import numpy as np
import tensorflow as tf
import os 
import glob
import argparse
import random
import importlib
#from resnet import ResNet
import matplotlib.pyplot as plt
from pysim import config
importlib.reload(config)
import glob
import cv2
import shutil
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split

1. Gewünschte Struktur-Verzeichniss (Varinate 1)

flow_from_directory - Struktur

  -  TRAIN: data/train/class1/jpg,  data/train/class2/jpg
  -  VAL: data/val/class1/jpg,  data/val/class2/jpg
  -  TEST: data/test/class1/jpg,  data/test/class2/jpg

In diesem Datensazt sind die Daten schon in Train, Val, Test verteilt

for split in (config.TRAIN, config.VAL, config.TEST):
    print("[INFO] processing '{} split'...".format(split))
    imagePaths = glob.glob(os.path.sep.join([config.ORIG_INPUT_DATASET, split, '*']))
    for imagePath in imagePaths:
        filename =  imagePath.split(os.path.sep)[-1]
        label = config.CLASSES[int(filename.split("_")[0])]
        #new directory path
        newPath = os.path.sep.join([config.BASE_PATH, split, label])
        # if directory doesn't exist than creat new
        if not os.path.exists(newPath):
            os.makedirs(newPath)
        newPathFile = os.path.sep.join([newPath, filename])
        shutil.copy2(imagePath, newPath)

2. Gewünschte Struktur-Verzeichniss (Varinate 2)

filesPaths = glob.glob(os.path.sep.join([config.BASE_PATH, "*", "*"]))
data  = []
labels = []
for imagePath in filesPaths:
    label  = imagePath.split(os.path.sep)[-2]
    image  = cv2.imread(imagePath)
    image  = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    image  = cv2.resize(image, (128, 128))
    data.append(image)
    labels.append(label)

Referenzen:

Adrian Rosebrock, OpenCV Face Recognition, PyImageSearch, https://www.pyimagesearch.com/, accessed on 3 January, 2021> www:https://www.pyimagesearch.com/2019/05/20/transfer-learning-with-keras-and-deep-learning/