Running an Tensorflow graph in OpenCV gives wrong results

So I am trying to run an image through a frozen graph of a tensorflow model in OpenCV. Here is my OpenCV code. I have an image of Size (250, 250):

#include <stdio.h>
#include <opencv2/opencv.hpp>
#include <opencv2/dnn.hpp>
#include <string>
#include <vector>
#include <dirent.h>
#include <string>

using namespace cv;
using namespace std;

int main(int argc, char** argv )
{
    Mat image = imread("0_1_125_131_203.png", CV_8UC1);
    Mat blob =  cv::dnn::blobFromImage(image);
    cv::dnn::Net net = cv::dnn::readNetFromTensorflow("output_graph.pb");
    net.setInput(blob, "input_node");
    Mat result = net.forward("Dense4/output_node");
    cout << result << endl;
    return 0;
}

Here is the tensorflow code:

import cv2
import numpy as np
import tensorflow as tf
import argparse 

def load_graph(frozen_graph_filename):
    with tf.gfile.GFile(frozen_graph_filename, "rb") as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())

    with tf.Graph().as_default() as graph:
        tf.import_graph_def(graph_def, name="prefix")
    return graph

if __name__ == '__main__':
    image = cv2.imread("0_1_125_131_203.png", cv2.CV_8UC1)
    a = np.asarray(image[:,:])
    a = np.reshape(a, [1,250,250,1])
    parser = argparse.ArgumentParser()
    parser.add_argument("--frozen_model_filename", default="output_graph.pb", type=str, help="Frozen model file to import")
    args = parser.parse_args()

    graph = load_graph(args.frozen_model_filename)

    x = graph.get_tensor_by_name('prefix/input_node:0')
    y = graph.get_tensor_by_name('prefix/Dense4/fully_connected6/BiasAdd:0')

    # We launch a Session
    with tf.Session(graph=graph) as sess:
        y_out = sess.run( y, feed_dict={
            x: a
        })
        print("Result", y_out)

The only difference between the two is that OpenCV creates a blob of shape ( 1, 1, 250, 250 ) from the image, whereas I pass the image as reshaped np array of shape ( 1, 250, 250, 1 ) in tensorflow. I get the correct answer in tensorflow whereas I get a random answer in through OpenCV. Now I want to know where am I going wrong ??. Or if anyone can suggest some other C++ api to port a tensorflow frozen graph.