app.py

import os
from keras.models import Model
from tensorflow.keras.optimizers import Adam
from keras.applications.vgg16 import VGG16, preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint, EarlyStopping
from keras.layers import Dense, Dropout, Flatten
from pathlib import Path
import numpy as np



BATCH_SIZE = 64

train_generator = ImageDataGenerator(rotation_range=90, 
                                     brightness_range=[0.1, 0.7],
                                     width_shift_range=0.5, 
                                     height_shift_range=0.5,
                                     horizontal_flip=True, 
                                     vertical_flip=True,
                                     validation_split=0.15,
                                     preprocessing_function=preprocess_input) # VGG16 preprocessing

test_generator = ImageDataGenerator(preprocessing_function=preprocess_input) # VGG16 preprocessing





train_data_dir = '/kaggle/input/pic-a-plant2/DBa4/‏‏DBa/train'
test_data_dir = '/kaggle/input/pic-a-plant2/DBa4/‏‏DBa/test'

class_subset = sorted(os.listdir(train_data_dir))[:] # Using only the first 10 classes

traingen = train_generator.flow_from_directory(train_data_dir,
                                               target_size=(150, 150),
                                               class_mode='categorical',
                                               classes=class_subset,
                                               subset='training',
                                               batch_size=BATCH_SIZE, 
                                               shuffle=True,
                                               seed=42)

validgen = train_generator.flow_from_directory(train_data_dir,
                                               target_size=(150, 150),
                                               class_mode='categorical',
                                               classes=class_subset,
                                               subset='validation',
                                               batch_size=BATCH_SIZE,
                                               shuffle=True,
                                               seed=42)

testgen = test_generator.flow_from_directory(test_data_dir,
                                             target_size=(150, 150),
                                             class_mode=None,
                                             classes=class_subset,
                                             batch_size=1,
                                             shuffle=False,
                                             seed=42)