Opencv with pre-trained model

Question

I'm getting this error: cv2.error:

OpenCV(4.6.0) d:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layer_internals.hpp:110: error: (-2:Unspecified error) Can't create layer "NHWC_output" of type "DepthToSpace" in function 'cv::dnn::dnn4_v20220524::detail::LayerData::getLayerInstance'

when trying to read and use the pre trained model (.pb).

here's the code:

import cv2
import numpy as np
import os

esrgan = cv2.dnn.readNetFromTensorflow('./models/EDSR_x4.pb')

def upscale_image(image):
    blob = cv2.dnn.blobFromImage(image, scalefactor=1/255.0)
    esrgan.setInput(blob)
    result = esrgan.forward()
    result = np.clip(result[0] * 255, 0, 255).astype(np.uint8)
    return result