def scheduler(epoch):
    if epoch <= 100:
       return 0.1
    if epoch <= 180:
       return 0.01
    return 0.0005

定義一個DenseNet模型（github搬運工上線！）：

def densenet(img_input,classes_num):

    def bn_relu(x):
        x = BatchNormalization()(x)
        x = Activation("relu")(x)
        return x

    def bottleneck(x):
        channels = growth_rate * 4
        x = bn_relu(x)
        x = Conv2D(channels,kernel_size=(1,1),strides=(1,1),padding="same",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay),use_bias=False)(x)
        x = bn_relu(x)
        x = Conv2D(growth_rate,kernel_size=(3,3),strides=(1,1),padding="same",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay),use_bias=False)(x)
        return x

    def single(x):
        x = bn_relu(x)
        x = Conv2D(growth_rate,kernel_size=(3,3),strides=(1,1),padding="same",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay),use_bias=False)(x)
        return x

    def transition(x, inchannels):
        x = bn_relu(x)
        x = Conv2D(int(inchannels * compression),kernel_size=(1,1),strides=(1,1),padding="same",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay),use_bias=False)(x)
        x = AveragePooling2D((2,2), strides=(2, 2))(x)
        return x

    def dense_block(x,blocks,nchannels):
        concat = x
        for i in range(blocks):
            x = bottleneck(concat)
            concat = concatenate([x,concat], axis=-1)
            nchannels += growth_rate
        return concat, nchannels

    def dense_layer(x):
        return Dense(classes_num,activation="softmax",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay))(x)


    # nblocks = (depth - 4) // 3 
    nblocks = (depth - 4) // 6 
    nchannels = growth_rate * 2

    x = Conv2D(nchannels,kernel_size=(3,3),strides=(1,1),padding="same",kernel_initializer=he_normal(),kernel_regularizer=regularizers.l2(weight_decay),use_bias=False)(img_input)

    x, nchannels = dense_block(x,nblocks,nchannels)
    x = transition(x,nchannels)
    x, nchannels = dense_block(x,nblocks,nchannels)
    x = transition(x,nchannels)
    x, nchannels = dense_block(x,nblocks,nchannels)
    x = bn_relu(x)
    x = GlobalAveragePooling2D()(x)
    x = dense_layer(x)
    return x

載入數(shù)據(jù)集，并對標簽進行矩陣設(shè)置，改變數(shù)據(jù)集數(shù)據(jù)類型：

(x_train, y_train), (x_test, y_test) = cifar10.load_data()
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test  = keras.utils.to_categorical(y_test, num_classes)
x_train = x_train.astype("float32")
x_test  = x_test.astype("float32")

將數(shù)據(jù)集歸一化，方便訓(xùn)練：

for i in range(3):
    x_train[:,:,:,i] = (x_train[:,:,:,i] - mean[i]) / std[i]
    x_test[:,:,:,i] = (x_test[:,:,:,i] - mean[i]) / std[i]

定義模型并打印簡圖，shell中打印的模型圖太長了，就不貼了，長得一逼，需要看的話直接在shell中print summary就可以：

img_input = Input(shape=(img_rows,img_cols,img_channels))
output    = densenet(img_input,num_classes)
model     = Model(img_input, output)
# model.load_weights("ckpt.h5")
print(model.summary())
plot(model, to_file="cnn_model.png",show_shapes=True)

這個模型的參數(shù)情況如下圖所示。圖像識別的問題就是這點麻煩，參數(shù)太多了，大批求導(dǎo)，怪不得天價核彈這么貴還這么有市場：

本質(zhì)上還是一個分類問題，使用交叉熵作為損失函數(shù)，定義輸出結(jié)果的好壞：

sgd = optimizers.SGD(lr=.1, momentum=0.9, nesterov=True)
model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=["accuracy"])

設(shè)定回饋：

tb_cb     = TensorBoard(log_dir="./densenet/", histogram_freq=0)
change_lr = LearningRateScheduler(scheduler)
ckpt      = ModelCheckpoint("./ckpt.h5", save_best_only=False, mode="auto", period=10)
cbks      = [change_lr,tb_cb,ckpt]

添加上數(shù)據(jù)集擴充功能，對圖像做一些彈性變換，比如水平翻轉(zhuǎn)，垂直翻轉(zhuǎn)，旋轉(zhuǎn)：

print("Using real-time data augmentation.")
datagen   = ImageDataGenerator(horizontal_flip=True,width_shift_range=0.125,height_shift_range=0.125,fill_mode="constant",cval=0.)

datagen.fit(x_train)

訓(xùn)練模型：

model.fit_generator(datagen.flow(x_train, y_train,batch_size=batch_size), steps_per_epoch=iterations, epochs=epochs, callbacks=cbks,validation_data=(x_test, y_test))
model.save("densenet.h5")

訓(xùn)練過程cpu（i7-7820hk）滿載：

在cpu上進行一次訓(xùn)練需要將近10000秒：

根據(jù)之前手寫數(shù)字文本識別模型的經(jīng)驗（cpu需要12秒，gtx1080只需要0.47秒，gpu是cpu性能的25.72倍），把本程序的epoch改到2500，則gtx1080需要大概270小時。

在v100天價核彈上會是個什么情況呢？明天去試試看咯！