Created
March 21, 2018 08:04
-
-
Save sam-thecoder/4da97642919253085b52c3a82f87b558 to your computer and use it in GitHub Desktop.
training model
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from keras.preprocessing.image import ImageDataGenerator | |
from keras.models import Sequential | |
from keras.layers import Conv2D, MaxPooling2D | |
from keras.layers import Activation, Dropout, Flatten, Dense | |
from keras import backend as K | |
from keras.callbacks import EarlyStopping | |
from keras.callbacks import ModelCheckpoint | |
# dimensions of our images. | |
img_width, img_height = 250, 250 | |
train_data_dir = 'training_images' | |
validation_data_dir = 'validation_images' | |
nb_train_samples = 10000 | |
nb_validation_samples = 800 | |
epochs = 50 | |
batch_size = 10 | |
if K.image_data_format() == 'channels_first': | |
input_shape = (1, img_width, img_height) | |
else: | |
input_shape = (img_width, img_height, 1) | |
model = Sequential() | |
model.add(Conv2D(128, (3, 3), input_shape=input_shape)) | |
model.add(Activation('relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Conv2D(128, (3, 3))) | |
model.add(Activation('relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Conv2D(64, (3, 3))) | |
model.add(Activation('relu')) | |
model.add(MaxPooling2D(pool_size=(2, 2))) | |
model.add(Flatten()) | |
model.add(Dense(1000)) | |
model.add(Activation('relu')) | |
model.add(Dense(14951, activation="softmax")) | |
monitor = EarlyStopping(monitor='val_loss', min_delta=1e-3, patience=5, verbose=0, mode='auto') | |
checkpointer = ModelCheckpoint(filepath="best_weights.hdf5", verbose=0, save_best_only=True) # save best model | |
model.compile(loss='categorical_crossentropy', optimizer='rmsprop') | |
# this is the augmentation configuration we will use for training | |
train_datagen = ImageDataGenerator( | |
rescale=1. / 255, | |
shear_range=0.2, | |
zoom_range=0.2, | |
horizontal_flip=True) | |
# this is the augmentation configuration we will use for testing: | |
# only rescaling | |
test_datagen = ImageDataGenerator(rescale=1. / 255) | |
train_generator = train_datagen.flow_from_directory( | |
train_data_dir, | |
target_size=(img_width, img_height), | |
color_mode='grayscale', | |
batch_size=batch_size, | |
class_mode='categorical', | |
shuffle=True) | |
validation_generator = test_datagen.flow_from_directory( | |
validation_data_dir, | |
target_size=(img_width, img_height), | |
batch_size=batch_size, | |
color_mode='grayscale', | |
class_mode='categorical', | |
shuffle=True) | |
from PIL import ImageFile | |
ImageFile.LOAD_TRUNCATED_IMAGES = True | |
model.fit_generator( | |
train_generator, | |
steps_per_epoch=nb_train_samples // batch_size, | |
epochs=epochs, | |
validation_steps=nb_validation_samples // batch_size, | |
callbacks=[monitor,checkpointer], | |
validation_data=validation_generator) | |
model.load_weights('best_weights.hdf5') # load weights from best model | |
model.save('grey_model.h5') | |
scoreSeg = model.evaluate_generator(validation_generator,800) | |
print("Accuracy = ",scoreSeg[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment