Fixing minor multi-streaming issues with TensoRT engine (#6504)

detect.py

@@ -110,7 +110,7 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
     vid_path, vid_writer = [None] * bs, [None] * bs
 
     # Run inference
-    model.warmup(imgsz=(1, 3, *imgsz), half=half)  # warmup
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)  # warmup
     dt, seen = [0.0, 0.0, 0.0], 0
     for path, im, im0s, vid_cap, s in dataset:
         t1 = time_sync()
@@ -175,9 +175,6 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
                         if save_crop:
                             save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
 
-            # Print time (inference-only)
-            LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
-
             # Stream results
             im0 = annotator.result()
             if view_img:
@@ -203,6 +200,9 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
                         vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                     vid_writer[i].write(im0)
 
+        # Print time (inference-only)
+        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
+
     # Print results
     t = tuple(x / 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)

val.py

@@ -162,7 +162,7 @@ def run(data,
 
     # Dataloader
     if not training:
-        model.warmup(imgsz=(1, 3, imgsz, imgsz), half=half)  # warmup
+        model.warmup(imgsz=(1 if pt else batch_size, 3, imgsz, imgsz), half=half)  # warmup
         pad = 0.0 if task == 'speed' else 0.5
         task = task if task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
         dataloader = create_dataloader(data[task], imgsz, batch_size, stride, single_cls, pad=pad, rect=pt,