def forward(self, x, boxes):
"""
Arguments:
x (Tensor): the mask logits
boxes (list[BoxList]): bounding boxes that are used as
reference, one for ech image
Returns:
results (list[BoxList]): one BoxList for each image, containing
the extra field mask
"""
mask_prob = x.sigmoid()
# select masks coresponding to the predicted classes
num_masks = x.shape[0]
labels = [bbox.get_field("labels") for bbox in boxes]
labels = torch.cat(labels)
index = torch.arange(num_masks, device=labels.device)
mask_prob = mask_prob[index, labels][:, None]
boxes_per_image = [len(box) for box in boxes]
mask_prob = mask_prob.split(boxes_per_image, dim=0)
if self.masker:
mask_prob = self.masker(mask_prob, boxes)
results = []
for prob, box in zip(mask_prob, boxes):
bbox = BoxList(box.bbox, box.size, mode="xyxy")
for field in box.fields():
bbox.add_field(field, box.get_field(field))
bbox.add_field("mask", prob)
results.append(bbox)
return results
def __call__(self,
proposals,
source_score,
labels,
device,
return_targets=False):
gt_boxes = torch.zeros((0, 4), dtype=torch.float, device=device)
gt_classes = torch.zeros((0, 1), dtype=torch.long, device=device)
gt_scores = torch.zeros((0, 1), dtype=torch.float, device=device)
# not using the background class
_prob = source_score[:, 1:].clone()
_labels = labels[1:]
positive_classes = _labels.eq(1).nonzero(as_tuple=False)[:, 0]
for c in positive_classes:
cls_prob = _prob[:, c]
max_index = torch.argmax(cls_prob)
gt_boxes = torch.cat(
(gt_boxes, proposals.bbox[max_index].view(1, -1)), dim=0)
gt_classes = torch.cat((gt_classes, c.add(1).view(1, 1)), dim=0)
gt_scores = torch.cat((gt_scores, cls_prob[max_index].view(1, 1)),
dim=0)
_prob[max_index].fill_(0)
if return_targets == True:
gt_boxes = BoxList(gt_boxes, proposals.size, mode=proposals.mode)
gt_boxes.add_field('labels', gt_classes[:, 0].float())
# gt_boxes.add_field('difficult', bb)
return gt_boxes
if gt_boxes.shape[0] == 0:
num_rois = len(source_score)
pseudo_labels = torch.zeros(num_rois,
dtype=torch.long,
device=device)
loss_weights = torch.zeros(num_rois,
dtype=torch.float,
device=device)
else:
gt_boxes = BoxList(gt_boxes, proposals.size, mode=proposals.mode)
overlaps = boxlist_iou(proposals, gt_boxes)
max_overlaps, gt_assignment = overlaps.max(dim=1)
pseudo_labels = gt_classes[gt_assignment, 0]
loss_weights = gt_scores[gt_assignment, 0]
# Select background RoIs as those with <= FG_IOU_THRESHOLD
bg_inds = max_overlaps.le(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD).nonzero(
as_tuple=False)[:, 0]
pseudo_labels[bg_inds] = 0
# PCL_TRICK:
# ignore_thres = 0.1
# ignore_inds = max_overlaps.le(ignore_thres).nonzero(as_tuple=False)[:,0]
# loss_weights[ignore_inds] = 0
return pseudo_labels, loss_weights
def get_groundtruth(self, index):
img_id = self.ids[index]
anno = ET.parse(self._annopath % img_id).getroot()
anno = self._preprocess_annotation(anno)
height, width = anno["im_info"]
target = BoxList(anno["boxes"], (width, height), mode="xyxy")
target.add_field("labels", anno["labels"])
target.add_field("difficult", anno["difficult"])
return target
def forward_for_single_feature_map(self, anchors, objectness, box_regression):
"""
Arguments:
anchors: list[BoxList]
objectness: tensor of size N, A, H, W
box_regression: tensor of size N, A * 4, H, W
"""
device = objectness.device
N, A, H, W = objectness.shape
# put in the same format as anchors
objectness = permute_and_flatten(objectness, N, A, 1, H, W).view(N, -1)
objectness = objectness.sigmoid()
box_regression = permute_and_flatten(box_regression, N, A, 4, H, W)
num_anchors = A * H * W
pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
objectness, topk_idx = objectness.topk(pre_nms_top_n, dim=1, sorted=True)
batch_idx = torch.arange(N, device=device)[:, None]
box_regression = box_regression[batch_idx, topk_idx]
image_shapes = [box.size for box in anchors]
concat_anchors = torch.cat([a.bbox for a in anchors], dim=0)
concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx]
proposals = self.box_coder.decode(
box_regression.view(-1, 4), concat_anchors.view(-1, 4)
)
proposals = proposals.view(N, -1, 4)
result = []
for proposal, score, im_shape in zip(proposals, objectness, image_shapes):
boxlist = BoxList(proposal, im_shape, mode="xyxy")
boxlist.add_field("objectness", score)
boxlist = boxlist.clip_to_image(remove_empty=False)
boxlist = remove_small_boxes(boxlist, self.min_size)
boxlist = boxlist_nms(
boxlist,
self.nms_thresh,
max_proposals=self.post_nms_top_n,
score_field="objectness",
)
result.append(boxlist)
return result
def prepare_boxlist(self, boxes, scores, image_shape):
"""
Returns BoxList from `boxes` and adds probability scores information
as an extra field
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
boxes = boxes.reshape(-1, 4)
scores = scores.reshape(-1)
boxlist = BoxList(boxes, image_shape, mode="xyxy")
boxlist.add_field("scores", scores)
return boxlist
def select_over_all_levels(self, boxlists):
num_images = len(boxlists)
results = []
for i in range(num_images):
scores = boxlists[i].get_field("scores")
labels = boxlists[i].get_field("labels")
boxes = boxlists[i].bbox
boxlist = boxlists[i]
result = []
# skip the background
for j in range(1, self.num_classes):
inds = (labels == j).nonzero().view(-1)
scores_j = scores[inds]
boxes_j = boxes[inds, :].view(-1, 4)
boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy")
boxlist_for_class.add_field("scores", scores_j)
boxlist_for_class = boxlist_nms(boxlist_for_class,
self.nms_thresh,
score_field="scores")
num_labels = len(boxlist_for_class)
boxlist_for_class.add_field(
"labels",
torch.full((num_labels, ),
j,
dtype=torch.int64,
device=scores.device))
result.append(boxlist_for_class)
result = cat_boxlist(result)
number_of_detections = len(result)
# Limit to max_per_image detections **over all classes**
if number_of_detections > self.fpn_post_nms_top_n > 0:
cls_scores = result.get_field("scores")
image_thresh, _ = torch.kthvalue(
cls_scores.cpu(),
number_of_detections - self.fpn_post_nms_top_n + 1)
keep = cls_scores >= image_thresh.item()
keep = torch.nonzero(keep).squeeze(1)
result = result[keep]
results.append(result)
return results
def filter_results(self, boxlist, num_classes):
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
"""
# unwrap the boxlist to avoid additional overhead.
# if we had multi-class NMS, we could perform this directly on the boxlist
boxes = boxlist.bbox.reshape(-1, num_classes * 4)
scores = boxlist.get_field("scores").reshape(-1, num_classes)
device = scores.device
result = []
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
inds_all = scores > self.score_thresh
for j in range(1, num_classes):
inds = inds_all[:, j].nonzero(as_tuple=False).squeeze(1)
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4 : (j + 1) * 4]
boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy")
boxlist_for_class.add_field("scores", scores_j)
boxlist_for_class = boxlist_nms(
boxlist_for_class, self.nms
)
num_labels = len(boxlist_for_class)
boxlist_for_class.add_field(
"labels", torch.full((num_labels,), j, dtype=torch.int64, device=device)
)
result.append(boxlist_for_class)
result = cat_boxlist(result)
number_of_detections = len(result)
# Limit to max_per_image detections **over all classes**
if number_of_detections > self.detections_per_img > 0:
cls_scores = result.get_field("scores")
image_thresh, _ = torch.kthvalue(
cls_scores.cpu(), number_of_detections - self.detections_per_img + 1
)
keep = cls_scores >= image_thresh.item()
keep = torch.nonzero(keep, as_tuple=False).squeeze(1)
result = result[keep]
return result
def forward(self, x, boxes):
mask_prob = x
scores = None
if self.keypointer:
mask_prob, scores = self.keypointer(x, boxes)
assert len(boxes) == 1, "Only non-batched inference supported for now"
boxes_per_image = [box.bbox.size(0) for box in boxes]
mask_prob = mask_prob.split(boxes_per_image, dim=0)
scores = scores.split(boxes_per_image, dim=0)
results = []
for prob, box, score in zip(mask_prob, boxes, scores):
bbox = BoxList(box.bbox, box.size, mode="xyxy")
for field in box.fields():
bbox.add_field(field, box.get_field(field))
prob = PersonKeypoints(prob, box.size)
prob.add_field("logits", score)
bbox.add_field("keypoints", prob)
results.append(bbox)
return results
def forward_for_single_feature_map(self, anchors, box_cls, box_regression):
"""
Arguments:
anchors: list[BoxList]
box_cls: tensor of size N, A * C, H, W
box_regression: tensor of size N, A * 4, H, W
"""
device = box_cls.device
N, _, H, W = box_cls.shape
A = box_regression.size(1) // 4
C = box_cls.size(1) // A
# put in the same format as anchors
box_cls = permute_and_flatten(box_cls, N, A, C, H, W)
box_cls = box_cls.sigmoid()
box_regression = permute_and_flatten(box_regression, N, A, 4, H, W)
box_regression = box_regression.reshape(N, -1, 4)
num_anchors = A * H * W
candidate_inds = box_cls > self.pre_nms_thresh
pre_nms_top_n = candidate_inds.view(N, -1).sum(1)
pre_nms_top_n = pre_nms_top_n.clamp(max=self.pre_nms_top_n)
results = []
for per_box_cls, per_box_regression, per_pre_nms_top_n, \
per_candidate_inds, per_anchors in zip(
box_cls,
box_regression,
pre_nms_top_n,
candidate_inds,
anchors):
# Sort and select TopN
# TODO most of this can be made out of the loop for
# all images.
# TODO:Yang: Not easy to do. Because the numbers of detections are
# different in each image. Therefore, this part needs to be done
# per image.
per_box_cls = per_box_cls[per_candidate_inds]
per_box_cls, top_k_indices = \
per_box_cls.topk(per_pre_nms_top_n, sorted=False)
per_candidate_nonzeros = \
per_candidate_inds.nonzero()[top_k_indices, :]
per_box_loc = per_candidate_nonzeros[:, 0]
per_class = per_candidate_nonzeros[:, 1]
per_class += 1
detections = self.box_coder.decode(
per_box_regression[per_box_loc, :].view(-1, 4),
per_anchors.bbox[per_box_loc, :].view(-1, 4))
boxlist = BoxList(detections, per_anchors.size, mode="xyxy")
boxlist.add_field("labels", per_class)
boxlist.add_field("scores", per_box_cls)
boxlist = boxlist.clip_to_image(remove_empty=False)
boxlist = remove_small_boxes(boxlist, self.min_size)
results.append(boxlist)
return results
def __getitem__(self, idx):
img, anno = super(COCODataset, self).__getitem__(idx)
# filter crowd annotations
# TODO might be better to add an extra field
if "lvis_v0.5" not in self.ann_file:
anno = [obj for obj in anno if obj["iscrowd"] == 0]
if self.proposals is not None:
img_id = self.ids[idx]
id_field = 'indexes' if 'indexes' in self.proposals else 'ids' # compat fix
roi_idx = self.proposals[id_field].index(img_id)
rois = self.proposals['boxes'][roi_idx]
# remove duplicate, clip, remove small boxes, and take top k
keep = unique_boxes(rois)
rois = rois[keep, :]
# scores = scores[keep]
rois = BoxList(torch.tensor(rois), img.size, mode="xyxy")
rois = rois.clip_to_image(remove_empty=True)
rois = remove_small_boxes(boxlist=rois, min_size=2)
if self.top_k > 0:
rois = rois[[range(self.top_k)]]
# scores = scores[:self.top_k]
else:
rois = None
# support un-labled
if anno == [] and 'unlabeled' in self.ann_file:
boxes = torch.as_tensor([[0, 0, 0, 0]]).reshape(-1, 4)
target = BoxList(boxes, img.size, mode="xyxy")
classes = torch.tensor([0])
target.add_field("labels", classes)
if self._transforms is not None:
img, target, rois = self._transforms(img, target, rois)
target.bbox.fill_(0)
else:
boxes = [obj["bbox"] for obj in anno]
boxes = torch.as_tensor(boxes).reshape(-1,
4) # guard against no boxes
target = BoxList(boxes, img.size, mode="xywh").convert("xyxy")
classes = [obj["category_id"] for obj in anno]
classes = [
self.json_category_id_to_contiguous_id[c] for c in classes
]
classes = torch.tensor(classes)
target.add_field("labels", classes)
if anno and "segmentation" in anno[0]:
masks = [obj["segmentation"] for obj in anno]
masks = SegmentationMask(masks, img.size, mode='poly')
target.add_field("masks", masks)
if anno and "keypoints" in anno[0]:
keypoints = [obj["keypoints"] for obj in anno]
keypoints = PersonKeypoints(keypoints, img.size)
target.add_field("keypoints", keypoints)
if anno and 'point' in anno[0]:
click = [obj["point"] for obj in anno]
click = Click(click, img.size)
target.add_field("click", click)
if anno and 'scribble' in anno[0]:
scribble = [obj["scribble"] for obj in anno]
# xmin, ymin, xmax, ymax
scribble_box = []
for sc in scribble:
if len(sc[0]) == 0:
scribble_box.append([1, 2, 3, 4])
else:
scribble_box.append(
[min(sc[0]),
min(sc[1]),
max(sc[0]),
max(sc[1])])
scribble_box = torch.tensor(scribble_box)
scribble_box = torch.as_tensor(scribble_box).reshape(
-1, 4) # guard against no boxes
scribble_target = BoxList(scribble_box, img.size, mode="xyxy")
target.add_field("scribble", scribble_target)
if anno and 'use_as' in anno[0]:
tag_to_ind = {'tag': 0, 'point': 1, 'scribble': 2, 'box': 3}
use_as = [tag_to_ind[obj['use_as']] for obj in anno]
use_as = torch.tensor(use_as)
target.add_field("use_as", use_as)
target = target.clip_to_image(remove_empty=True)
if self._transforms is not None:
img, target, rois = self._transforms(img, target, rois)
return img, target, rois, idx
def im_detect_bbox_aug(model, images, device, rois=None):
# Collect detections computed under different transformations
boxlists_ts = []
for _ in range(len(images)):
boxlists_ts.append([])
def add_preds_t(boxlists_t):
for i, boxlist_t in enumerate(boxlists_t):
if len(boxlists_ts[i]) == 0:
# The first one is identity transform, no need to resize the boxlist
boxlists_ts[i].append(boxlist_t)
else:
# Resize the boxlist as the first one
boxlists_ts[i].append(boxlist_t.resize(boxlists_ts[i][0].size))
# Compute detections for the original image (identity transform)
boxlists_i = im_detect_bbox(model,
images,
cfg.INPUT.MIN_SIZE_TEST,
cfg.INPUT.MAX_SIZE_TEST,
device,
rois=rois)
add_preds_t(boxlists_i)
# Perform detection on the horizontally flipped image
if cfg.TEST.BBOX_AUG.H_FLIP:
boxlists_hf = im_detect_bbox_hflip(model,
images,
cfg.INPUT.MIN_SIZE_TEST,
cfg.INPUT.MAX_SIZE_TEST,
device,
rois=rois)
add_preds_t(boxlists_hf)
# Compute detections at different scales
for scale in cfg.TEST.BBOX_AUG.SCALES:
max_size = cfg.TEST.BBOX_AUG.MAX_SIZE
boxlists_scl = im_detect_bbox_scale(model,
images,
scale,
max_size,
device,
rois=rois)
add_preds_t(boxlists_scl)
if cfg.TEST.BBOX_AUG.SCALE_H_FLIP:
boxlists_scl_hf = im_detect_bbox_scale(model,
images,
scale,
max_size,
device,
hflip=True,
rois=rois)
add_preds_t(boxlists_scl_hf)
# Merge boxlists detected by different bbox aug params
boxlists = []
for i, boxlist_ts in enumerate(boxlists_ts):
if cfg.TEST.BBOX_AUG.HEUR == 'UNION':
bbox = torch.cat([boxlist_t.bbox for boxlist_t in boxlist_ts])
scores = torch.cat(
[boxlist_t.get_field('scores') for boxlist_t in boxlist_ts])
elif cfg.TEST.BBOX_AUG.HEUR == 'AVG':
bbox = torch.mean(torch.stack(
[boxlist_t.bbox for boxlist_t in boxlist_ts]),
dim=0)
scores = torch.mean(torch.stack(
[boxlist_t.get_field('scores') for boxlist_t in boxlist_ts]),
dim=0)
else:
raise ValueError('please use proper BBOX_AUG.HEUR ')
boxlist = BoxList(bbox, boxlist_ts[0].size, boxlist_ts[0].mode)
boxlist.add_field('scores', scores)
boxlists.append(boxlist)
# Apply NMS and limit the final detections
results = []
post_processor = make_roi_box_post_processor(cfg)
for boxlist in boxlists:
results.append(
post_processor.filter_results(boxlist,
cfg.MODEL.ROI_BOX_HEAD.NUM_CLASSES))
return results
