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
"""
N, _, H, W = box_cls.shape
A = box_regression.shape[1] // 4
C = box_cls.shape[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)
num_anchors = A * H * W
candidate_inds = box_cls > self.pre_nms_thresh
pre_nms_top_n = candidate_inds.reshape(N, -1).sum(1)
pre_nms_top_n = pre_nms_top_n.clamp(max_v=self.pre_nms_top_n)
results = []
for i in range(box_cls.shape[0]):
per_box_cls, per_box_regression, per_pre_nms_top_n,per_candidate_inds, per_anchors = \
box_cls[i],box_regression[i],pre_nms_top_n[i],candidate_inds[i],anchors[i]
# 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]
if per_class.numel() > 0:
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
anno = [obj for obj in anno if obj["iscrowd"] == 0]
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)
masks = [obj["segmentation"] for obj in anno]
masks = SegmentationMask(masks, img.size, mode='poly')
target.add_field("masks", masks)
target = target.clip_to_image(remove_empty=True)
if self.transforms is not None:
img, target = self.transforms(img, target)
return img, target, idx
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 __getitem__(self, idx):
img, anno = super(COCODataset, self).__getitem__(idx)
if not self.is_train:
if self._transforms is not None:
img, target = self._transforms(img, None)
return img, target, idx
# filter crowd annotations
# TODO might be better to add an extra field
anno = [obj for obj in anno if obj["iscrowd"] == 0]
boxes = np.array([obj["bbox"] for obj in anno], dtype=np.float32)
boxes = boxes.reshape(-1, 4)
target = BoxList(boxes, img.size, mode="xywh", to_jittor=False)
target = target.convert("xyxy")
classes = [obj["category_id"] for obj in anno]
classes = [self.json_category_id_to_contiguous_id[c] for c in classes]
classes = np.array(classes, dtype=np.int32)
target.add_field("labels", classes)
if self.with_masks and anno and "segmentation" in anno[0]:
masks = [obj["segmentation"] for obj in anno]
masks = SegmentationMask(masks,
img.size,
mode='poly',
to_jittor=False)
target.add_field("masks", masks)
if self.with_masks and anno and "keypoints" in anno[0]:
keypoints = [obj["keypoints"] for obj in anno]
keypoints = PersonKeypoints(keypoints, img.size, to_jittor=False)
target.add_field("keypoints", keypoints)
target = target.clip_to_image(remove_empty=True)
if self._transforms is not None:
img, target = self._transforms(img, target)
img = img.astype(np.float32)
return img, target, idx
def forward_for_single_feature_map(self, locations, box_cls,
box_regression, centerness,
proposal_embed, proposal_margin,
image_sizes, level):
"""
Arguments:
anchors: list[BoxList]
box_cls: tensor of size N, A * C, H, W
box_regression: tensor of size N, A * 4, H, W
"""
N, C, H, W = box_cls.shape
# put in the same format as locations
box_cls = box_cls.view(N, C, H, W).transpose(0, 2, 3, 1)
box_cls = box_cls.reshape(N, -1, C).sigmoid()
box_regression = box_regression.view(N, 4, H, W).transpose(0, 2, 3, 1)
box_regression = box_regression.reshape(N, -1, 4)
centerness = centerness.view(N, 1, H, W).transpose(0, 2, 3, 1)
centerness = centerness.reshape(N, -1).sigmoid()
proposal_embed = proposal_embed.view(N, -1, H, W).transpose(0, 2, 3, 1)
proposal_embed = proposal_embed.reshape(N, H * W, -1)
proposal_margin = proposal_margin.view(N, 1, H,
W).transpose(0, 2, 3, 1)
proposal_margin = proposal_margin.reshape(N, -1)
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_v=self.pre_nms_top_n)
# multiply the classification scores with centerness scores
box_cls = box_cls * centerness[:, :].unsqueeze(2)
results = []
for i in range(N):
per_box_cls = box_cls[i]
per_candidate_inds = candidate_inds[i]
per_box_cls = per_box_cls[per_candidate_inds]
per_candidate_nonzeros = per_candidate_inds.nonzero()
per_box_loc = per_candidate_nonzeros[:, 0]
per_class = per_candidate_nonzeros[:, 1]
if per_candidate_nonzeros.numel() > 0:
per_class = per_candidate_nonzeros[:, 1] + 1
per_box_regression = box_regression[i]
per_box_regression = per_box_regression[per_box_loc]
per_locations = locations[per_box_loc]
per_proposal_embed = proposal_embed[i]
per_proposal_embed = per_proposal_embed[per_box_loc, :]
per_proposal_margin = proposal_margin[i][per_box_loc]
per_pre_nms_top_n = pre_nms_top_n[i]
if per_candidate_inds.sum().item() > per_pre_nms_top_n.item():
per_box_cls, top_k_indices = \
per_box_cls.topk(per_pre_nms_top_n.item(), sorted=False)
per_class = per_class[top_k_indices]
per_box_regression = per_box_regression[top_k_indices]
per_locations = per_locations[top_k_indices]
per_proposal_embed = per_proposal_embed[top_k_indices]
per_proposal_margin = per_proposal_margin[top_k_indices]
detections = jt.stack([
per_locations[:, 0] - per_box_regression[:, 0],
per_locations[:, 1] - per_box_regression[:, 1],
per_locations[:, 0] + per_box_regression[:, 2],
per_locations[:, 1] + per_box_regression[:, 3],
],
dim=1)
h, w = image_sizes[i]
boxlist = BoxList(detections, (int(w), int(h)), mode="xyxy")
boxlist.add_field("labels", per_class)
boxlist.add_field("scores", per_box_cls)
boxlist.add_field("proposal_embed", per_proposal_embed)
boxlist.add_field("proposal_margin", per_proposal_margin)
if boxlist.bbox.numel() > 0:
boxlist = boxlist.clip_to_image(remove_empty=False)
boxlist = remove_small_boxes(boxlist, self.min_size)
results.append(boxlist)
return results
def forward_for_single_feature_map(self, locations, box_cls,
box_regression, centerness,
image_sizes):
"""
Arguments:
anchors: list[BoxList]
box_cls: tensor of size N, A * C, H, W
box_regression: tensor of size N, A * 4, H, W
"""
N, C, H, W = box_cls.shape
# put in the same format as locations
box_cls = box_cls.view(N, C, H, W).permute(0, 2, 3, 1)
box_cls = box_cls.reshape(N, -1, self.num_classes - 1).sigmoid()
box_regression = box_regression.view(N, self.dense_points * 4, H,
W).permute(0, 2, 3, 1)
box_regression = box_regression.reshape(N, -1, 4)
centerness = centerness.view(N, self.dense_points, H,
W).permute(0, 2, 3, 1)
centerness = centerness.reshape(N, -1).sigmoid()
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_v=self.pre_nms_top_n)
# multiply the classification scores with centerness scores
box_cls = box_cls * centerness[:, :].unsqueeze(2)
results = []
#print('forward_for_single_feature_map start',N)
for i in range(N):
#print(i)
per_box_cls = box_cls[i]
per_candidate_inds = candidate_inds[i]
#print(per_candidate_inds.shape,per_box_cls.shape)
# if per_candidate_inds.sum().item()>0:
# per_box_cls = per_box_cls[per_candidate_inds]
# else:
# per_box_cls = jt.zeros((0,),dtype=per_box_cls.dtype)
#print(per_candidate_inds.shape,jt.sum(per_candidate_inds))
per_box_cls = per_box_cls[per_candidate_inds]
per_candidate_nonzeros = per_candidate_inds.nonzero()
per_box_loc = per_candidate_nonzeros[:, 0]
per_class = per_candidate_nonzeros[:, 1]
# if per_candidate_nonzeros.numel()>0:
# per_class = per_candidate_nonzeros[:, 1] + 1
per_class = per_candidate_nonzeros[:, 1] + 1
#print(per_candidate_nonzeros.shape)
per_box_regression = box_regression[i]
#print('GG',per_box_loc.numel(),per_box_loc.shape)
# if per_box_loc.numel()>0:
# per_box_regression = per_box_regression[per_box_loc]
# per_locations = locations[per_box_loc]
# else:
# shape = list(per_box_regression.shape)
# shape[0]=0
# per_box_regression = jt.zeros(shape,dtype=per_box_regression.dtype)
# shape = list(locations.shape)
# shape[0]=0
# per_locations = jt.zeros(shape,dtype=locations.dtype)
per_box_regression = per_box_regression[per_box_loc]
per_locations = locations[per_box_loc]
#print('??')
#print('per_box_cls1',per_box_cls.mean())
per_pre_nms_top_n = pre_nms_top_n[i]
#print('per_locations',jt.mean(per_locations))
#print('per_box_regressions',jt.mean(per_box_regression))
#print(per_pre_nms_top_n.item(),per_candidate_inds.sum().item())
if per_candidate_inds.sum().item() > per_pre_nms_top_n.item():
per_box_cls, top_k_indices = \
per_box_cls.topk(per_pre_nms_top_n.item(), sorted=False)
per_class = per_class[top_k_indices]
per_box_regression = per_box_regression[top_k_indices]
per_locations = per_locations[top_k_indices]
#print('per_box_cls',per_box_cls.mean())
#print('emmm',jt.mean(per_locations))
#print('hhh',jt.mean(per_box_regression))
# if per_box_loc.numel()>0:
# detections = jt.stack([
# per_locations[:, 0] - per_box_regression[:, 0],
# per_locations[:, 1] - per_box_regression[:, 1],
# per_locations[:, 0] + per_box_regression[:, 2],
# per_locations[:, 1] + per_box_regression[:, 3],
# ], dim=1)
# else:
# detections = jt.zeros((0,4),dtype=per_locations.dtype)
detections = jt.stack([
per_locations[:, 0] - per_box_regression[:, 0],
per_locations[:, 1] - per_box_regression[:, 1],
per_locations[:, 0] + per_box_regression[:, 2],
per_locations[:, 1] + per_box_regression[:, 3],
],
dim=1)
#print('detections',jt.mean(detections),detections.shape)
h, w = image_sizes[i]
boxlist = BoxList(detections, (int(w), int(h)), mode="xyxy")
boxlist.add_field("labels", per_class)
if self.is_sqrt:
boxlist.add_field("scores", per_box_cls.sqrt())
else:
boxlist.add_field("scores", per_box_cls)
#print('??',boxlist.get_field('scores'))
if boxlist.bbox.numel() > 0:
boxlist = boxlist.clip_to_image(remove_empty=False)
boxlist = remove_small_boxes(boxlist, self.min_size)
results.append(boxlist)
#print('Good')
return results
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
"""
# global II
# import pickle
N, A, H, W = objectness.shape
# put in the same format as anchors
objectness = permute_and_flatten(objectness, N, A, 1, H,
W).reshape(N, -1)
# print('objectness',objectness.mean())
objectness = objectness.sigmoid()
box_regression = permute_and_flatten(box_regression, N, A, 4, H, W)
# print('regression',box_regression.mean())
num_anchors = A * H * W
pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
# print(pre_nms_top_n)
#print('objectness',objectness)
# objectness = jt.array(pickle.load(open(f'/home/lxl/objectness_0_{II}.pkl','rb')))
# print(objectness.shape)
objectness, topk_idx = objectness.topk(pre_nms_top_n,
dim=1,
sorted=True)
# print(II,'topk',topk_idx.sum(),topk_idx.shape)
batch_idx = jt.arange(N).unsqueeze(1)
# pickle.dump(topk_idx.numpy(),open(f'/home/lxl/topk_idx_{II}_jt.pkl','wb'))
# topk_idx_tmp = topk_idx.numpy()
# batch_idx = jt.array(pickle.load(open(f'/home/lxl/batch_idx_{II}.pkl','rb')))
# topk_idx = jt.array(pickle.load(open(f'/home/lxl/topk_idx_{II}.pkl','rb')))
# err = np.abs(topk_idx_tmp-topk_idx.numpy())
# print('Error!!!!!!!!!!!!!!!!',err.sum())
# print(err.nonzero())
#print('box_regression0',box_regression)
#batch_idx = jt.index(topk_idx.shape,dim=0)
box_regression = box_regression[batch_idx, topk_idx]
#print('box_regression1',box_regression)
image_shapes = [box.size for box in anchors]
concat_anchors = jt.contrib.concat([a.bbox for a in anchors], dim=0)
concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx]
# box_regression = jt.array(pickle.load(open(f'/home/lxl/box_regression_{II}.pkl','rb')))
# concat_anchors = jt.array(pickle.load(open(f'/home/lxl/concat_anchors_{II}.pkl','rb')))
proposals = self.box_coder.decode(box_regression.reshape(-1, 4),
concat_anchors.reshape(-1, 4))
proposals = proposals.reshape(N, -1, 4)
# proposals = jt.array(pickle.load(open(f'/home/lxl/proposal_{II}.pkl','rb')))
# objectness = jt.array(pickle.load(open(f'/home/lxl/objectness_{II}.pkl','rb')))
# II+=1
result = []
for i in range(len(image_shapes)):
proposal, score, im_shape = proposals[i], objectness[
i], image_shapes[i]
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