舊版本中：
from keras.layers import merge
merge6 = merge([layer1,layer2], mode = 'concat', concat_axis = 3)
新版本中：
from keras.layers.merge import concatenate
merge = concatenate([layer1, layer2], axis=3)
補充知識：keras輸入數據的方法：model.fit和model.fit_generator
1.第一種，普通的不用數據增強的
from keras.datasets import mnist,cifar10，cifar100 (X_train, y_train), (X_valid, Y_valid) = cifar10.load_data() model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, shuffle=True, verbose=1, validation_data=(X_valid, Y_valid), )
2.第二種，帶數據增強的 ImageDataGenerator，可以旋轉角度、平移等操作。
from keras.preprocessing.image import ImageDataGenerator (trainX, trainY), (testX, testY) = cifar100.load_data() trainX = trainX.astype('float32') testX = testX.astype('float32') trainX /= 255. testX /= 255. Y_train = np_utils.to_categorical(trainY, nb_classes) Y_test = np_utils.to_categorical(testY, nb_classes) generator = ImageDataGenerator(rotation_range=15, width_shift_range=5./32, height_shift_range=5./32) generator.fit(trainX, seed=0) model.fit_generator(generator.flow(trainX, Y_train, batch_size=batch_size), steps_per_epoch=len(trainX) // batch_size, epochs=nb_epoch, callbacks=callbacks, validation_data=(testX, Y_test), validation_steps=testX.shape[0] // batch_size, verbose=1)
[zmcjlove ] 關於keras中keras.layers.merge的用法說明已經有328次圍觀