I have the following problems when using rnnt_loss_simple:
I checked the shape of the input tensor:
and the output of the code:
python=3.8.11 torch verison=1.10.1 cudatoolkit=10.2.89 CUDA version=10.2.
Is this a known issue? How can it be debugged and solved?
Thank you!
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: <danpovey/fast_rnnt/issues/7@github.com>
I have the following problems when using rnnt_loss_simple:
I checked the shape of the input tensor:![1655195453(1)](https://user-images.githubusercontent.com/74249633/173531740-86be3d91-a36e-4eb0-88fd-396d052d30c7.png)
and the output of the code:![1655195474(1)](https://user-images.githubusercontent.com/74249633/173531847-a2062334-3754-4394-a051-7a5e78b4a080.png)
python=3.8.11 torch verison=1.10.1 cudatoolkit=10.2.89 CUDA version=10.2.
Is this a known issue? How can it be debugged and solved?
Thank you!