCAL_RANK == 0 else None
# -----------------------create dataloader & network & optimizer---------------------------
train_set, train_loader, train_sampler = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=dist_train,
workers=args.workers,
logger=logger,
training=True,
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch,
total_epochs=args.epochs)
model = build_network(model_cfg=cfg.MODEL,
num_class=len(cfg.CLASS_NAMES),
dataset=train_set)
if args.sync_bn:
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)
model.cuda()
optimizer = build_optimizer(model, cfg.OPTIMIZATION)
# load checkpoint if it is possible
start_epoch = it = 0
last_epoch = -1
if args.pretrained_model is not None:
model.load_params_from_file(filename=args.pretrained_model,
to_cpu=dist,
logger=logger)
if args.ckpt is not None:
it, start_epoch = model.load_params_with_optimizer(args.ckpt,
to_cpu=dist,
optimizer=optimizer,
logger=logger)
last_epoch = start_epoch + 1
else:
ckpt_list = glob.glob(str(ckpt_dir / '*checkpoint_epoch_*.pth'))
if len(ckpt_list) > 0:
ckpt_list.sort(key=os.path.getmtime)
it, start_epoch = model.load_params_with_optimizer(
ckpt_list[-1], to_cpu=dist, optimizer=optimizer, logger=logger)
last_epoch = start_epoch + 1
model.train(
) # before wrap to DistributedDataParallel to support fixed some parameters
if dist_train:
model = nn.parallel.DistributedDataParallel(
model, device_ids=[cfg.LOCAL_RANK % torch.cuda.device_count()])
logger.info(model)
lr_scheduler, lr_warmup_scheduler = build_scheduler(
optimizer,
total_iters_each_epoch=len(train_loader),
total_epochs=args.epochs,
last_epoch=last_epoch,
optim_cfg=cfg.OPTIMIZATION)
# -----------------------start training---------------------------
logger.info(
'**********************Start training %s/%s(%s)**********************'
% (cfg.EXP_GROUP_PATH, cfg.TAG, args.extra_tag))
train_model(model,
optimizer,
train_loader,
model_func=model_fn_decorator(),
lr_scheduler=lr_scheduler,
optim_cfg=cfg.OPTIMIZATION,
start_epoch=start_epoch,
total_epochs=args.epochs,
start_iter=it,
rank=cfg.LOCAL_RANK,
tb_log=tb_log,
ckpt_save_dir=ckpt_dir,
train_sampler=train_sampler,
lr_warmup_scheduler=lr_warmup_scheduler,
ckpt_save_interval=args.ckpt_save_interval,
max_ckpt_save_num=args.max_ckpt_save_num,
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch)
logger.info(
'**********************End training %s/%s(%s)**********************\n\n\n'
% (cfg.EXP_GROUP_PATH, cfg.TAG, args.extra_tag))
logger.info(
'**********************Start evaluation %s/%s(%s)**********************'
% (cfg.EXP_GROUP_PATH, cfg.TAG, args.extra_tag))
test_set, test_loader, sampler = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=dist_train,
workers=args.workers,
logger=logger,
training=False)
eval_output_dir = output_dir / 'eval' / 'eval_with_train'
eval_output_dir.mkdir(parents=True, exist_ok=True)
args.start_epoch = max(args.epochs - 10,
0) # Only evaluate the last 10 epochs
repeat_eval_ckpt(model.module if dist_train else model,
test_loader,
args,
eval_output_dir,
logger,
ckpt_dir,
dist_test=dist_train)
logger.info(
'**********************End evaluation %s/%s(%s)**********************'
% (cfg.EXP_GROUP_PATH, cfg.TAG, args.extra_tag))
def inference_with_scene():
total_gpus = 1
assert args.batch_size % total_gpus == 0, 'Batch size should match the number of gpus'
args.batch_size = args.batch_size // total_gpus
test_set, _, _ = build_dataloader(
dataset_cfg=cfg.DATA_CONFIG,
class_names=cfg.CLASS_NAMES,
batch_size=args.batch_size,
dist=False, workers=args.workers, training=False
)
# Load the data
mot_dataset_path = Path("/home/yao.xu/datasets/mot_dataset")
test_scene_list = os.listdir(mot_dataset_path)
test_scene_list.sort()
test_scene_list = test_scene_list[0:1]
model = build_network(model_cfg=cfg.MODEL, num_class=len(cfg.CLASS_NAMES), dataset=test_set)
with torch.no_grad():
# load checkpoint
model.load_params_from_file(filename=args.ckpt, logger=logger, to_cpu=False)
model.cuda()
model.eval()
# start inference
class_names = cfg.CLASS_NAMES
point_cloud_range = np.array(cfg.DATA_CONFIG.POINT_CLOUD_RANGE)
processor = DataProcessor(cfg.DATA_CONFIG.DATA_PROCESSOR, point_cloud_range, training=False)
frame_idx = 0
for test_scene in tqdm(test_scene_list):
test_scene_path = mot_dataset_path / test_scene
test_frame_list = os.listdir(test_scene_path / 'pointcloud')
for lidar_file in tqdm(test_frame_list):
with open(test_scene_path / 'pointcloud' / lidar_file, 'rb') as f:
points = np.fromfile(f, dtype=np.float32)
points = np.reshape(points, (-1, 4))[:, :3]
points = np.concatenate((points, np.zeros((points.shape[0], 1))), axis=1)
batch_dict = processor.forward({'points': points, 'use_lead_xyz': True, 'batch_size': 1})
batch_dict['points'] = np.concatenate(
(np.zeros((batch_dict['points'].shape[0], 1)), batch_dict['points']), axis=1)
batch_dict['voxel_coords'] = np.concatenate(
(np.zeros((batch_dict['voxel_coords'].shape[0], 1)), batch_dict['voxel_coords']), axis=1)
load_data_to_gpu(batch_dict)
pred_dicts, _ = model(batch_dict)
det_boxes = pred_dicts[0]['pred_boxes'].cpu().detach().numpy()
# Load annotation from pickle file
gt_boxes = []
label_file = lidar_file.replace('bin', 'pkl')
try:
assert (test_scene_path / 'label' / label_file).exists()
except AssertionError:
continue
with open(test_scene_path / 'label' / label_file, 'rb') as f:
anno = pickle.load(f, encoding='iso-8859-1')
for obj in anno['obstacle_list']:
loc = np.array([obj['position']['x'], obj['position']['y'], obj['position']['z']])
dims = obj['size']
rotz = np.array([math.atan(obj['direction']['y'] / obj['direction']['x'])])
if loc[0] < point_cloud_range[0] or loc[0] > point_cloud_range[3] \
or loc[1] < point_cloud_range[1] or loc[1] > point_cloud_range[4]:
continue
gt_boxes.append(np.concatenate((loc, dims, rotz), axis=0))
gt_boxes = np.array(gt_boxes)
###########################Plot DET results###############################
PLOT_BOX = False
if PLOT_BOX:
points = batch_dict['points'][:, 1:4].cpu().detach().numpy()
bev_range = cfg.DATA_CONFIG.POINT_CLOUD_RANGE
# plot_gt_boxes(points, det_boxes, bev_range, name="mot_bench_%04d" % idx)
plot_gt_det_cmp(points, gt_boxes, det_boxes, bev_range, name="mot_bench_%04d" % frame_idx)
##########################################################################
# Evaluate current frame
for iou_idx in range(len(ious)):
for dist_range_idx in range(len(dist_ranges)):
tp, num_valid_det, num_valid_gt, dist_err = get_metrics(gt_boxes, det_boxes,
dist_ranges[dist_range_idx],
ious[iou_idx])
total_num_tp[iou_idx, dist_range_idx] += tp
total_num_valid_det[iou_idx, dist_range_idx] += num_valid_det
total_num_valid_gt[iou_idx, dist_range_idx] += num_valid_gt
total_dist_err[iou_idx, dist_range_idx] += dist_err
frame_idx += 1