def display_differences(image, gt_box, gt_class_id, gt_mask, pred_box, pred_class_id, pred_score, pred_mask,
class_names, title="", ax=None, show_mask=True, show_box=True, iou_threshold=0.5,
score_threshold=0.5):
"""
Отобразите эталоннык и предсказательные объекты на одном
и том же изображении.
"""
# Сопоставить предсказанное к эталонному
gt_match, pred_match, overlaps = utils.compute_matches(
gt_box, gt_class_id, gt_mask,
pred_box, pred_class_id, pred_score, pred_mask,
iou_threshold=iou_threshold, score_threshold=score_threshold
)
# Эталонное = green. Предсказанные = red
colors = [(0, 1, 0, .8)] * len(gt_match) + [(1, 0, 0, 1)] * len(pred_match)
# Конкатенация GT и прогнозы
class_ids = np.concatenate([gt_class_id, pred_class_id])
scores = np.concatenate([np.zeros([len(gt_match)]), pred_score])
boxes = np.concatenate([gt_box, pred_box])
masks = np.concatenate([gt_mask, pred_mask], axis=-1)
# Подписи на экземпляр показывают score/IoU
captions = ["" for m in gt_match] + ["{:.2f} / {:.2f}".format(
pred_score[i],
(overlaps[i, int(pred_match[i])]
if pred_match[i] > -1 else overlaps[i].max()))
for i in range(len(pred_match))]
# Установить заголовок, если не указан
title = title or "Ground Truth and Detections\n GT=green, pred=red, captions: score/IoU"
# Отобразить
display_instances(image, boxes, masks, class_ids, class_names, scores, ax=ax, show_bbox=show_box,
show_mask=show_mask, colors=colors, captions=captions, title=title)
def display_differences(image,
gt_box,
gt_class_id,
gt_mask,
pred_box,
pred_class_id,
pred_score,
pred_mask,
class_names,
title="",
ax=None,
show_mask=True,
show_box=True,
iou_threshold=0.5,
score_threshold=0.5):
"""Display ground truth and prediction instances on the same image."""
# Match predictions to ground truth
gt_match, pred_match, overlaps = utils.compute_matches(
gt_box,
gt_class_id,
gt_mask,
pred_box,
pred_class_id,
pred_score,
pred_mask,
iou_threshold=iou_threshold,
score_threshold=score_threshold)
# Ground truth = green. Predictions = red
colors = [(0, 1, 0, .8)] * len(gt_match)\
+ [(1, 0, 0, 1)] * len(pred_match)
# Concatenate GT and predictions
class_ids = np.concatenate([gt_class_id, pred_class_id])
scores = np.concatenate([np.zeros([len(gt_match)]), pred_score])
boxes = np.concatenate([gt_box, pred_box])
masks = np.concatenate([gt_mask, pred_mask], axis=-1)
# Captions per instance show score/IoU
captions = ["" for m in gt_match] + [
"{:.2f} / {:.2f}".format(pred_score[i],
(overlaps[i, int(pred_match[i])] if
pred_match[i] > -1 else overlaps[i].max()))
for i in range(len(pred_match))
]
# Set title if not provided
title = title or "Ground Truth and Detections\n GT=green, pred=red, captions: score/IoU"
# Display
display_instances(image,
boxes,
masks,
class_ids,
class_names,
scores,
ax=ax,
show_bbox=show_box,
show_mask=show_mask,
colors=colors,
captions=captions,
title=title)
