Quantization with tflite : Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(int8))

I am quantizing my yolov5 model with tflite using the following code :

import tensorflow as tf
saved_model_dir ='path2_saved_model'
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.inference_input_type = tf.int8 # or tf.uint8
converter.inference_output_type = tf.int8 # or tf.uint8
tflite_quant_model = converter.convert()

however when I try to run detect, it expects the input image to be int8, how can I solve this issue, thank you in advance!

Start by reproducing the TFLite conversion with the shown TensorFlow code and then run detect while comparing the converted model's expected input type with the image data supplied. No repository file or test is named; the issue is done when the quantized model and detect path accept compatible input data without the reported type error.