日本免费高清视频-国产福利视频导航-黄色在线播放国产-天天操天天操天天操天天操|www.shdianci.com

學無先后，達者為師

網站首頁 編程語言 正文

python神經網絡MobileNetV2模型的復現詳解_python

作者：Bubbliiiing ? 更新時間： 2022-06-30 編程語言

什么是MobileNetV2模型

MobileNet它哥MobileNetV2也是很不錯的呢

MobileNet模型是Google針對手機等嵌入式設備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。

MobileNetV2是MobileNet的升級版，它具有兩個特征點：

1、Inverted residuals，在ResNet50里我們認識到一個結構，bottleneck design結構，在3x3網絡結構前利用1x1卷積降維，在3x3網絡結構后，利用1x1卷積升維，相比直接使用3x3網絡卷積效果更好，參數更少，先進行壓縮，再進行擴張。而在MobileNetV2網絡部分，其采用Inverted residuals結構，在3x3網絡結構前利用1x1卷積升維，在3x3網絡結構后，利用1x1卷積降維，先進行擴張，再進行壓縮。

2、Linear bottlenecks，為了避免Relu對特征的破壞，在在3x3網絡結構前利用1x1卷積升維，在3x3網絡結構后，再利用1x1卷積降維后，不再進行Relu6層，直接進行殘差網絡的加法。

整體網絡結構如下：（其中bottleneck進行的操作就是上述的創新操作）

MobileNetV2網絡部分實現代碼

#-------------------------------------------------------------#
#   MobileNetV2的網絡部分
#-------------------------------------------------------------#
import math
import numpy as np
import tensorflow as tf
from tensorflow.keras import backend
from keras import backend as K
from keras.preprocessing import image
from keras.models import Model
from keras.layers.normalization import BatchNormalization
from keras.layers import Conv2D, Add, ZeroPadding2D, GlobalAveragePooling2D, Dropout, Dense
from keras.layers import MaxPooling2D,Activation,DepthwiseConv2D,Input,GlobalMaxPooling2D
from keras.applications import imagenet_utils
from keras.applications.imagenet_utils import decode_predictions
from keras.utils.data_utils import get_file
# TODO Change path to v1.1
BASE_WEIGHT_PATH = ('https://github.com/JonathanCMitchell/mobilenet_v2_keras/'
                    'releases/download/v1.1/')
# relu6！
def relu6(x):
    return K.relu(x, max_value=6)
# 用于計算padding的大小
def correct_pad(inputs, kernel_size):
    img_dim = 1
    input_size = backend.int_shape(inputs)[img_dim:(img_dim + 2)]
    if isinstance(kernel_size, int):
        kernel_size = (kernel_size, kernel_size)
    if input_size[0] is None:
        adjust = (1, 1)
    else:
        adjust = (1 - input_size[0] % 2, 1 - input_size[1] % 2)
    correct = (kernel_size[0] // 2, kernel_size[1] // 2)
    return ((correct[0] - adjust[0], correct[0]),
            (correct[1] - adjust[1], correct[1]))
# 使其結果可以被8整除，因為使用到了膨脹系數α
def _make_divisible(v, divisor, min_value=None):
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v
def MobileNetV2(input_shape=[224,224,3],
                alpha=1.0,
                include_top=True,
                weights='imagenet',
                classes=1000):
    rows = input_shape[0]
    img_input = Input(shape=input_shape)
    # stem部分
    # 224,224,3 -> 112,112,32
    first_block_filters = _make_divisible(32 * alpha, 8)
    x = ZeroPadding2D(padding=correct_pad(img_input, 3),
                             name='Conv1_pad')(img_input)
    x = Conv2D(first_block_filters,
                      kernel_size=3,
                      strides=(2, 2),
                      padding='valid',
                      use_bias=False,
                      name='Conv1')(x)
    x = BatchNormalization(epsilon=1e-3,
                                  momentum=0.999,
                                  name='bn_Conv1')(x)
    x = Activation(relu6, name='Conv1_relu')(x)
    # 112,112,32 -> 112,112,16
    x = _inverted_res_block(x, filters=16, alpha=alpha, stride=1,
                            expansion=1, block_id=0)
    # 112,112,16 -> 56,56,24
    x = _inverted_res_block(x, filters=24, alpha=alpha, stride=2,
                            expansion=6, block_id=1)
    x = _inverted_res_block(x, filters=24, alpha=alpha, stride=1,
                            expansion=6, block_id=2)
    # 56,56,24 -> 28,28,32
    x = _inverted_res_block(x, filters=32, alpha=alpha, stride=2,
                            expansion=6, block_id=3)
    x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
                            expansion=6, block_id=4)
    x = _inverted_res_block(x, filters=32, alpha=alpha, stride=1,
                            expansion=6, block_id=5)
    # 28,28,32 -> 14,14,64
    x = _inverted_res_block(x, filters=64, alpha=alpha, stride=2,
                            expansion=6, block_id=6)
    x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
                            expansion=6, block_id=7)
    x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
                            expansion=6, block_id=8)
    x = _inverted_res_block(x, filters=64, alpha=alpha, stride=1,
                            expansion=6, block_id=9)
    # 14,14,64 -> 14,14,96
    x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
                            expansion=6, block_id=10)
    x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
                            expansion=6, block_id=11)
    x = _inverted_res_block(x, filters=96, alpha=alpha, stride=1,
                            expansion=6, block_id=12)
    # 14,14,96 -> 7,7,160
    x = _inverted_res_block(x, filters=160, alpha=alpha, stride=2,
                            expansion=6, block_id=13)
    x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1,
                            expansion=6, block_id=14)
    x = _inverted_res_block(x, filters=160, alpha=alpha, stride=1,
                            expansion=6, block_id=15)
    # 7,7,160 -> 7,7,320
    x = _inverted_res_block(x, filters=320, alpha=alpha, stride=1,
                            expansion=6, block_id=16)
    if alpha > 1.0:
        last_block_filters = _make_divisible(1280 * alpha, 8)
    else:
        last_block_filters = 1280
    # 7,7,320 -> 7,7,1280
    x = Conv2D(last_block_filters,
                      kernel_size=1,
                      use_bias=False,
                      name='Conv_1')(x)
    x = BatchNormalization(epsilon=1e-3,
                                  momentum=0.999,
                                  name='Conv_1_bn')(x)
    x = Activation(relu6, name='out_relu')(x)
    x = GlobalAveragePooling2D()(x)
    x = Dense(classes, activation='softmax',
                        use_bias=True, name='Logits')(x)
    inputs = img_input
    model = Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows))
    # Load weights.
    if weights == 'imagenet':
        if include_top:
            model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
                          str(alpha) + '_' + str(rows) + '.h5')
            weight_path = BASE_WEIGHT_PATH + model_name
            weights_path = get_file(
                model_name, weight_path, cache_subdir='models')
        else:
            model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
                          str(alpha) + '_' + str(rows) + '_no_top' + '.h5')
            weight_path = BASE_WEIGHT_PATH + model_name
            weights_path = get_file(
                model_name, weight_path, cache_subdir='models')
        model.load_weights(weights_path)
    elif weights is not None:
        model.load_weights(weights)
    return model
def _inverted_res_block(inputs, expansion, stride, alpha, filters, block_id):
    in_channels = backend.int_shape(inputs)[-1]
    pointwise_conv_filters = int(filters * alpha)
    pointwise_filters = _make_divisible(pointwise_conv_filters, 8)
    x = inputs
    prefix = 'block_{}_'.format(block_id)
    # part1 數據擴張
    if block_id:
        # Expand
        x = Conv2D(expansion * in_channels,
                          kernel_size=1,
                          padding='same',
                          use_bias=False,
                          activation=None,
                          name=prefix + 'expand')(x)
        x = BatchNormalization(epsilon=1e-3,
                                      momentum=0.999,
                                      name=prefix + 'expand_BN')(x)
        x = Activation(relu6, name=prefix + 'expand_relu')(x)
    else:
        prefix = 'expanded_conv_'
    if stride == 2:
        x = ZeroPadding2D(padding=correct_pad(x, 3),
                                 name=prefix + 'pad')(x)
    # part2 可分離卷積
    x = DepthwiseConv2D(kernel_size=3,
                               strides=stride,
                               activation=None,
                               use_bias=False,
                               padding='same' if stride == 1 else 'valid',
                               name=prefix + 'depthwise')(x)
    x = BatchNormalization(epsilon=1e-3,
                                  momentum=0.999,
                                  name=prefix + 'depthwise_BN')(x)
    x = Activation(relu6, name=prefix + 'depthwise_relu')(x)
    # part3壓縮特征，而且不使用relu函數，保證特征不被破壞
    x = Conv2D(pointwise_filters,
                      kernel_size=1,
                      padding='same',
                      use_bias=False,
                      activation=None,
                      name=prefix + 'project')(x)
    x = BatchNormalization(epsilon=1e-3,
                                  momentum=0.999,
                                  name=prefix + 'project_BN')(x)
    if in_channels == pointwise_filters and stride == 1:
        return Add(name=prefix + 'add')([inputs, x])
    return x

圖片預測

建立網絡后，可以用以下的代碼進行預測。

def preprocess_input(x):
    x /= 255.
    x -= 0.5
    x *= 2.
    return x
if __name__ == '__main__':
    model = MobileNetV2(input_shape=(224, 224, 3))
    model.summary()
    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))

預測所需的已經訓練好的MobileNetV2模型會在運行時自動下載，下載后的模型位于C:\Users\Administrator.keras\models文件夾內。

可以修改MobileNetV2內不同的alpha值實現不同depth的MobileNetV2模型。可選的alpha值有：

? Top-1 Top-5 10-5 Size Stem
MobileNetV2(alpha=0.35) 39.914 17.568 15.422 1.7M 0.4M
MobileNetV2(alpha=0.50) 34.806 13.938 11.976 2.0M 0.7M
MobileNetV2(alpha=0.75) 30.468 10.824 9.188 2.7M 1.4M
MobileNetV2(alpha=1.0) 28.664 9.858 8.322 3.5M 2.3M
MobileNetV2(alpha=1.3) 25.320 7.878 6.728 5.4M 3.8M

原文鏈接：https://blog.csdn.net/weixin_44791964/article/details/102851214

欄目分類
最近更新