Improved detect.py timing (#4741)

* Improved detect.py timing

* Eliminate 1 time_sync() call

* Inference-only time

* dash

* #Save section

* Cleanup

val.py

@@ -154,22 +154,22 @@ def run(data,
     names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.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')
-    p, r, f1, mp, mr, map50, map, t0, t1, t2 = 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.
+    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
     loss = torch.zeros(3, device=device)
     jdict, stats, ap, ap_class = [], [], [], []
     for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
-        t_ = time_sync()
+        t1 = time_sync()
         img = img.to(device, non_blocking=True)
         img = img.half() if half else img.float()  # uint8 to fp16/32
         img /= 255.0  # 0 - 255 to 0.0 - 1.0
         targets = targets.to(device)
         nb, _, height, width = img.shape  # batch size, channels, height, width
-        t = time_sync()
-        t0 += t - t_
+        t2 = time_sync()
+        dt[0] += t2 - t1
 
         # Run model
         out, train_out = model(img, augment=augment)  # inference and training outputs
-        t1 += time_sync() - t
+        dt[1] += time_sync() - t2
 
         # Compute loss
         if compute_loss:
@@ -178,9 +178,9 @@ def run(data,
         # Run NMS
         targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
         lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
-        t = time_sync()
+        t3 = time_sync()
         out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
-        t2 += time_sync() - t
+        dt[2] += time_sync() - t3
 
         # Statistics per image
         for si, pred in enumerate(out):
@@ -247,7 +247,7 @@ def run(data,
             print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
 
     # Print speeds
-    t = tuple(x / seen * 1E3 for x in (t0, t1, t2))  # speeds per image
+    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
     if not training:
         shape = (batch_size, 3, imgsz, imgsz)
         print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)