Enable ONNX `--half` FP16 inference (#6268)

* Enable ONNX ``--half` FP16 inference

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

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

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

detect.py

@@ -94,7 +94,7 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
     imgsz = check_img_size(imgsz, s=stride)  # check image size
 
     # Half
-    half &= (pt or jit or engine) and device.type != 'cpu'  # half precision only supported by PyTorch on CUDA
+    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()
 

tutorial.ipynb

@@ -1099,4 +1099,4 @@
       "outputs": []
     }
   ]
-}
+}

val.py

@@ -137,9 +137,9 @@ def run(data,
 
         # Load model
         model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
-        stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
+        stride, pt, jit, onnx, engine = model.stride, model.pt, model.jit, model.onnx, model.engine
         imgsz = check_img_size(imgsz, s=stride)  # check image size
-        half &= (pt or jit or engine) and device.type != 'cpu'  # half precision only supported by PyTorch on CUDA
+        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: