def encode_label(image, gt_boxes):
target_scores = np.zeros(shape=[45, 60, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[45, 60, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(
shape=[45, 60, 9]) # negative_samples: -1, positive_samples: 1
for i in range(45): # y: height
for j in range(60): # x: width
for k in range(9):
center_x = j * grid_width + grid_width * 0.5
center_y = i * grid_height + grid_height * 0.5
xmin = center_x - wandhG[k][0] * 0.5
ymin = center_y - wandhG[k][1] * 0.5
xmax = center_x + wandhG[k][0] * 0.5
ymax = center_y + wandhG[k][1] * 0.5
# print(xmin, ymin, xmax, ymax)
# ignore cross-boundary anchors
if (xmin > -5) & (ymin > -5) & (xmax < (image_width + 5)) & (
ymax < (image_height + 5)):
anchor_boxes = np.array([xmin, ymin, xmax, ymax])
anchor_boxes = np.expand_dims(anchor_boxes, axis=0)
# compute iou between this anchor and all ground-truth boxes in image.
ious = compute_iou(anchor_boxes, gt_boxes)
positive_masks = ious > pos_thresh
negative_masks = ious < neg_thresh
if np.any(positive_masks):
plot_boxes_on_image(image, anchor_boxes, thickness=1)
print("=> encode: %d, %d, %d" % (i, j, k))
cv2.circle(image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[255, 0, 0],
thickness=4)
target_scores[i, j, k, 1] = 1.
target_masks[i, j,
k] = 1 # labeled as a positive sample
# find out which ground-truth box matches this anchor
max_iou_idx = np.argmax(ious)
selected_gt_boxes = gt_boxes[max_iou_idx]
target_bboxes[i, j, k] = compute_regression(
selected_gt_boxes, anchor_boxes[0])
if np.all(negative_masks):
target_scores[i, j, k, 0] = 1.
target_masks[i, j,
k] = -1 # labeled as a negative sample
cv2.circle(image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[0, 0, 0],
thickness=4)
Image.fromarray(image).show()
return target_scores, target_bboxes, target_masks
def encode_label(gt_boxes):
target_scores = np.zeros(shape=[wnum, hnum, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[wnum, hnum, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(
shape=[wnum, hnum, 9]) # negative_samples: -1, positive_samples: 1
for i in range(wnum): # y: height
for j in range(hnum): # x: width
for k in range(9):
center_x = j * grid_width + grid_width * 0.5
center_y = i * grid_height + grid_height * 0.5
xmin = center_x - wandhG[k][0] * 0.5
ymin = center_y - wandhG[k][1] * 0.5
xmax = center_x + wandhG[k][0] * 0.5
ymax = center_y + wandhG[k][1] * 0.5
# print(xmin, ymin, xmax, ymax)
# ignore cross-boundary anchors
if (xmin > -5) & (ymin > -5) & (xmax < (image_width + 5)) & (
ymax < (image_height + 5)):
anchor_boxes = np.array([xmin, ymin, xmax, ymax])
anchor_boxes = np.expand_dims(anchor_boxes, axis=0)
# compute iou between this anchor and all ground-truth boxes in image.
ious = compute_iou(anchor_boxes, gt_boxes)
positive_masks = ious >= pos_thresh
negative_masks = ious <= neg_thresh
if np.any(positive_masks):
target_scores[i, j, k, 1] = 1.
target_masks[i, j,
k] = 1 # labeled as a positive sample
# find out which ground-truth box matches this anchor
max_iou_idx = np.argmax(ious)
selected_gt_boxes = gt_boxes[max_iou_idx]
target_bboxes[i, j, k] = compute_regression(
selected_gt_boxes, anchor_boxes[0])
if np.all(negative_masks):
target_scores[i, j, k, 0] = 1.
target_masks[i, j,
k] = -1 # labeled as a negative sample
return target_scores, target_bboxes, target_masks
thickness=1)
print("=> Encoding positive sample: %d, %d, %d" %
(i, j, k))
cv2.circle(encoded_image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[255, 0, 0],
thickness=4)
target_scores[i, j, k, 1] = 1.
target_masks[i, j, k] = 1 # labeled as a positive sample
# find out which ground-truth box matches this anchor
max_iou_idx = np.argmax(ious)
selected_gt_boxes = gt_boxes[max_iou_idx]
target_bboxes[i, j, k] = compute_regression(
selected_gt_boxes, anchor_boxes[0])
if np.all(negative_masks):
target_scores[i, j, k, 0] = 1.
target_masks[i, j, k] = -1 # labeled as a negative sample
cv2.circle(encoded_image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[0, 0, 0],
thickness=4)
Image.fromarray(encoded_image).show()
################################### DECODE OUTPUT #################################