tensorflow.python.framework.errors_impl.InvalidArgumentError

On the terminal window, it runs fine when an image is passed to tensorflow for image object recognition using:

python run.py http://image_url.jpg

However, with JSON data that contains stream of imageURL, it failed with the following main error:

InvalidArgumentError: Invalid JPEG data or crop window, data size 15022
 [[Node: DecodeJpeg = DecodeJpeg[acceptable_fraction=1, channels=3, dct_method="", fancy_upscaling=true, ratio=1, try_recover_truncated=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_DecodeJpeg/contents_0_0)]]
Caused by op u'DecodeJpeg'

Another error encountered:

ValueError: GraphDef cannot be larger than 2GB.

Below is my tensorflow source code as a function(again it runs with single ImageUrl passed as parameter):

import tensorflow as tf
import sys
import os
import urllib2

def tensorflow_pred(imageUrl):

    #suppress TF log-info messages - remove to display TF logs 
    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

    response = urllib2.urlopen(imageUrl)

    image_data = response.read()

    # Loads label file, strips off carriage return
    label_lines = [line.rstrip() for line 
                    in tf.gfile.GFile("./retrained_labels.txt")]

    # Unpersists graph from file
    with tf.gfile.FastGFile("./retrained_graph.pb", 'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        _ = tf.import_graph_def(graph_def, name='')

    with tf.Session() as sess:
        # Feed the image_data as input to the graph and get first prediction
        softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

        predictions = sess.run(softmax_tensor, \
                {'DecodeJpeg/contents:0': image_data})

        # Sort to show labels of first prediction in order of confidence
        top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

        for node_id in top_k:
            classification = label_lines[node_id]
            score = predictions[0][node_id]
            if (score >=0.5):
                return ('%s (score = %.5f)' % (classification, score))