DetectMultiBackend() --half handling (#6945)

* DetectMultiBackend() `--half` handling

* CI fixes

* rename .half to .fp16 to avoid conflict

* warmup fix

* val update

* engine update

* engine update

detect.py

@@ -89,19 +89,10 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
 
     # Load model
     device = select_device(device)
-    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
-    stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
     imgsz = check_img_size(imgsz, s=stride)  # check image size
 
-    # Half
-    half &= (pt or jit or onnx or engine) and device.type != 'cpu'  # FP16 supported on limited backends with CUDA
-    if pt or jit:
-        model.model.half() if half else model.model.float()
-    elif engine and model.trt_fp16_input != half:
-        LOGGER.info('model ' + (
-            'requires' if model.trt_fp16_input else 'incompatible with') + ' --half. Adjusting automatically.')
-        half = model.trt_fp16_input
-
     # Dataloader
     if webcam:
         view_img = check_imshow()
@@ -114,12 +105,12 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
     vid_path, vid_writer = [None] * bs, [None] * bs
 
     # Run inference
-    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)  # warmup
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
     dt, seen = [0.0, 0.0, 0.0], 0
     for path, im, im0s, vid_cap, s in dataset:
         t1 = time_sync()
         im = torch.from_numpy(im).to(device)
-        im = im.half() if half else im.float()  # uint8 to fp16/32
+        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