Opencv : 4.6.0
OS: Ubantu 20.04
Python 3.9.12

Description : I have a TFlite (Efficienet_lite0) object detection model which I converted to onnx. I want to run this model with NPU as a backend. But I am not able to load a model which giving me the following error.
Model

Step:

import cv2
model = cv2.dnn.readNet("model.onnx")

Error:
[ERROR:0@1.598] global /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp (1018) handleNode DNN/ONNX: ERROR during processing node with 3 inputs and 1 outputs: [DequantizeLinear]:(onnx_node!stem/conv2d/Conv2D;stem/conv2d/Conv2D_dequant) from domain='ai.onnx'

model = cv2.dnn.readNet("model.onnx")

error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:1040: error: (-2:Unspecified error) in function 'handleNode'

Node [DequantizeLinear@ai.onnx]:(onnx_node!stem/conv2d/Conv2D;stem/conv2d/Conv2D_dequant) parse error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/int8layers/quantization_utils.cpp:103: error: (-215:Assertion failed) inputs.size() == 1 in function 'getMemoryShapes'

Thanks in advance