def fused_compute_statistics(
overlaps,
pr,
gt_nums,
dt_nums,
dc_nums,
gt_datas,
dt_datas,
dontcares,
ignored_gts,
ignored_dets,
metric,
min_overlap,
thresholds,
compute_aos=False,
):
gt_num = 0
dt_num = 0
dc_num = 0
for i in range(gt_nums.shape[0]):
for t, thresh in enumerate(thresholds):
overlap = overlaps[
dt_num : dt_num + dt_nums[i], gt_num : gt_num + gt_nums[i]
]
gt_data = gt_datas[gt_num : gt_num + gt_nums[i]]
dt_data = dt_datas[dt_num : dt_num + dt_nums[i]]
ignored_gt = ignored_gts[gt_num : gt_num + gt_nums[i]]
ignored_det = ignored_dets[dt_num : dt_num + dt_nums[i]]
dontcare = dontcares[dc_num : dc_num + dc_nums[i]]
tp, fp, fn, similarity, _ = compute_statistics_jit(
overlap,
gt_data,
dt_data,
ignored_gt,
ignored_det,
dontcare,
metric,
min_overlap=min_overlap,
thresh=thresh,
compute_fp=True,
compute_aos=compute_aos,
)
pr[t, 0] += tp
pr[t, 1] += fp
pr[t, 2] += fn
if similarity != -1:
pr[t, 3] += similarity
gt_num += gt_nums[i]
dt_num += dt_nums[i]
dc_num += dc_nums[i]
def eval_class_v3(
gt_annos,
dt_annos,
current_classes,
difficultys,
metric,
min_overlaps,
compute_aos=False,
z_axis=1,
z_center=1.0,
num_parts=50,
):
"""Kitti eval. support 2d/bev/3d/aos eval. support 0.5:0.05:0.95 coco AP.
Args:
gt_annos: dict, must from get_label_annos() in kitti_common.py
dt_annos: dict, must from get_label_annos() in kitti_common.py
current_class: int, 0: car, 1: pedestrian, 2: cyclist
difficulty: int. eval difficulty, 0: easy, 1: normal, 2: hard
metric: eval type. 0: bbox, 1: bev, 2: 3d
min_overlap: float, min overlap. official:
[[0.7, 0.5, 0.5], [0.7, 0.5, 0.5], [0.7, 0.5, 0.5]]
format: [metric, class]. choose one from matrix above.
num_parts: int. a parameter for fast calculate algorithm
Returns:
dict of recall, precision and aos
"""
assert len(gt_annos) == len(dt_annos)
num_examples = len(gt_annos)
split_parts = get_split_parts(num_examples, num_parts)
split_parts = [i for i in split_parts if i != 0]
rets = calculate_iou_partly(dt_annos,
gt_annos,
metric,
num_parts,
z_axis=z_axis,
z_center=z_center)
overlaps, parted_overlaps, total_dt_num, total_gt_num = rets
N_SAMPLE_PTS = 41
num_minoverlap = len(min_overlaps)
num_class = len(current_classes)
num_difficulty = len(difficultys)
precision = np.zeros(
[num_class, num_difficulty, num_minoverlap, N_SAMPLE_PTS])
recall = np.zeros(
[num_class, num_difficulty, num_minoverlap, N_SAMPLE_PTS])
aos = np.zeros([num_class, num_difficulty, num_minoverlap, N_SAMPLE_PTS])
all_thresholds = np.zeros(
[num_class, num_difficulty, num_minoverlap, N_SAMPLE_PTS])
for m, current_class in enumerate(current_classes):
for l, difficulty in enumerate(difficultys):
rets = prepare_data(
gt_annos,
dt_annos,
current_class,
difficulty=difficulty,
clean_data=clean_data,
)
(
gt_datas_list,
dt_datas_list,
ignored_gts,
ignored_dets,
dontcares,
total_dc_num,
total_num_valid_gt,
) = rets
for k, min_overlap in enumerate(min_overlaps[:, metric, m]):
thresholdss = []
for i in range(len(gt_annos)):
rets = compute_statistics_jit(
overlaps[i],
gt_datas_list[i],
dt_datas_list[i],
ignored_gts[i],
ignored_dets[i],
dontcares[i],
metric,
min_overlap=min_overlap,
thresh=0.0,
compute_fp=False,
)
tp, fp, fn, similarity, thresholds = rets
thresholdss += thresholds.tolist()
thresholdss = np.array(thresholdss)
thresholds = get_thresholds(thresholdss, total_num_valid_gt)
thresholds = np.array(thresholds)
# print(thresholds)
all_thresholds[m, l, k, :len(thresholds)] = thresholds
pr = np.zeros([len(thresholds), 4])
idx = 0
for j, num_part in enumerate(split_parts):
gt_datas_part = np.concatenate(
gt_datas_list[idx:idx + num_part], 0)
dt_datas_part = np.concatenate(
dt_datas_list[idx:idx + num_part], 0)
dc_datas_part = np.concatenate(
dontcares[idx:idx + num_part], 0)
ignored_dets_part = np.concatenate(
ignored_dets[idx:idx + num_part], 0)
ignored_gts_part = np.concatenate(
ignored_gts[idx:idx + num_part], 0)
fused_compute_statistics(
parted_overlaps[j],
pr,
total_gt_num[idx:idx + num_part],
total_dt_num[idx:idx + num_part],
total_dc_num[idx:idx + num_part],
gt_datas_part,
dt_datas_part,
dc_datas_part,
ignored_gts_part,
ignored_dets_part,
metric,
min_overlap=min_overlap,
thresholds=thresholds,
compute_aos=compute_aos,
)
idx += num_part
for i in range(len(thresholds)):
# recall[m, l, k, i] = pr[i, 0] / (pr[i, 0] + pr[i, 2])
precision[m, l, k, i] = pr[i, 0] / (pr[i, 0] + pr[i, 1])
if compute_aos:
aos[m, l, k, i] = pr[i, 3] / (pr[i, 0] + pr[i, 1])
for i in range(len(thresholds)):
precision[m, l, k, i] = np.max(precision[m, l, k, i:],
axis=-1)
if compute_aos:
aos[m, l, k, i] = np.max(aos[m, l, k, i:], axis=-1)
# use interp to calculate recall
"""
current_recalls = np.linspace(0, 1, 41)
prec_unique, inds = np.unique(precision[m, l, k], return_index=True)
current_recalls = current_recalls[inds]
f = interp1d(prec_unique, current_recalls)
precs_for_recall = np.linspace(0, 1, 41)
max_prec = np.max(precision[m, l, k])
valid_prec = precs_for_recall < max_prec
num_valid_prec = valid_prec.sum()
recall[m, l, k, :num_valid_prec] = f(precs_for_recall[valid_prec])
"""
ret_dict = {
"recall":
recall, # [num_class, num_difficulty, num_minoverlap, N_SAMPLE_PTS]
"precision": precision,
"orientation": aos,
"thresholds": all_thresholds,
"min_overlaps": min_overlaps,
}
return ret_dict