Does trt 8.0 support Bidirectional LSTM？

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

TensorRT 8.0

Does trt 8.0 support Bidirectional LSTM ?

from keras.layers import Bidirectional
from keras.layers.recurrent import LSTM

x = Bidirectional(LSTM(32, return_sequences=True))(x)

$ trtexec --onnx=./bidirectional_LSTM_.onnx --saveEngine=my.engine
gets the below error


[08/02/2021-06:12:13] [E] [TRT] ModelImporter.cpp:723: --- End node ---
[08/02/2021-06:12:13] [E] [TRT] ModelImporter.cpp:725: ERROR: builtin_op_importers.cpp:2339 In function importLSTM:
[8] Assertion failed: std::equal(activationAlphas.begin(), activationAlphas.begin() + NUM_ACTIVATIONS, activationAlphas.begin() + NUM_ACTIVATIONS) && "The parser does not currently support cases where activations for the reverse pass of the LSTM do not match the forward pass."
[08/02/2021-06:12:13] [E] Failed to parse onnx file
[08/02/2021-06:12:13] [I] Finish parsing network model
[08/02/2021-06:12:13] [E] Parsing model failed
[08/02/2021-06:12:13] [E] Engine creation failed
[08/02/2021-06:12:13] [E] Engine set up failed

Thanks

2

Hi,
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:

  1. validating your model with the below snippet

check_model.py

import sys
import onnx
filename = yourONNXmodel
model = onnx.load(filename)
onnx.checker.check_model(model).
2) Try running your model with trtexec command.
https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!

4

Thanks for the reply.
The issue has been fixed: The keras version is upgraded from 2.2.4 to 2.3.1