HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.79 expand Docs reference section (#2053)

Browse source 
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Fri3dChicken <87434761+AmoghDhaliwal@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-04-16 12:28:12 +02:00 • committed by GitHub
parent 47bd8b433b
commit 31db8ed163
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
106 changed files with 2570 additions and 529 deletions
Download patch file Download diff file Expand all files Collapse all files

64
ultralytics/yolo/utils/tal.py
View file

@ -54,6 +54,19 @@ def select_highest_overlaps(mask_pos, overlaps, n_max_boxes):
class TaskAlignedAssigner(nn.Module):
"""
A task-aligned assigner for object detection.
This class assigns ground-truth (gt) objects to anchors based on the task-aligned metric,
which combines both classification and localization information.
Attributes:
topk (int): The number of top candidates to consider.
num_classes (int): The number of object classes.
alpha (float): The alpha parameter for the classification component of the task-aligned metric.
beta (float): The beta parameter for the localization component of the task-aligned metric.
eps (float): A small value to prevent division by zero.
"""
def __init__(self, topk=13, num_classes=80, alpha=1.0, beta=6.0, eps=1e-9):
super().__init__()
@ -66,8 +79,9 @@ class TaskAlignedAssigner(nn.Module):
@torch.no_grad()
def forward(self, pd_scores, pd_bboxes, anc_points, gt_labels, gt_bboxes, mask_gt):
"""This code referenced to
https://github.com/Nioolek/PPYOLOE_pytorch/blob/master/ppyoloe/assigner/tal_assigner.py
"""
Compute the task-aligned assignment.
Reference https://github.com/Nioolek/PPYOLOE_pytorch/blob/master/ppyoloe/assigner/tal_assigner.py
Args:
pd_scores (Tensor): shape(bs, num_total_anchors, num_classes)
@ -76,11 +90,13 @@ class TaskAlignedAssigner(nn.Module):
gt_labels (Tensor): shape(bs, n_max_boxes, 1)
gt_bboxes (Tensor): shape(bs, n_max_boxes, 4)
mask_gt (Tensor): shape(bs, n_max_boxes, 1)
Returns:
target_labels (Tensor): shape(bs, num_total_anchors)
target_bboxes (Tensor): shape(bs, num_total_anchors, 4)
target_scores (Tensor): shape(bs, num_total_anchors, num_classes)
fg_mask (Tensor): shape(bs, num_total_anchors)
target_gt_idx (Tensor): shape(bs, num_total_anchors)
"""
self.bs = pd_scores.size(0)
self.n_max_boxes = gt_bboxes.size(1)
@ -142,9 +158,19 @@ class TaskAlignedAssigner(nn.Module):
def select_topk_candidates(self, metrics, largest=True, topk_mask=None):
"""
Select the top-k candidates based on the given metrics.
Args:
metrics: (b, max_num_obj, h*w).
topk_mask: (b, max_num_obj, topk) or None
metrics (Tensor): A tensor of shape (b, max_num_obj, h*w), where b is the batch size,
max_num_obj is the maximum number of objects, and h*w represents the
total number of anchor points.
largest (bool): If True, select the largest values; otherwise, select the smallest values.
topk_mask (Tensor): An optional boolean tensor of shape (b, max_num_obj, topk), where
topk is the number of top candidates to consider. If not provided,
the top-k values are automatically computed based on the given metrics.
Returns:
(Tensor): A tensor of shape (b, max_num_obj, h*w) containing the selected top-k candidates.
"""
num_anchors = metrics.shape[-1] # h*w
@ -165,22 +191,38 @@ class TaskAlignedAssigner(nn.Module):
def get_targets(self, gt_labels, gt_bboxes, target_gt_idx, fg_mask):
"""
Compute target labels, target bounding boxes, and target scores for the positive anchor points.
Args:
gt_labels: (b, max_num_obj, 1)
gt_bboxes: (b, max_num_obj, 4)
target_gt_idx: (b, h*w)
fg_mask: (b, h*w)
gt_labels (Tensor): Ground truth labels of shape (b, max_num_obj, 1), where b is the
batch size and max_num_obj is the maximum number of objects.
gt_bboxes (Tensor): Ground truth bounding boxes of shape (b, max_num_obj, 4).
target_gt_idx (Tensor): Indices of the assigned ground truth objects for positive
anchor points, with shape (b, h*w), where h*w is the total
number of anchor points.
fg_mask (Tensor): A boolean tensor of shape (b, h*w) indicating the positive
(foreground) anchor points.
Returns:
(Tuple[Tensor, Tensor, Tensor]): A tuple containing the following tensors:
- target_labels (Tensor): Shape (b, h*w), containing the target labels for
positive anchor points.
- target_bboxes (Tensor): Shape (b, h*w, 4), containing the target bounding boxes
for positive anchor points.
- target_scores (Tensor): Shape (b, h*w, num_classes), containing the target scores
for positive anchor points, where num_classes is the number
of object classes.
"""
# assigned target labels, (b, 1)
# Assigned target labels, (b, 1)
batch_ind = torch.arange(end=self.bs, dtype=torch.int64, device=gt_labels.device)[..., None]
target_gt_idx = target_gt_idx + batch_ind * self.n_max_boxes # (b, h*w)
target_labels = gt_labels.long().flatten()[target_gt_idx] # (b, h*w)
# assigned target boxes, (b, max_num_obj, 4) -> (b, h*w)
# Assigned target boxes, (b, max_num_obj, 4) -> (b, h*w)
target_bboxes = gt_bboxes.view(-1, 4)[target_gt_idx]
# assigned target scores
# Assigned target scores
target_labels.clamp(0)
target_scores = F.one_hot(target_labels, self.num_classes) # (b, h*w, 80)
fg_scores_mask = fg_mask[:, :, None].repeat(1, 1, self.num_classes) # (b, h*w, 80)