Keras架構：Mobilenet網絡代碼實作

Mobilenet概念：

MobileNet模型是Google針對手機等嵌入式裝置提出的一種輕量級的深層神經網絡，其使用的核心思想便是depthwise separable convolution。

Mobilenet思想：

通俗地了解就是3x3的卷積核厚度隻有一層，然後在輸入張量上一層一層地滑動，每一次卷積完生成 一個輸出通道，當卷積完成後，在利用1x1的卷積調整厚度。

對于一個卷積點而言： 假設有一個3×3大小的卷積層，其輸入通道為16、輸出通道為32。具體為，32個3×3大小的卷積核會 周遊16個通道中的每個資料，最後可得到所需的32個輸出通道，所需參數為16×32×3×3=4608個。

應用深度可分離卷積，用16個3×3大小的卷積核分别周遊16通道的資料，得到了16個特征圖譜。在 融合操作之前，接着用32個1×1大小的卷積核周遊這16個特征圖譜，所需參數為 16×3×3+16×32×1×1=656個。

可以看出來depthwise separable convolution可以減少模型的參數。

Mobilenet網絡代碼實作

網絡主體部分：

#-------------------------------------------------------------#
#   MobileNet的網絡部分
#-------------------------------------------------------------#
import warnings
import numpy as np

from keras.preprocessing import image

from keras.models import Model
from keras.layers import DepthwiseConv2D,Input,Activation,Dropout,Reshape,BatchNormalization,GlobalAveragePooling2D,GlobalMaxPooling2D,Conv2D
from keras.applications.imagenet_utils import decode_predictions
from keras import backend as K


def MobileNet(input_shape=[224,224,3],
              depth_multiplier=1,
              dropout=1e-3,
              classes=1000):


    img_input = Input(shape=input_shape)

    # 224,224,3 -> 112,112,32
    x = _conv_block(img_input, 32, strides=(2, 2))

    # 112,112,32 -> 112,112,64
    x = _depthwise_conv_block(x, 64, depth_multiplier, block_id=1)

    # 112,112,64 -> 56,56,128
    x = _depthwise_conv_block(x, 128, depth_multiplier,
                              strides=(2, 2), block_id=2)
    # 56,56,128 -> 56,56,128
    x = _depthwise_conv_block(x, 128, depth_multiplier, block_id=3)

    # 56,56,128 -> 28,28,256
    x = _depthwise_conv_block(x, 256, depth_multiplier,
                              strides=(2, 2), block_id=4)
    
    # 28,28,256 -> 28,28,256
    x = _depthwise_conv_block(x, 256, depth_multiplier, block_id=5)

    # 28,28,256 -> 14,14,512
    x = _depthwise_conv_block(x, 512, depth_multiplier,
                              strides=(2, 2), block_id=6)
    
    # 14,14,512 -> 14,14,512
    x = _depthwise_conv_block(x, 512, depth_multiplier, block_id=7)
    x = _depthwise_conv_block(x, 512, depth_multiplier, block_id=8)
    x = _depthwise_conv_block(x, 512, depth_multiplier, block_id=9)
    x = _depthwise_conv_block(x, 512, depth_multiplier, block_id=10)
    x = _depthwise_conv_block(x, 512, depth_multiplier, block_id=11)

    # 14,14,512 -> 7,7,1024
    x = _depthwise_conv_block(x, 1024, depth_multiplier,
                              strides=(2, 2), block_id=12)
    x = _depthwise_conv_block(x, 1024, depth_multiplier, block_id=13)

    # 7,7,1024 -> 1,1,1024
    x = GlobalAveragePooling2D()(x)
    x = Reshape((1, 1, 1024), name='reshape_1')(x)
    x = Dropout(dropout, name='dropout')(x)
    x = Conv2D(classes, (1, 1),padding='same', name='conv_preds')(x)
    x = Activation('softmax', name='act_softmax')(x)
    x = Reshape((classes,), name='reshape_2')(x)

    inputs = img_input

    model = Model(inputs, x, name='mobilenet_1_0_224_tf')
    model_name = 'mobilenet_1_0_224_tf.h5'
    model.load_weights(model_name)

    return model

def _conv_block(inputs, filters, kernel=(3, 3), strides=(1, 1)):
    x = Conv2D(filters, kernel,
               padding='same',
               use_bias=False,
               strides=strides,
               name='conv1')(inputs)
    x = BatchNormalization(name='conv1_bn')(x)
    return Activation(relu6, name='conv1_relu')(x)


def _depthwise_conv_block(inputs, pointwise_conv_filters,
                          depth_multiplier=1, strides=(1, 1), block_id=1):

    x = DepthwiseConv2D((3, 3),
                        padding='same',
                        depth_multiplier=depth_multiplier,
                        strides=strides,
                        use_bias=False,
                        name='conv_dw_%d' % block_id)(inputs)

    x = BatchNormalization(name='conv_dw_%d_bn' % block_id)(x)
    x = Activation(relu6, name='conv_dw_%d_relu' % block_id)(x)

    x = Conv2D(pointwise_conv_filters, (1, 1),
               padding='same',
               use_bias=False,
               strides=(1, 1),
               name='conv_pw_%d' % block_id)(x)
    x = BatchNormalization(name='conv_pw_%d_bn' % block_id)(x)
    return Activation(relu6, name='conv_pw_%d_relu' % block_id)(x)

def relu6(x):
    return K.relu(x, max_value=6)

def preprocess_input(x):
    x /= 255.
    x -= 0.5
    x *= 2.
    return x

if __name__ == '__main__':
    model = MobileNet(input_shape=(224, 224, 3))

    img_path = 'elephant.jpg'
    img = image.load_img(img_path, target_size=(224, 224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)
    print('Input image shape:', x.shape)

    preds = model.predict(x)
    print(np.argmax(preds))
    print('Predicted:', decode_predictions(preds,1))  # 隻顯示top1