Give me a serialized model , how to determine it is fp32 or fp16?

[shaoyan_shi93]

Description

give me a serialized model , how to determine it is fp32 or fp16? and i donnot know parameters in serializing

Environment

TensorRT Version: 8.2.4
GPU Type: 1660ti
Nvidia Driver Version: 530
CUDA Version: 11.6
CUDNN Version: 8.2.1
Operating System + Version: win10
Python Version (if applicable): 3.9.7
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 1.9.0
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

• Exact steps/commands to build your repro
• Exact steps/commands to run your repro
• Full traceback of errors encountered

[AakankshaS]

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:

Quick Start Guide :: NVIDIA Deep Learning TensorRT Documentation

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.

TensorRT/samples/trtexec at master · NVIDIA/TensorRT

In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!

[shaoyan_shi93]

my serialized model is serialized with c++ project, can it is validated in python script?

[shaoyan_shi93]

i run it ‘–verbose’,but cannot find information about it

[AakankshaS]

Hi @shaoyan_shi93 ,
I am afraid that the data type is logged in only during the build phase.

Thanks