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

`torch.empty()` for speed improvement

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

utils/autobatch.py

@@ -47,7 +47,7 @@ def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
     # Profile batch sizes
     batch_sizes = [1, 2, 4, 8, 16]
     try:
-        img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
+        img = [torch.empty(b, 3, imgsz, imgsz) for b in batch_sizes]
         results = profile(img, model, n=3, device=device)
     except Exception as e:
         LOGGER.warning(f'{prefix}{e}')

utils/loggers/__init__.py

@@ -300,7 +300,7 @@ def log_tensorboard_graph(tb, model, imgsz=(640, 640)):
     try:
         p = next(model.parameters())  # for device, type
         imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz  # expand
-        im = torch.zeros((1, 3, *imgsz)).to(p.device).type_as(p)  # input image
+        im = torch.empty((1, 3, *imgsz)).to(p.device).type_as(p)  # input image
         with warnings.catch_warnings():
             warnings.simplefilter('ignore')  # suppress jit trace warning
             tb.add_graph(torch.jit.trace(de_parallel(model), im, strict=False), [])

utils/torch_utils.py

@@ -282,7 +282,7 @@ def model_info(model, verbose=False, imgsz=640):
     try:  # FLOPs
         p = next(model.parameters())
         stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32  # max stride
-        im = torch.zeros((1, p.shape[1], stride, stride), device=p.device)  # input image in BCHW format
+        im = torch.empty((1, p.shape[1], stride, stride), device=p.device)  # input image in BCHW format
         flops = thop.profile(deepcopy(model), inputs=(im,), verbose=False)[0] / 1E9 * 2  # stride GFLOPs
         imgsz = imgsz if isinstance(imgsz, list) else [imgsz, imgsz]  # expand if int/float
         fs = f', {flops * imgsz[0] / stride * imgsz[1] / stride:.1f} GFLOPs'  # 640x640 GFLOPs