def prep_metrics(ap_data, ids_p, classes_p, boxes_p, masks_p, gt, gt_masks,
height, width, iou_thres):
gt_boxes = gt[:, :4]
gt_boxes[:, [0, 2]] *= width
gt_boxes[:, [1, 3]] *= height
gt_classes = gt[:, 4].int().tolist()
gt_masks = gt_masks.reshape(-1, height * width)
masks_p = masks_p.reshape(-1, height * width)
mask_iou_cache = mask_iou(masks_p, gt_masks)
bbox_iou_cache = box_iou(boxes_p.float(), gt_boxes.float()).cpu()
for _class in set(ids_p + gt_classes):
num_gt_per_class = gt_classes.count(_class)
for iouIdx in range(len(iou_thres)):
iou_threshold = iou_thres[iouIdx]
for iou_type, iou_func in zip(['box', 'mask'],
[bbox_iou_cache, mask_iou_cache]):
gt_used = [False] * len(gt_classes)
ap_obj = ap_data[iou_type][iouIdx][_class]
ap_obj.add_gt_positives(num_gt_per_class)
for i, pred_class in enumerate(ids_p):
if pred_class != _class:
continue
max_iou_found = iou_threshold
max_match_idx = -1
for j, gt_class in enumerate(gt_classes):
if gt_used[j] or gt_class != _class:
continue
iou = iou_func[i, j].item()
if iou > max_iou_found:
max_iou_found = iou
max_match_idx = j
if max_match_idx >= 0:
gt_used[max_match_idx] = True
ap_obj.push(classes_p[i], True)
else:
ap_obj.push(classes_p[i], False)
def prep_metrics(ap_data, nms_outs, gt, gt_masks, h, w, num_crowd, image_id, make_json, cocoapi):
""" Returns a list of APs for this image, with each element being for a class """
with timer.env('After NMS'):
class_ids, classes, boxes, masks = after_nms(nms_outs, h, w)
if class_ids.size(0) == 0:
return
class_ids = list(class_ids.cpu().numpy().astype(int))
classes = list(classes.cpu().numpy().astype(float))
masks = masks.view(-1, h * w).cuda() if cuda else masks.view(-1, h * w)
boxes = boxes.cuda() if cuda else boxes
if cocoapi:
with timer.env('Output json'):
boxes = boxes.cpu().numpy()
masks = masks.view(-1, h, w).cpu().numpy()
for i in range(masks.shape[0]):
# Make sure that the bounding box actually makes sense and a mask was produced
if (boxes[i, 3] - boxes[i, 1]) * (boxes[i, 2] - boxes[i, 0]) > 0:
make_json.add_bbox(image_id, class_ids[i], boxes[i, :], classes[i])
make_json.add_mask(image_id, class_ids[i], masks[i, :, :], classes[i])
return
with timer.env('Prepare gt'):
gt_boxes = torch.Tensor(gt[:, :4])
gt_boxes[:, [0, 2]] *= w
gt_boxes[:, [1, 3]] *= h
gt_classes = list(gt[:, 4].astype(int))
gt_masks = torch.Tensor(gt_masks).view(-1, h * w)
if num_crowd > 0:
split = lambda x: (x[-num_crowd:], x[:-num_crowd])
crowd_boxes, gt_boxes = split(gt_boxes)
crowd_masks, gt_masks = split(gt_masks)
crowd_classes, gt_classes = split(gt_classes)
with timer.env('Eval Setup'):
num_pred = len(class_ids)
num_gt = len(gt_classes)
mask_iou_cache = mask_iou(masks, gt_masks)
bbox_iou_cache = bbox_iou(boxes.float(), gt_boxes.float())
if num_crowd > 0:
crowd_mask_iou_cache = mask_iou(masks, crowd_masks, iscrowd=True)
crowd_bbox_iou_cache = bbox_iou(boxes.float(), crowd_boxes.float(), iscrowd=True)
else:
crowd_mask_iou_cache = None
crowd_bbox_iou_cache = None
iou_types = [('box', lambda i, j: bbox_iou_cache[i, j].item(), lambda i, j: crowd_bbox_iou_cache[i, j].item()),
('mask', lambda i, j: mask_iou_cache[i, j].item(), lambda i, j: crowd_mask_iou_cache[i, j].item())]
timer.start('Main loop')
for _class in set(class_ids + gt_classes):
num_gt_for_class = sum([1 for x in gt_classes if x == _class])
for iouIdx in range(len(iou_thresholds)):
iou_threshold = iou_thresholds[iouIdx]
for iou_type, iou_func, crowd_func in iou_types:
gt_used = [False] * len(gt_classes)
ap_obj = ap_data[iou_type][iouIdx][_class]
ap_obj.add_gt_positives(num_gt_for_class)
for i in range(num_pred):
if class_ids[i] != _class:
continue
max_iou_found = iou_threshold
max_match_idx = -1
for j in range(num_gt):
if gt_used[j] or gt_classes[j] != _class:
continue
iou = iou_func(i, j)
if iou > max_iou_found:
max_iou_found = iou
max_match_idx = j
if max_match_idx >= 0:
gt_used[max_match_idx] = True
ap_obj.push(classes[i], True)
else:
# If the detection matches a crowd, we can just ignore it
matched_crowd = False
if num_crowd > 0:
for j in range(len(crowd_classes)):
if crowd_classes[j] != _class:
continue
iou = crowd_func(i, j)
if iou > iou_threshold:
matched_crowd = True
break
# All this crowd code so that we can make sure that our eval code gives the
# same result as COCOEval. There aren't even that many crowd annotations to
# begin with, but accuracy is of the utmost importance.
if not matched_crowd:
ap_obj.push(classes[i], False)
timer.stop('Main loop')
def _mask_iou(mask1, mask2, iscrowd=False):
ret = mask_iou(mask1, mask2, iscrowd)
return ret.cpu()
def prep_metrics(ap_data, classes_p, confs_p, boxes_p, masks_p, gt, gt_masks,
num_crowd, height, width):
gt_boxes = gt[:, :4]
gt_boxes[:, [0, 2]] *= width
gt_boxes[:, [1, 3]] *= height
gt_classes = gt[:, 4].int().tolist()
gt_masks = gt_masks.reshape(-1, height * width)
masks_p = masks_p.reshape(-1, height * width)
if num_crowd > 0:
split = lambda x: (x[-num_crowd:], x[:-num_crowd])
crowd_boxes, gt_boxes = split(gt_boxes)
crowd_masks, gt_masks = split(gt_masks)
crowd_classes, gt_classes = split(gt_classes)
mask_iou_cache = mask_iou(masks_p, gt_masks)
bbox_iou_cache = bbox_iou(boxes_p.float(), gt_boxes.float())
if num_crowd > 0:
crowd_mask_iou_cache = mask_iou(masks_p, crowd_masks, iscrowd=True)
crowd_bbox_iou_cache = bbox_iou(boxes_p.float(),
crowd_boxes.float(),
iscrowd=True)
else:
crowd_mask_iou_cache = None
crowd_bbox_iou_cache = None
iou_types = [('box', lambda i, j: bbox_iou_cache[i, j].item(),
lambda i, j: crowd_bbox_iou_cache[i, j].item()),
('mask', lambda i, j: mask_iou_cache[i, j].item(),
lambda i, j: crowd_mask_iou_cache[i, j].item())]
for _class in set(classes_p + gt_classes):
num_gt_per_class = gt_classes.count(_class)
for iouIdx in range(len(iou_thresholds)):
iou_threshold = iou_thresholds[iouIdx]
for iou_type, iou_func, crowd_func in iou_types:
gt_used = [False] * len(gt_classes)
ap_obj = ap_data[iou_type][iouIdx][_class]
ap_obj.add_gt_positives(num_gt_per_class)
for i, pred_class in enumerate(classes_p):
if pred_class != _class:
continue
max_iou_found = iou_threshold
max_match_idx = -1
for j, gt_class in enumerate(gt_classes):
if gt_used[j] or gt_class != _class:
continue
iou = iou_func(i, j)
if iou > max_iou_found:
max_iou_found = iou
max_match_idx = j
if max_match_idx >= 0:
gt_used[max_match_idx] = True
ap_obj.push(confs_p[i], True)
else:
# If the detection matches a crowd, we can just ignore it
matched_crowd = False
if num_crowd > 0:
for j in range(len(crowd_classes)):
if crowd_classes[j] != _class:
continue
iou = crowd_func(i, j)
if iou > iou_threshold:
matched_crowd = True
break
# All this crowd code so that we can make sure that our eval code gives the
# same result as COCOEval. There aren't even that many crowd annotations to
# begin with, but accuracy is of the utmost importance.
if not matched_crowd:
ap_obj.push(confs_p[i], False)