Open vincentme opened 5 months ago
<
ir_version: 9,
opset_import: ["" : 20]
>
test (float[row,col] img_in) => (float[row,col] img_out) {
const = Constant <value: tensor = float[2] const {2,2}> ()
img_out = Resize <mode: string = "linear"> (img_in, const)
}
You observation is correct and could be a bug. Please use None
for now for any optional inputs. E.g.
img_out = op.Resize(img_in, None, scales = [2.0, 2.0], mode = 'linear')
behavior
I specified
scales = [2.0, 2.0]
inop.Resize
. Evaluation works in onnxscript itself, but after export to modelproto and run by onnx ReferenceEvaluator or onnxruntime, error occurs and seems that the parameter[2.0, 2.0]
was set toroi
,scale_factors
andoutput_size
are bothNone
.code to reproduce
error message