🐛 [Bug] Bug encountered when compiling Jasper10x5dr network

[gs-olive]

Bug Description

When compiling the Jasper10x5dr speech recognition model with Torch-TRT, the following error is displayed:

ERROR: [Torch-TensorRT TorchScript Conversion Context] - 3: (Unnamed Layer* 22) [Unary]: operation FLOOR not allowed on type Int32
...
RuntimeError: [Error thrown at core/conversion/converters/impl/unsqueeze.cpp:25] Expected dim <= nbDims && dim >= -(nbDims + 1) to be true but got false
Dimension out of range (expected to be in range of [-1, 0], but got 1)

To Reproduce

Steps to reproduce the behavior:

1. Run torch_tensorrt.compile with Jasper10x5dr model as input, using fp32 precision.
2. Choose fixed input sizes of [1, 64, 256] and [1,] and enable truncate_long_and_double with 8 GB workspace.

Expected behavior

Model should successfully compile to Torch-TRT. Specifically, the floor operation should not throw an error on the input

Environment

• Torch-TensorRT Version: 1.3.0a0+b5bcccf9
• PyTorch Version: 1.14.0.dev20221018+cu116
• CPU Architecture: Intel Xeon CPU
• OS: Ubuntu 20.04
• How you installed PyTorch: pip
• Build command you used: python setup.py develop
• Are you using local sources or building from archives: local
• Python version: 3.8.13
• CUDA version: 11.6