def match_anchor_to_bbox(ground_truth, anchors, device, iou_threshold=0.5):
"""Assign ground-truth bounding boxes to anchor boxes similar to them."""
num_anchors, num_gt_boxes = anchors.shape[0], ground_truth.shape[0]
# Element `x_ij` in the `i^th` row and `j^th` column is the IoU
# of the anchor box `anc_i` to the ground-truth bounding box `box_j`
jaccard = box_iou(anchors, ground_truth)
# Initialize the tensor to hold assigned ground truth bbox for each anchor
anchors_bbox_map = np.full((num_anchors, ),
fill_value=-1,
dtype=np.int32,
ctx=device)
# Assign ground truth bounding box according to the threshold
max_ious, indices = np.max(jaccard, axis=1), np.argmax(jaccard, axis=1)
anc_i = np.nonzero(max_ious >= iou_threshold)[0]
box_j = indices[max_ious >= iou_threshold]
anchors_bbox_map[anc_i] = box_j
# Find the largest iou for each bbox
col_discard = np.full((num_anchors, ), -1)
row_discard = np.full((num_gt_boxes, ), -1)
for _ in range(num_gt_boxes):
max_idx = np.argmax(jaccard)
box_idx = (max_idx % num_gt_boxes).astype('int32')
anc_idx = (max_idx / num_gt_boxes).astype('int32')
anchors_bbox_map[anc_idx] = box_idx
jaccard[:, box_idx] = col_discard
jaccard[anc_idx, :] = row_discard
return anchors_bbox_map
def multibox_target(anchors, labels):
batch_size, anchors = labels.shape[0], anchors.squeeze(0)
batch_offset, batch_mask, batch_class_labels = [], [], []
device, num_anchors = anchors.ctx, anchors.shape[0]
print(labels.shape)
print(batch_size)
for i in range(batch_size):
label = labels[i, :, :]
anchors_bbox_map = match_anchor_to_bbox(label[:, 1:], anchors,
device) # [-1, 0, 1, -1 , 1]
bbox_mask = np.tile((np.expand_dims((anchors_bbox_map >= 0), axis=-1)),
(1, 4)).astype('int32')
# Initialize class_labels and assigned bbox coordinates with zeros
class_labels = np.zeros(num_anchors, dtype=np.int32, ctx=device)
assigned_bb = np.zeros((num_anchors, 4), dtype=np.float32, ctx=device)
# Assign class labels to the anchor boxes using matched gt bbox labels
# If no gt bbox is assigned to an anchor box, then let the
# class_labels and assigned_bb remain zero, i.e the background class
indices_true = np.nonzero(anchors_bbox_map >= 0)[0] #[1,2,4]
print(indices_true)
bb_idx = anchors_bbox_map[indices_true] #[0, 1, 1]
class_labels[indices_true] = label[bb_idx, 0].astype(
'int32') + 1 # Get category
assigned_bb[indices_true] = label[bb_idx, 1:] # Get ground-truth
# offset transformations
offset = offset_boxes(anchors, assigned_bb) * bbox_mask
batch_offset.append(offset.reshape(-1))
batch_mask.append(bbox_mask.reshape(-1))
batch_class_labels.append(class_labels)
bbox_offset = np.stack(batch_offset)
bbox_mask = np.stack(batch_mask)
class_labels = np.stack(batch_class_labels)
return (bbox_offset, bbox_mask, class_labels)
def nms(boxes, scores, iou_threshold):
# sorting scores by the descending order and return their indices
B = scores.argsort()[::-1]
keep = [] # boxes indices that will be kept
while B.size > 0:
i = B[0] # Get max confidence
keep.append(i)
if B.size == 1: break
iou = box_iou(boxes[i, :].reshape(-1, 4),
boxes[B[1:], :].reshape(-1, 4)).reshape(-1)
inds = np.nonzero(iou <= iou_threshold)[0]
B = B[inds + 1]
return np.array(keep, dtype=np.int32, ctx=boxes.ctx)
def dnp_func(a, b=None, split_inputs=(), ret_type=list):
"""
Dummy Doc:
dnp_func is using the same np.xxx operators
"""
ret_lst = []
# unsupported indexing case
ret_lst.append(a[:, a[1, :] > 0])
# unsupported operator
ret_lst.append(np.nonzero(b))
# unsupported operator case
ret_lst.append(tuple(np.split(split_inputs[0], split_inputs[1])))
return ret_type(ret_lst)