def kitti_bbox2results(boxes_lidar, scores, labels, meta, class_names=None):
calib = meta['calib']
sample_id = meta['sample_idx']
image_shape = meta['img_shape'][: 2]
if scores is None \
or len(scores) == 0 \
or boxes_lidar is None \
or len(boxes_lidar) == 0:
return kitti.empty_result_anno()
hehe = kitti.get_start_result_anno()
hehe.update({'image_idx': []})
boxes_lidar[:, -1] = limit_period(
boxes_lidar[:, -1], offset=0.5, period=np.pi * 2,
)
boxes_cam = np.zeros_like(boxes_lidar)
boxes_cam[:, :3] = project_velo_to_rect(boxes_lidar[:, :3], calib)
boxes_cam[:, 3:] = boxes_lidar[:, [4, 5, 3, 6]]
corners_cam = center_to_corner_box3d(boxes_cam, origin=[0.5, 1.0, 0.5], axis=1)
corners_rgb = project_rect_to_image(corners_cam, calib)
minxy = np.min(corners_rgb, axis=1)
maxxy = np.max(corners_rgb, axis=1)
box2d_rgb = np.concatenate([minxy, maxxy], axis=1)
alphas = -np.arctan2(-boxes_lidar[:, 1], boxes_lidar[:, 0]) + boxes_lidar[:, 6]
for i, (lb, score, box3d, box2d, alpha) in enumerate(zip(labels, scores, boxes_cam, box2d_rgb, alphas)):
if box2d[0] > image_shape[1] or box2d[1] > image_shape[0]:
continue
if box2d[2] < 0 or box2d[3] < 0:
continue
box2d[2:] = np.minimum(box2d[2:], image_shape[::-1])
box2d[:2] = np.maximum(box2d[:2], [0, 0])
hehe["name"].append(class_names[lb])
hehe["truncated"].append(0.0)
hehe["occluded"].append(0)
hehe["alpha"].append(alpha)
hehe["bbox"].append(box2d)
hehe["dimensions"].append(box3d[[3, 4, 5]])
hehe["location"].append(box3d[:3])
hehe["rotation_y"].append(box3d[6])
hehe["score"].append(score)
hehe['image_idx'].append(int(sample_id))
try:
hehe = {n: np.stack(v) for n, v in hehe.items()}
except:
return kitti.empty_result_anno()
return hehe
def single_test(model, data_loader, saveto=None, class_names=['Car']):
template = '{} ' + ' '.join(['{:.4f}' for _ in range(15)]) + '\n'
if saveto is not None:
mmcv.mkdir_or_exist(saveto)
model.eval()
annos = []
prog_bar = mmcv.ProgressBar(len(data_loader.dataset))
for i, data in enumerate(data_loader):
with torch.no_grad():
results = model(return_loss=False, **data)
image_shape = (375,1242)
for re in results:
img_idx = re['image_idx']
if re['bbox'] is not None:
box2d = re['bbox']
box3d = re['box3d_camera']
labels = re['label_preds']
scores = re['scores']
alphas = re['alphas']
anno = kitti.get_start_result_anno()
num_example = 0
for bbox2d, bbox3d, label, score, alpha in zip(box2d, box3d, labels, scores, alphas):
if bbox2d[0] > image_shape[1] or bbox2d[1] > image_shape[0]:
continue
if bbox2d[2] < 0 or bbox2d[3] < 0:
continue
bbox2d[2:] = np.minimum(bbox2d[2:], image_shape[::-1])
bbox2d[:2] = np.maximum(bbox2d[:2], [0, 0])
anno["name"].append(class_names[int(label)])
anno["truncated"].append(0.0)
anno["occluded"].append(0)
# anno["alpha"].append(-10)
anno["alpha"].append(alpha)
anno["bbox"].append(bbox2d)
# anno["dimensions"].append(np.array([-1,-1,-1]))
anno["dimensions"].append(bbox3d[[3, 4, 5]])
# anno["location"].append(np.array([-1000,-1000,-1000]))
anno["location"].append(bbox3d[:3])
# anno["rotation_y"].append(-10)
anno["rotation_y"].append(bbox3d[6])
anno["score"].append(score)
num_example += 1
if num_example != 0:
if saveto is not None:
of_path = os.path.join(saveto, '%06d.txt' % img_idx)
with open(of_path, 'w+') as f:
for name, bbox, dim, loc, ry, score, alpha in zip(anno['name'], anno["bbox"], \
anno["dimensions"], anno["location"], anno["rotation_y"], anno["score"],anno["alpha"]):
line = template.format(name, 0, 0, alpha, *bbox, *dim[[1,2,0]], *loc, ry, score)
f.write(line)
anno = {n: np.stack(v) for n, v in anno.items()}
annos.append(anno)
else:
if saveto is not None:
of_path = os.path.join(saveto, '%06d.txt' % img_idx)
f = open(of_path, 'w+')
f.close()
annos.append(kitti.empty_result_anno())
else:
if saveto is not None:
of_path = os.path.join(saveto, '%06d.txt' % img_idx)
f = open(of_path, 'w+')
f.close()
annos.append(kitti.empty_result_anno())
num_example = annos[-1]["name"].shape[0]
annos[-1]["image_idx"] = np.array(
[img_idx] * num_example, dtype=np.int64)
batch_size = len(results)
for _ in range(batch_size):
prog_bar.update()
return annos
def after_train_epoch(self, runner):
if not self.every_n_epochs(runner, self.interval):
return
if runner.rank == 0:
runner.model.eval()
prog_bar = mmcv.ProgressBar(len(self.dataset))
class_names = get_classes('kitti')
results = []
for i, data in enumerate(self.dataloader):
# compute output
with torch.no_grad():
result = runner.model(return_loss=False, **data)
image_shape = (600, 1987)
for re in result:
img_idx = re['image_idx']
if re['bbox'] is not None:
box2d = re['bbox']
box3d = re['box3d_camera']
labels = re['label_preds']
scores = re['scores']
alphas = re['alphas']
anno = kitti.get_start_result_anno()
num_example = 0
for bbox2d, bbox3d, label, score, alpha in zip(
box2d, box3d, labels, scores, alphas):
if bbox2d[0] > image_shape[1] or bbox2d[
1] > image_shape[0]:
continue
if bbox2d[2] < 0 or bbox2d[3] < 0:
continue
bbox2d[2:] = np.minimum(bbox2d[2:],
image_shape[::-1])
bbox2d[:2] = np.maximum(bbox2d[:2], [0, 0])
anno["name"].append(class_names[label])
anno["truncated"].append(0.0)
anno["occluded"].append(0)
#anno["alpha"].append(-10)
anno["alpha"].append(alpha)
anno["bbox"].append(bbox2d)
#anno["dimensions"].append(np.array([-1,-1,-1]))
anno["dimensions"].append(bbox3d[[3, 4, 5]])
#anno["location"].append(np.array([-1000,-1000,-1000]))
anno["location"].append(bbox3d[:3])
#anno["rotation_y"].append(-10)
anno["rotation_y"].append(bbox3d[6])
anno["score"].append(score)
num_example += 1
if num_example != 0:
anno = {n: np.stack(v) for n, v in anno.items()}
results.append(anno)
else:
results.append(kitti.empty_result_anno())
else:
results.append(kitti.empty_result_anno())
num_example = results[-1]["name"].shape[0]
results[-1]["image_idx"] = np.array([img_idx] *
num_example,
dtype=np.int64)
batch_size = len(data['sample_idx'])
for _ in range(batch_size):
prog_bar.update()
self._barrier(runner.rank, runner.world_size)
self.evaluate(runner, results)
else:
self._barrier(runner.rank, runner.world_size)