diff --git a/models/common.py b/models/common.py
index ec5fbfaec4ca..c269cfef9a6c 100644
--- a/models/common.py
+++ b/models/common.py
@@ -320,9 +320,11 @@ def __init__(self, weights='yolov5s.pt', device=None, dnn=False):
             net = cv2.dnn.readNetFromONNX(w)
         elif onnx:  # ONNX Runtime
             LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
-            check_requirements(('onnx', 'onnxruntime-gpu' if torch.cuda.is_available() else 'onnxruntime'))
+            cuda = torch.cuda.is_available()
+            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
             import onnxruntime
-            session = onnxruntime.InferenceSession(w, None)
+            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+            session = onnxruntime.InferenceSession(w, providers=providers)
         elif engine:  # TensorRT
             LOGGER.info(f'Loading {w} for TensorRT inference...')
             import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download