NMZivkovic

def download_image(image):
    response = requests.get(image[0], stream=True)
    realname = ''.join(e for e in image[1] if e.isalnum())
    
    file = open("C://images//bs//{}.jpg".format(realname), 'wb')
    
    response.raw.decode_content = True
    shutil.copyfileobj(response.raw, file)
    del response

NMZivkovic

image_info = []

for a in aas:
    image_tag = a.findChildren("img")
    image_info.append((image_tag[0]["src"], image_tag[0]["alt"]))

NMZivkovic

url = "https://rubikscode.net/"
response = requests.get(url)

soup = BeautifulSoup(response.text, "html.parser")

aas = soup.find_all("a", class_='entry-featured-image-url')

NMZivkovic

from bs4 import BeautifulSoup

import requests
import urllib.request
import shutil

NMZivkovic

loss, accuracy = resnet.evaluate(data_loader.test_batches, steps = validation_steps)

print("--------ResNet---------")
print("Loss: {:.2f}".format(loss))
print("Accuracy: {:.2f}".format(accuracy))
print("---------------------------")

NMZivkovic

history = resnet.fit(data_loader.train_batches,
                    epochs=10,
                    validation_data=data_loader.validation_batches)

NMZivkovic

base_learning_rate = 0.0001

resnet = Wrapper(resnet_base)
resnet.compile(optimizer=tf.keras.optimizers.RMSprop(lr=base_learning_rate),
              loss='binary_crossentropy',
              metrics=['accuracy'])

NMZivkovic

resnet_base = tf.keras.applications.ResNet101V2(input_shape=IMG_SHAPE, include_top=False, weights='imagenet')

resnet_base.trainable = True

from_layer = 100

for layer in resnet_base.layers[:from_layer]:
    layer.trainable =  False

NMZivkovic

loss1, accuracy1 = vgg16.evaluate(data_loader.test_batches, steps = 20)
loss2, accuracy2 = googlenet.evaluate(data_loader.test_batches, steps = 20)
loss3, accuracy3 = resnet.evaluate(data_loader.test_batches, steps = 20)

print("--------VGG16---------")
print("Loss: {:.2f}".format(loss1))
print("Accuracy: {:.2f}".format(accuracy1))
print("---------------------------")

print("--------GoogLeNet---------")

NMZivkovic

history = resnet.fit(data_loader.train_batches,
                    epochs=10,
                    validation_data=data_loader.validation_batches)