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>

val.py

@@ -37,7 +37,7 @@ ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 from models.common import DetectMultiBackend
 from utils.callbacks import Callbacks
 from utils.dataloaders import create_dataloader
-from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_yaml,
+from utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_yaml,
                            coco80_to_coco91_class, colorstr, increment_path, non_max_suppression, print_args,
                            scale_coords, xywh2xyxy, xyxy2xywh)
 from utils.metrics import ConfusionMatrix, ap_per_class, box_iou
@@ -187,26 +187,24 @@ def run(
         names = dict(enumerate(names))
     class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
     s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
-    dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
+    dt, p, r, f1, mp, mr, map50, map = (Profile(), Profile(), Profile()), 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
     loss = torch.zeros(3, device=device)
     jdict, stats, ap, ap_class = [], [], [], []
     callbacks.run('on_val_start')
     pbar = tqdm(dataloader, desc=s, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
     for batch_i, (im, targets, paths, shapes) in enumerate(pbar):
         callbacks.run('on_val_batch_start')
-        t1 = time_sync()
-        if cuda:
-            im = im.to(device, non_blocking=True)
-            targets = targets.to(device)
-        im = im.half() if half else im.float()  # uint8 to fp16/32
-        im /= 255  # 0 - 255 to 0.0 - 1.0
-        nb, _, height, width = im.shape  # batch size, channels, height, width
-        t2 = time_sync()
-        dt[0] += t2 - t1
+        with dt[0]:
+            if cuda:
+                im = im.to(device, non_blocking=True)
+                targets = targets.to(device)
+            im = im.half() if half else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            nb, _, height, width = im.shape  # batch size, channels, height, width
 
         # Inference
-        out, train_out = model(im) if training else model(im, augment=augment, val=True)  # inference, loss outputs
-        dt[1] += time_sync() - t2
+        with dt[1]:
+            out, train_out = model(im) if training else model(im, augment=augment, val=True)  # inference, loss outputs
 
         # Loss
         if compute_loss:
@@ -215,9 +213,8 @@ def run(
         # NMS
         targets[:, 2:] *= torch.tensor((width, height, width, height), device=device)  # to pixels
         lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
-        t3 = time_sync()
-        out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
-        dt[2] += time_sync() - t3
+        with dt[2]:
+            out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
 
         # Metrics
         for si, pred in enumerate(out):
@@ -284,7 +281,7 @@ def run(
             LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
 
     # Print speeds
-    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
     if not training:
         shape = (batch_size, 3, imgsz, imgsz)
         LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)