NMZivkovic

class DataSetCreator(object):
    def __init__(self, batch_size, image_height, image_width, dataset):
        self.batch_size = batch_size
        self.image_height = image_height
        self.image_width = image_width
        self.dataset = dataset
        
    def _get_class(self, path):
        pat_splited = tf.strings.split(path, os.path.sep)
        return pat_splited[-2] == CLASS_NAMES

NMZivkovic

list_dataset = tf.data.Dataset.list_files(str(data_directory/'*/*'))

NMZivkovic

image_batch, label_batch = next(dataset)

NMZivkovic

from tf.keras.preprocessing.image import ImageDataGenerator

image_generator = ImageDataGenerator(rescale=1./255)

dataset = image_generator.flow_from_directory(directory=str(data_directory),
                                                     batch_size=32,
                                                     shuffle=True,
                                                     target_size=(300, 500),
                                                     classes = list(CLASSES))

NMZivkovic

data_directory = pathlib.WindowsPath("./LEGO brick images/train")
CLASSES = np.array([item.name for item in data_directory.glob('*') if item.name != "LICENSE.txt"])

NMZivkovic

import pandas
import os
import numpy as np
import pathlib
import IPython.display as display
import matplotlib.pyplot as plt
from PIL import Image

import tensorflow as tf

NMZivkovic

import scrapy
from ..items import ImageItem

class ImgSpider(scrapy.spiders.Spider):
    name = "img_spider"
    start_urls = ["https://rubikscode.net/"]

    def parse(self, response):
        image = ImageItem()
        img_urls = []

NMZivkovic

import scrapy

class ImageItem(scrapy.Item):
    images = scrapy.Field()
    image_urls = scrapy.Field()

NMZivkovic

ITEM_PIPELINES = {'scrapy.pipelines.images.ImagesPipeline': 1}
IMAGES_STORE = 'C:/images/scrapy'

NMZivkovic

for i in range(0, len(image_info)):
    download_image(image_info[i])