torch.empty() for speed improvements (#9025)

`torch.empty()` for speed improvement

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

models/common.py

@@ -531,7 +531,7 @@ class DetectMultiBackend(nn.Module):
         # Warmup model by running inference once
         warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb
         if any(warmup_types) and self.device.type != 'cpu':
-            im = torch.zeros(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
+            im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
             for _ in range(2 if self.jit else 1):  #
                 self.forward(im)  # warmup
 
@@ -600,7 +600,7 @@ class AutoShape(nn.Module):
 
         dt = (Profile(), Profile(), Profile())
         with dt[0]:
-            p = next(self.model.parameters()) if self.pt else torch.zeros(1, device=self.model.device)  # param
+            p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device)  # param
             autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
             if isinstance(ims, torch.Tensor):  # torch
                 with amp.autocast(autocast):

models/yolo.py

@@ -46,8 +46,8 @@ class Detect(nn.Module):
         self.no = nc + 5  # number of outputs per anchor
         self.nl = len(anchors)  # number of detection layers
         self.na = len(anchors[0]) // 2  # number of anchors
-        self.grid = [torch.zeros(1)] * self.nl  # init grid
-        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
+        self.grid = [torch.empty(1)] * self.nl  # init grid
+        self.anchor_grid = [torch.empty(1)] * self.nl  # init anchor grid
         self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
         self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
         self.inplace = inplace  # use inplace ops (e.g. slice assignment)
@@ -175,7 +175,7 @@ class DetectionModel(BaseModel):
         if isinstance(m, Detect):
             s = 256  # 2x min stride
             m.inplace = self.inplace
-            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.empty(1, ch, s, s))])  # forward
             check_anchor_order(m)  # must be in pixel-space (not grid-space)
             m.anchors /= m.stride.view(-1, 1, 1)
             self.stride = m.stride