Hello, I'm working on a speech classification model built on Pytorch's nn.Conv1d. PyTorch expects the conv1d input shape to be (batch, channel, length), in my case (time_stamps, 1, feat_dimension).
After converting to TFLite, MLIA analysis shows that Conv ops only run on the NPU if batch_size=1.
If batch_size>1, it runs on the CPU with the message: "IFM Tensor batch size must be 1."
Since my user case requires time_stamps > 1 (a.k.a batch_size > 1), how can I solve to ensure Conv ops run on NPU?
Thank you,Hao
Ok, thanks for confirming.There will be an update on pypi soon that will fix this. I'll notify when it's ready to use.
That would be great, thanks!
FYI - if you build mlia and it's ethos-u plugin yourself you can have the fix now.
We have released today the new versions on pypi! https://pypi.org/search/?q=mlia-
As Ben mentioned, we’ve moved to a plugin architecture. To target Ethos-U, you’ll need to install the mlia-ethos-u package.
mlia-ethos-u
The error appears to be fixed in our tests. Can you please let us know if you still encounter it? Thanks!