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
BatchToSpaceND is used by TensorFlow to implement dilated convolutions (and this is the case for wav2letter model). So theoretically tfonnx could fold them.
I'm trying to convert the OpenSeq2Seq's wav2letter model checkpoints from TensorFlow to ONNX.
It contains BatchToSpaceND ops. Inputs are however a 3d tensor. Currently tfonnx supports NHWC.
Proposal: if the input is 3d, insert automatically an Unsqueeze op or a rewriter in order to reshape to NH1C and then back to NHC.
The text was updated successfully, but these errors were encountered: