resnet-tf2.py

import tensorflow as tf
import os
import time

import numpy as np
import matplotlib.pyplot as plt

from tensorflow import keras
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions

def run():
    MAIN_PATH = "./"
    import urllib
    from pathlib import Path
    Path(MAIN_PATH).mkdir(parents=True, exist_ok=True)

    opener = urllib.request.URLopener()
    opener.addheader('User-Agent', 'whatever')

    opener.retrieve(
        "https://d17fnq9dkz9hgj.cloudfront.net/breed-uploads/2018/08/siberian-husky-detail.jpg?bust=1535566590&width=630", "{}/img0.JPG".format(MAIN_PATH))
    opener.retrieve(
        "https://www.hakaimagazine.com/wp-content/uploads/header-gulf-birds.jpg", "{}/img1.JPG".format(MAIN_PATH))
    opener.retrieve("https://www.artis.nl/media/filer_public_thumbnails/filer_public/00/f1/00f1b6db-fbed-4fef-9ab0-84e944ff11f8/chimpansee_amber_r_1920x1080.jpg__1920x1080_q85_subject_location-923%2C365_subsampling-2.jpg", "{}/img2.JPG".format(MAIN_PATH))
    opener.retrieve(
        "https://www.familyhandyman.com/wp-content/uploads/2018/09/How-to-Avoid-Snakes-Slithering-Up-Your-Toilet-shutterstock_780480850.jpg", "{}/img3.JPG".format(MAIN_PATH))


    model = tf.keras.models.load_model('resnet50_saved_model')
    img_path = '{}/img0.JPG'.format(MAIN_PATH)  # Siberian_husky
    img = image.load_img(img_path, target_size=(224, 224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)

    preds = model.predict(x)
    # decode the results into a list of tuples (class, description, probability)
    # (one such list for each sample in the batch)
    print('{} - Predicted: {}'.format(img_path,
                                      decode_predictions(preds, top=3)[0]))
    plt.subplot(2, 2, 1)
    plt.imshow(img)
    plt.axis('off')
    plt.title(decode_predictions(preds, top=3)[0][0][1])
    batch_size = 8
    batched_input = np.zeros((batch_size, 224, 224, 3), dtype=np.float32)

    for i in range(batch_size):
        img_path = '{}/img%d.JPG'.format(MAIN_PATH) % (i % 4)
        img = image.load_img(img_path, target_size=(224, 224))
        x = image.img_to_array(img)
        x = np.expand_dims(x, axis=0)
        x = preprocess_input(x)
        batched_input[i, :] = x
    batched_input = tf.constant(batched_input)
    print('batched_input shape: ', batched_input.shape)
    # Benchmarking throughput
    N_warmup_run = 50
    N_run = 1000
    elapsed_time = []

    for i in range(N_warmup_run):
        preds = model.predict(batched_input)

    for i in range(N_run):
        start_time = time.time()
        preds = model.predict(batched_input)
        end_time = time.time()
        elapsed_time = np.append(elapsed_time, end_time - start_time)
        if i % 50 == 0:
            print('Step {}: {:4.1f}ms'.format(
                i, (elapsed_time[-50:].mean()) * 1000))

    print('Throughput: {:.0f} images/s'.format(N_run *
                                               batch_size / elapsed_time.sum()))

if __name__ == "__main__":
    run()