Loss and IoU speed improvements (#7361)

* Loss speed improvements

* bbox_iou speed improvements

* bbox_ioa speed improvements

* box_iou speed improvements

* box_iou speed improvements

utils/loss.py

@@ -138,7 +138,7 @@ class ComputeLoss:
                 pxy = pxy.sigmoid() * 2 - 0.5
                 pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
                 pbox = torch.cat((pxy, pwh), 1)  # predicted box
-                iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
+                iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze()  # iou(prediction, target)
                 lbox += (1.0 - iou).mean()  # iou loss
 
                 # Objectness
@@ -180,7 +180,7 @@ class ComputeLoss:
         tcls, tbox, indices, anch = [], [], [], []
         gain = torch.ones(7, device=self.device)  # normalized to gridspace gain
         ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
-        targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2)  # append anchor indices
+        targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2)  # append anchor indices
 
         g = 0.5  # bias
         off = torch.tensor(
@@ -199,10 +199,10 @@ class ComputeLoss:
             gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  # xyxy gain
 
             # Match targets to anchors
-            t = targets * gain
+            t = targets * gain  # shape(3,n,7)
             if nt:
                 # Matches
-                r = t[:, :, 4:6] / anchors[:, None]  # wh ratio
+                r = t[..., 4:6] / anchors[:, None]  # wh ratio
                 j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t']  # compare
                 # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
                 t = t[j]  # filter