update: 适配昇腾

ultralytics/nn/modules/head.py

@@ -102,9 +102,9 @@ class Detect(nn.Module):
         # Inference path
         shape = x[0].shape  # BCHW
         x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)
-        if self.format != "imx" and (self.dynamic or self.shape != shape):
-            self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
-            self.shape = shape
+        anchors, strides = make_anchors(x, self.stride, 0.5)
+        anchors = anchors.transpose(0, 1)
+        strides = strides.transpose(0, 1)
 
         if self.export and self.format in {"saved_model", "pb", "tflite", "edgetpu", "tfjs"}:  # avoid TF FlexSplitV ops
             box = x_cat[:, : self.reg_max * 4]
@@ -118,15 +118,15 @@ class Detect(nn.Module):
             grid_h = shape[2]
             grid_w = shape[3]
             grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1)
-            norm = self.strides / (self.stride[0] * grid_size)
-            dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
+            norm = strides / (stride[0] * grid_size)
+            dbox = self.decode_bboxes(self.dfl(box) * norm, anchors.unsqueeze(0) * norm[:, :2])
         elif self.export and self.format == "imx":
             dbox = self.decode_bboxes(
-                self.dfl(box) * self.strides, self.anchors.unsqueeze(0) * self.strides, xywh=False
+                self.dfl(box) * strides, anchors.unsqueeze(0) * strides, xywh=False
             )
             return dbox.transpose(1, 2), cls.sigmoid().permute(0, 2, 1)
         else:
-            dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
+            dbox = self.decode_bboxes(self.dfl(box), anchors.unsqueeze(0)) * strides
 
         return torch.cat((dbox, cls.sigmoid()), 1)