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

ultralytics 8.0.235 YOLOv8 OBB train, val, predict and export (#4499)

Browse source 
Co-authored-by: Yash Khurana <ykhurana6@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Swamita Gupta <swamita2001@gmail.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Laughing-q <1182102784@qq.com>
This commit is contained in:
Glenn Jocher 2024-01-05 03:00:26 +01:00 • committed by GitHub
parent f702b34a50
commit 072291bc78
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
52 changed files with 2090 additions and 524 deletions
Download patch file Download diff file Expand all files Collapse all files

140
ultralytics/utils/loss.py
View file

@ -6,9 +6,9 @@ import torch.nn.functional as F
from ultralytics.utils.metrics import OKS_SIGMA
from ultralytics.utils.ops import crop_mask, xywh2xyxy, xyxy2xywh
from ultralytics.utils.tal import TaskAlignedAssigner, dist2bbox, make_anchors
from ultralytics.utils.tal import RotatedTaskAlignedAssigner, TaskAlignedAssigner, dist2bbox, dist2rbox, make_anchors
from .metrics import bbox_iou
from .metrics import bbox_iou, probiou
from .tal import bbox2dist
@ -95,6 +95,30 @@ class BboxLoss(nn.Module):
F.cross_entropy(pred_dist, tr.view(-1), reduction='none').view(tl.shape) * wr).mean(-1, keepdim=True)
class RotatedBboxLoss(BboxLoss):
"""Criterion class for computing training losses during training."""
def __init__(self, reg_max, use_dfl=False):
"""Initialize the BboxLoss module with regularization maximum and DFL settings."""
super().__init__(reg_max, use_dfl)
def forward(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask):
"""IoU loss."""
weight = target_scores.sum(-1)[fg_mask].unsqueeze(-1)
iou = probiou(pred_bboxes[fg_mask], target_bboxes[fg_mask])
loss_iou = ((1.0 - iou) * weight).sum() / target_scores_sum
# DFL loss
if self.use_dfl:
target_ltrb = bbox2dist(anchor_points, xywh2xyxy(target_bboxes[..., :4]), self.reg_max)
loss_dfl = self._df_loss(pred_dist[fg_mask].view(-1, self.reg_max + 1), target_ltrb[fg_mask]) * weight
loss_dfl = loss_dfl.sum() / target_scores_sum
else:
loss_dfl = torch.tensor(0.0).to(pred_dist.device)
return loss_iou, loss_dfl
class KeypointLoss(nn.Module):
"""Criterion class for computing training losses."""
@ -243,9 +267,9 @@ class v8SegmentationLoss(v8DetectionLoss):
except RuntimeError as e:
raise TypeError('ERROR ❌ segment dataset incorrectly formatted or not a segment dataset.\n'
"This error can occur when incorrectly training a 'segment' model on a 'detect' dataset, "
"i.e. 'yolo train model=yolov8n-seg.pt data=coco128.yaml'.\nVerify your dataset is a "
"correctly formatted 'segment' dataset using 'data=coco128-seg.yaml' "
'as an example.\nSee https://docs.ultralytics.com/tasks/segment/ for help.') from e
"i.e. 'yolo train model=yolov8n-seg.pt data=coco8.yaml'.\nVerify your dataset is a "
"correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' "
'as an example.\nSee https://docs.ultralytics.com/datasets/segment/ for help.') from e
# Pboxes
pred_bboxes = self.bbox_decode(anchor_points, pred_distri) # xyxy, (b, h*w, 4)
@ -526,3 +550,109 @@ class v8ClassificationLoss:
loss = torch.nn.functional.cross_entropy(preds, batch['cls'], reduction='mean')
loss_items = loss.detach()
return loss, loss_items
class v8OBBLoss(v8DetectionLoss):
def __init__(self, model): # model must be de-paralleled
super().__init__(model)
self.assigner = RotatedTaskAlignedAssigner(topk=10, num_classes=self.nc, alpha=0.5, beta=6.0)
self.bbox_loss = RotatedBboxLoss(self.reg_max - 1, use_dfl=self.use_dfl).to(self.device)
def preprocess(self, targets, batch_size, scale_tensor):
"""Preprocesses the target counts and matches with the input batch size to output a tensor."""
if targets.shape[0] == 0:
out = torch.zeros(batch_size, 0, 6, device=self.device)
else:
i = targets[:, 0] # image index
_, counts = i.unique(return_counts=True)
counts = counts.to(dtype=torch.int32)
out = torch.zeros(batch_size, counts.max(), 6, device=self.device)
for j in range(batch_size):
matches = i == j
n = matches.sum()
if n:
bboxes = targets[matches, 2:]
bboxes[..., :4].mul_(scale_tensor)
out[j, :n] = torch.cat([targets[matches, 1:2], bboxes], dim=-1)
return out
def __call__(self, preds, batch):
"""Calculate and return the loss for the YOLO model."""
loss = torch.zeros(3, device=self.device) # box, cls, dfl
feats, pred_angle = preds if isinstance(preds[0], list) else preds[1]
batch_size = pred_angle.shape[0] # batch size, number of masks, mask height, mask width
pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
(self.reg_max * 4, self.nc), 1)
# b, grids, ..
pred_scores = pred_scores.permute(0, 2, 1).contiguous()
pred_distri = pred_distri.permute(0, 2, 1).contiguous()
pred_angle = pred_angle.permute(0, 2, 1).contiguous()
dtype = pred_scores.dtype
imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0] # image size (h,w)
anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)
# targets
try:
batch_idx = batch['batch_idx'].view(-1, 1)
targets = torch.cat((batch_idx, batch['cls'].view(-1, 1), batch['bboxes'].view(-1, 5)), 1)
rw, rh = targets[:, 4] * imgsz[0].item(), targets[:, 5] * imgsz[1].item()
targets = targets[(rw >= 2) & (rh >= 2)] # filter rboxes of tiny size to stabilize training
targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
gt_labels, gt_bboxes = targets.split((1, 5), 2) # cls, xywhr
mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)
except RuntimeError as e:
raise TypeError('ERROR ❌ OBB dataset incorrectly formatted or not a OBB dataset.\n'
"This error can occur when incorrectly training a 'OBB' model on a 'detect' dataset, "
"i.e. 'yolo train model=yolov8n-obb.pt data=coco8.yaml'.\nVerify your dataset is a "
"correctly formatted 'OBB' dataset using 'data=coco8-obb.yaml' "
'as an example.\nSee https://docs.ultralytics.com/datasets/obb/ for help.') from e
# Pboxes
pred_bboxes = self.bbox_decode(anchor_points, pred_distri, pred_angle) # xyxy, (b, h*w, 4)
bboxes_for_assigner = pred_bboxes.clone().detach()
# Only the first four elements need to be scaled
bboxes_for_assigner[..., :4] *= stride_tensor
_, target_bboxes, target_scores, fg_mask, _ = self.assigner(pred_scores.detach().sigmoid(),
bboxes_for_assigner.type(gt_bboxes.dtype),
anchor_points * stride_tensor, gt_labels, gt_bboxes,
mask_gt)
target_scores_sum = max(target_scores.sum(), 1)
# Cls loss
# loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum # VFL way
loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum # BCE
# Bbox loss
if fg_mask.sum():
target_bboxes[..., :4] /= stride_tensor
loss[0], loss[2] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores,
target_scores_sum, fg_mask)
else:
loss[0] += (pred_angle * 0).sum()
loss[0] *= self.hyp.box # box gain
loss[1] *= self.hyp.cls # cls gain
loss[2] *= self.hyp.dfl # dfl gain
return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl)
def bbox_decode(self, anchor_points, pred_dist, pred_angle):
"""
Decode predicted object bounding box coordinates from anchor points and distribution.
Args:
anchor_points (torch.Tensor): Anchor points, (h*w, 2).
pred_dist (torch.Tensor): Predicted rotated distance, (bs, h*w, 4).
pred_angle (torch.Tensor): Predicted angle, (bs, h*w, 1).
Returns:
(torch.Tensor): Predicted rotated bounding boxes with angles, (bs, h*w, 5).
"""
if self.use_dfl:
b, a, c = pred_dist.shape # batch, anchors, channels
pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
return torch.cat((dist2rbox(pred_dist, pred_angle, anchor_points), pred_angle), dim=-1)