Ich versuche derzeit, das Beispiel here mit einem Datensatz zu verfolgen, den ich selbst erstellt habe. Das Backend läuft mit Theano. Die Verzeichnisstruktur ist genau das gleiche:Keras imageGenerator Ausnahme: Die Ausgabe des Generators sollte ein Tupel (x, y, sample_weight) oder (x, y) sein. Gefunden: Keine
image_sets/
dogs/
dog001.jpg
dog002.jpg
...
cats/
cat001.jpg
cat002.jpg
...
validation/
dogs/
dog001.jpg
dog002.jpg
...
cats/
cat001.jpg
Hier ist mein Code für das keras Faltungs neuronales Netz ist.
img_width, img_height = 150, 150
img_width, img_height = 150, 150
train_data_dir = './image_sets'
validation_data_dir = './validation'
nb_train_samples = 267
print nb_train_samples
#number of validation images I have
nb_validation_samples = 2002
print nb_validation_samples
nb_epoch = 50
# from keras import backend as K
# K.set_image_dim_ordering('th')
model = Sequential()
model.add(Convolution2D(32, 3, 3, input_shape=(3,img_width, img_height)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=32,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=32,
class_mode='binary')
model.fit_generator(
train_generator,
samples_per_epoch=nb_train_samples,
nb_epoch=nb_epoch,
validation_data=validation_generator,
nb_val_samples=nb_validation_samples)
model.save_weights('first_try.h5')