У меня две одинаковые модели с одинаковыми параметрами. Оба они обучены на наборе данных MNIST. Первый обучается с использованием model.fit (), а второй обучается с использованием model.train_on_batch (). Вторая модель дает меньшую точность. Я хочу знать, что может быть причиной этого и как это исправить?
Подготовка данных:
batch_size = 150
num_classes = 10
epochs = 12
# input image dimensions
img_rows, img_cols = 28, 28
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
МОДЕЛЬ 1:
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(Conv2D(256, (3, 3), activation='relu'))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
ТОЧНОСТЬ МОДЕЛИ 1:
Потери при испытаниях: 0,023489486496470636 Точность испытаний: 0,9924
МОДЕЛЬ 2:
model2 = Sequential()
model2.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model2.add(Conv2D(64, (3, 3), activation='relu'))
model2.add(Conv2D(128, (3, 3), activation='relu'))
model2.add(Conv2D(256, (3, 3), activation='relu'))
model2.add(Conv2D(128, (3, 3), activation='relu'))
model2.add(Conv2D(64, (3, 3), activation='relu'))
model2.add(Conv2D(64, (3, 3), activation='relu'))
model2.add(Conv2D(32, (3, 3), activation='relu'))
model2.add(MaxPooling2D(pool_size=(2, 2)))
model2.add(Dropout(0.25))
model2.add(Flatten())
model2.add(Dense(128, activation='relu'))
model2.add(Dropout(0.5))
model2.add(Dense(num_classes, activation='softmax'))
model2.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
batch_size2 = 150
epochs2 = 12
step_epoch = x_train.shape[0] // batch_size2
def next_batch_train(i):
return x_train[i:i+batch_size2,:,:,:], y_train[i:i+batch_size2,:]
iter_num = 0
epoch_num = 0
model_outputs = []
loss_history = []
while epoch_num < epochs2:
while iter_num < step_epoch:
x,y = next_batch_train(iter_num)
loss_history += model2.train_on_batch(x,y)
iter_num += 1
print("EPOCH {} FINISHED".format(epoch_num + 1))
epoch_num += 1
iter_num = 0 # reset counter
score = model2.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
ТОЧНОСТЬ МОДЕЛИ 2:
Потери при испытаниях: 0,5577236003954947 Точность испытаний: 0,9387