Sai Ajay ajaymuktha

## train_generator.py
train_generator = train_datagen.flow_from_directory(
        'dataset/train',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

## traindata_gen.py
train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

## libraries.py
import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator

## evaluate.py
test_loss, test_accuracy = model.evaluate(X_test, y_test)

## train.py
model.fit(X_train, y_train, epochs =5)

## compile.py
model.compile(optimizer = 'adam', loss = 'sparse_categorical_crossentropy', metrics = ['sparse_categorical_accuracy'])

## layer2.py
model.add(tf.keras.layers.Dense(units = 10, activation = 'softmax'))

## dropout.py
model.add(tf.keras.layers.Dropout(0.2))

## Layer.py
model.add(tf.keras.layers.Dense(units = 128, activation = 'relu', input_shape = (784,)))

## Sequential.py
model = tf.keras.models.Sequential()
	train_generator = train_datagen.flow_from_directory(
	'dataset/train',
	target_size=(150, 150),
	batch_size=32,
	class_mode='binary')
	train_datagen = ImageDataGenerator(
	rescale=1./255,
	shear_range=0.2,
	zoom_range=0.2,
	horizontal_flip=True)
	import tensorflow as tf
	from keras.preprocessing.image import ImageDataGenerator