Testing a Random Image against a Python Keras/Tensorflow CNN

Question

I've created and CNN and I am trying to figure out how to test a random image against it. I am utilizing Keras and Tensorflow. Lets assume I wanted to test the image found here: https://i.ytimg.com/vi/7I8OeQs7cQA/maxresdefault.jpg.

How would I save the model, load it then test this image against it? Here is some example code I found online that demonstrates what I mean: https://meta.stackexchange.com/questions/144665/hide-email-address-from-my-profile

Any help is much appreciated, thanks!

import os
import cv2
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import display, Image

from keras.models import Sequential, load_model
from keras.layers import Conv2D, Flatten, MaxPooling2D, Input
from keras.preprocessing.image import ImageDataGenerator

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import models, layers

X = []
y = []

from sklearn.model_selection import train_test_split

labels = os.listdir(r'C:/Users/zF1bo/Desktop/natural_images')
labels



for label in labels:
    path = r'C:/Users/zF1bo/Desktop/natural_images/{}/'.format(label)
    img_data = os.listdir(path)
    
    for image in img_data:
        a = cv2.imread( path + image)
        a = cv2.resize(a, (64, 64))
        X.append(np.array(a.astype('float32')) / 255)
        y.append(label)


buckets = []
for i in y:
    if i == 'airplane':
        buckets.append(0)
    elif i == 'car':
        buckets.append(1)
    elif i == 'cat':
        buckets.append(2)
    elif i == 'dog':
        buckets.append(3)
    elif i == 'flower':
        buckets.append(4)
    elif i == 'fruit':
        buckets.append(5)
    elif i == 'motorbike':
        buckets.append(6)
    elif i == 'person':
        buckets.append(7)


y = buckets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, \
        random_state = 0)


model = models.Sequential()
model.add(layers.Conv2D(filters=32, kernel_size=(5,5), activation='relu', input_shape=(64,64,3)))
model.add(layers.MaxPool2D(pool_size=(2, 2)))
model.add(layers.Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
model.add(layers.MaxPool2D(pool_size=(2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(8, activation='softmax'))

model.compile(optimizer='adam', loss = 'sparse_categorical_crossentropy',metrics=['accuracy'])

y_train = np.array(y_train)

model.fit(X_train, y_train, batch_size=(256), epochs=25)

pred = model.predict(X_test)

diff = []
for i in pred:
    diff.append(np.argmax(i))

from sklearn.metrics import accuracy_score

accuracy_score(diff,y_test)

Answer 1

Step 1: Save the model

model.save('model.h5')

Step 2: Load the model

loaded_model = tensorflow.keras.models.load_model('model.h5')

Step 3: Download the image via requests library(answer is taken from: Downloading a picture via urllib and python):

import urllib.request 
urllib.request.urlretrieve(url, filename)

Otherwise you can apply the same steps like in the first picture you posted. Do not forget to expand_dims()

Answer 2

you can save your model using mode.save('path to save location') To input an image you should read it, perform any pre-processing that you did to the training images then use model.predict as shown in the code below.

import tensorflow as tf
from tensorflow import keras
model = keras.models.load_model('path/to/location') # loads the saved model
pred_img =r'path to the img'
img=cv2.imread (pred_img)
img=img/255 # rescale the image
print(img.shape)
img=cv2.resize(img, (64,64)) # resize to same size used in training
print (img.shape)
img=np.expand_dims(img, axis=0)
print (img.shape)
pred=model.predict(img)
print (pred)  # will be a list of 8 elements select the element in the list with the highest probability
index=np.argmax(pred)) # this will be the index of the class predicted
class_name=buckets[index] # this will be the name of the class predicted
print (class_name)

NOTE if your read in the training images with cv2 remember the order is bgr not rgb. The model was trained on bgr images. When you read in the image to predict it must be bgr also.