-
Notifications
You must be signed in to change notification settings - Fork 238
Description
Would it be possible to provide an example of running inference on the unconverted (non-tflite) model as well.
If I try to run the tflite if segfaults always. I think the conversation is a bit buggy.
my steps are:
In TensorFlowASR/examples/conformer:
- train_conformer.py -> creates checkpoint and h5 file
- tflite_conformer.py -> point to the h5 file
Then, I run TensorFlowASR/examples/demonstrations/conformer.py and point to tflite file produced.
INFO: TfLiteFlexDelegate delegate: 212 nodes delegated out of 2737 nodes with 130 partitions.
INFO: TfLiteFlexDelegate delegate: 0 nodes delegated out of 1 nodes with 0 partitions.
INFO: TfLiteFlexDelegate delegate: 0 nodes delegated out of 1 nodes with 0 partitions.
INFO: TfLiteFlexDelegate delegate: 0 nodes delegated out of 1 nodes with 0 partitions.
INFO: TfLiteFlexDelegate delegate: 0 nodes delegated out of 26 nodes with 0 partitions.
INFO: TfLiteFlexDelegate delegate: 0 nodes delegated out of 1 nodes with 0 partitions.
INFO: TfLiteFlexDelegate delegate: 1 nodes delegated out of 40 nodes with 1 partitions.
2020-11-16 23:01:41.748132: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
Segmentation fault (core dumped)