Sai Ajay ajaymuktha

## compile.py
cnn.compile(optmizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

## output.py
cnn.add(tf.keras.layers.Dense(units = 1, activation = 'sigmoid'))

## Dense.py
cnn.add(tf.keras.layers.Dense(units = 128, activation = 'relu'))

## Flatten.py
cnn.add(tf.keras.layers.Flatten())

## secondConv.py
cnn.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = 3, activation_function = 'relu'))
cnn.add(tf.keras.layers.MaxPool2D(pool_size = 2, strides = 2)

## maxpooling.py
cnn.add(tf.keras.layers.MaxPool2D(pool_size = 2, strides = 2)

## Convolution.py
cnn.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = 3, activation_function = 'relu', input_shape = (64,64,3))

## Sequential.py
cnn = tf.keras.models.Sequential()

## testset.py
test_set = test_datagen.flow_from_directory(
        'data/validation',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

## testgen.py
test_datagen = ImageDataGenerator(rescale=1./255)
	cnn.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = 3, activation_function = 'relu'))
	cnn.add(tf.keras.layers.MaxPool2D(pool_size = 2, strides = 2)
	test_set = test_datagen.flow_from_directory(
	'data/validation',
	target_size=(150, 150),
	batch_size=32,
	class_mode='binary')