Crashes when executing model quantification on Deeplabv3

[EzioQR]

Describe the issue

I want to perform INT8 precision inference on the Deeplabv3 model on the CPU. I first quantified the model, but during execution, I threw NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for ConvInteger(10) node with name '/resnet/conv1/Conv_quant' Error. The model file is shown in the attachment (https://drive.google.com/file/d/10QhV6_lqoD4nnGx3a4HJV-zA7bQJ86E5/view?usp=drive_link).

To reproduce

import onnxruntime as ort
from onnxruntime.quantization import quantize_dynamic, QuantType
import numpy as np

session = ort.InferenceSession("./deeplabv3.onnx",
providers=["CPUExecutionProvider"],graph_optimization_level=ort.GraphOptimizationLevel.ORT_ENABLE_EXTENDED)

quantized_model = quantize_dynamic("./deeplabv3.onnx", "./deeplabv3_quantized.onnx", weight_type=QuantType.QInt8)

input_data = np.random.rand(2, 3, 513, 513).astype(np.float32)
input_data_int8 = input_data.astype(np.int8)
inputs = {session.get_inputs()[0].name: input_data}
outputs = session.run(["infer_output"], inputs)

session_int8 = ort.InferenceSession("../deeplabv3_quantized.onnx", providers=["CPUExecutionProvider"])

outputs_int8 = session_int8.run(["infer_output"], quantized_model)

Expected behavior
Execute normally.

Urgency

No response

Platform

Linux

OS Version

(Linux Ubuntu 20.04)

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

1.17.0)

ONNX Runtime API

Python

Architecture

X64

Execution Provider

Default CPU

Execution Provider Library Version

No response