Improved Profile() inference timing (#9024)

* Improved `Profile()` class

* Update predict.py

* Update val.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update val.py

* Update AutoShape

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

detect.py

@@ -41,10 +41,10 @@ ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
 from models.common import DetectMultiBackend
 from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
-from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                            increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
 from utils.plots import Annotator, colors, save_one_box
-from utils.torch_utils import select_device, smart_inference_mode, time_sync
+from utils.torch_utils import select_device, smart_inference_mode
 
 
 @smart_inference_mode()
@@ -107,26 +107,23 @@ def run(
 
     # Run inference
     model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
-    seen, windows, dt = 0, [], [0.0, 0.0, 0.0]
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
     for path, im, im0s, vid_cap, s in dataset:
-        t1 = time_sync()
-        im = torch.from_numpy(im).to(device)
-        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
-        im /= 255  # 0 - 255 to 0.0 - 1.0
-        if len(im.shape) == 3:
-            im = im[None]  # expand for batch dim
-        t2 = time_sync()
-        dt[0] += t2 - t1
+        with dt[0]:
+            im = torch.from_numpy(im).to(device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
 
         # Inference
-        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
-        pred = model(im, augment=augment, visualize=visualize)
-        t3 = time_sync()
-        dt[1] += t3 - t2
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
 
         # NMS
-        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
-        dt[2] += time_sync() - t3
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
 
         # Second-stage classifier (optional)
         # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
@@ -201,10 +198,10 @@ def run(
                     vid_writer[i].write(im0)
 
         # Print time (inference-only)
-        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
 
     # Print results
-    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
     LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
     if save_txt or save_img:
         s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''