test_datagen = ImageDataGenerator(rescale=1./255)
train = train_datagen.flow_from_directory(
'Dataset Path', # Directory Name
target_size=(256, 256), # Size of the image expected in our mode
batch_size=32, # Size of the batch after which batch will be updated
class_mode='binary') # Show the class mode of the result
test = test_datagen.flow_from_directory(
'Dataset Path', # Directory Name
target_size=(256, 256), # Image of our test set
batch_size=32, # Size of the batch after which batch will be updated
class_mode='binary') # Show the class mode of the result
model.fit_generator(
train,
steps_per_epoch=2000, # Number of images in our train dataset
epochs=25, # Number of epoch we need
validation_data= test, # Test set
validation_steps=800) # Number of images in our test dataset
""" To improve the model you can
Add a convolution Layer
Increase the target size in train and test dataset so that more information of the pixel pattern is captured
"""
classifier.add(Dense(output_dim=1, activation='sigmoid'))
#compliling
classifier.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
from keras.preprosessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
training_set = train_datagen.flow_from_directory('dataset/training_set',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
test_set = test_datagen.flow_from_directory('data/validation',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
classifier.fit_generator(training_set,
steps_per_epoch=8000,
epochs=25,
validation_data=test_set,
validation_steps=2000)
