You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I tried the latest tf2onnx and used tf2onnx.convert.from_keras(model,opset=19) to convert my keras h5 model. Here is my partial code for preprocessing:
however, I got two error messages shown below:
The first error says that ComplexAbs doesn't expect the same dimesion input as tf.abs used. This is not an issue for opset -13, so i hope this is just a bug.
then, the second one says antialias for resize is not supported. I wonder if the antialias supported in Resize Op is the same as the tf.image.resize(..., antialias = True).
Here is the resize bilinear with antialias example in ONNX documentation.
Thanks for your time.
The text was updated successfully, but these errors were encountered:
Hi, I tried the latest tf2onnx and used tf2onnx.convert.from_keras(model,opset=19) to convert my keras h5 model. Here is my partial code for preprocessing:
however, I got two error messages shown below:
The first error says that ComplexAbs doesn't expect the same dimesion input as tf.abs used. This is not an issue for opset -13, so i hope this is just a bug.
then, the second one says antialias for resize is not supported. I wonder if the antialias supported in Resize Op is the same as the tf.image.resize(..., antialias = True).
Here is the resize bilinear with antialias example in ONNX documentation.
Thanks for your time.
The text was updated successfully, but these errors were encountered: