Update README.md

README.md

@@ -5,8 +5,10 @@ license: apache-2.0
 This is an ONNX model ported from original PyTorch big-lama model.
 
 ## Notes:
-1. We use a custom FourierUnit implementation, as the original cannot be directly ported to ONNX without overhead. The result is not the same, but close
+1. We use a custom FourierUnit implementation, as the original cannot be directly ported to ONNX without overhead. The result is not the same, but very close
 2. The input shape is fixed to 512x512 pixels.
+3. The opset version is 18.
+
 
 Original repo: https://github.com/advimman/lama