As seen here: https://mlis.fun/leveraging-transfer-learning-to-build-a-tensor-flow-image-classifier-in-less-than-10-minutes

tensorflow_image_classification_predict.py

import tensorflow as tf
import sys

image_path = sys.argv[1]
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
label_lines = [line.rstrip() for line in tf.gfile.GFile('labels.txt')]

with tf.gfile.FastGFile('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 session:
    softmax_tensor = session.graph.get_tensor_by_name('final_result:0')
    predictions = session.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})

predictions_by_confidence = predictions[0].argsort()[-len(predictions[0]):][::-1]

for node_id in predictions_by_confidence:
    human_readable = label_lines[node_id]
    score = predictions[0][node_id]
    print('%s (score = %5f)' % (human_readable, score))