TensorRT Initialization Failure

[sayyid-abolfazl]

Hello guys, thank you all for everything.

I am trying to use the s_face face_recognition model in tensorRT mode :

https://github.com/opencv/opencv_zoo/tree/main/models/face_recognition_sface

To start, I checked the model with the netron tool to get the model inputs and outputs :

Now, let's compare two photos for a test :

This is my program at this address
https://github.com/sayyid-abolfazl/sface_trt

and its output is not correct

I think the issue is that in the ONNX model, in addition to the image, it also receives face coordinates and landmarks, but in netron, nothing is visible.

This means the model crops the image, then aligns it, and extracts features. Could you please guide me on how to solve this challenge?

_recognizer alignCrop feature :

https://github.com/opencv/opencv_zoo/blob/main/models/face_recognition_sface/demo.cpp

Is it possible to simplify the model so that it only performs facial feature extraction and removes other operations such as facial alignment, cropping, and similarity calculation from the model?

[fengyuentau]

Hello, TensorRT is not supported by OpenCV. For helpful and faster responses, you should go to https://www.nvidia.com/en-us/forums/.

[Mo-Sam-Mo]

Hi,
I’d like to help with this issue. Could you provide more context or guidance on where to start?

[sayyid-abolfazl]

Hi, I’d like to help with this issue. Could you provide more context or guidance on where to start?

Hello, Thank you for your support.

To start, please run my program, which is based on the Tensor RT library
https://github.com/sayyid-abolfazl/sface_trt

to use the onnx model in Tensor RT, you need to check the input and output of the network and then implement it in Tensor RT.

The problem is that in the onnx model, in addition to the image, it receives 15 decimal numbers that include the coordinates of the face box and landmarks and Confidence, but in the network input there are only the dimensions of the network input, which are 112 * 112.

How do I define 15 decimal numbers in Tensor RT? And get the correct output? I tried several methods, but I did not get the correct output.