搭积木般构建深度学习网络 —— ResNet50完整代码解析

这里我们来看一下Keras中ResNet50的代码。关于ResNet的理解可以参阅深度残差网 点击打开链接

首先我们需要载入将会使用到的库文件

import numpy as np
import warnings

from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import GlobalMaxPooling2D
from keras.layers import ZeroPadding2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras.applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs

然后我们指定预训练模型的权重路径。权重可以从网上下载也可以是你自己此前训练并保存的权重，如何保存训练好的模型和权重可以参阅keras常见问题汇总 点击打开链接

这里提供网上预训练的ResNet50参数下载

WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'

在定义模型的主体结构前，如果你没有阅读本文开头关于深度残差网的链接文章，那么我们简单回顾一下它的模型结构。

现在我们可以来定义模型的主体结构部分。

首先我们来定义identity部分。输入变量包括input_tensor：输入张量；kenel_size：默认为3；filters：整数列表；stage：当前阶段标签；block：当前块标签；返回块的输出张量。

def identity_block(input_tensor, kernel_size, filters, stage, block):
    
    filters1, filters2, filters3 = filters
    if K.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size,
               padding='same', name=conv_name_base + '2b')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = layers.add([x, input_tensor])
    x = Activation('relu')(x)
    return x

然后我们定义卷积部分的块。

def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
    
    filters1, filters2, filters3 = filters
    if K.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), strides=strides,
               name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size, padding='same',
               name=conv_name_base + '2b')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = Conv2D(filters3, (1, 1), strides=strides,
                      name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = layers.add([x, shortcut])
    x = Activation('relu')(x)
    return x

接下来我们使用上述定义的两种块来构建ResNet的主体框架。我们先看一下模型构造图再看相应的代码。注意载入预训练参数部分是可选的内容。

def ResNet50(include_top=True, weights='imagenet',
             input_tensor=None, input_shape=None,
             pooling=None,
             classes=1000):
   
    if weights not in {'imagenet', None}:
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization) or `imagenet` '
                         '(pre-training on ImageNet).')

    if weights == 'imagenet' and include_top and classes != 1000:
        raise ValueError('If using `weights` as imagenet with `include_top`'
                         ' as true, `classes` should be 1000')


    input_shape = _obtain_input_shape(input_shape,
                                      default_size=224,
                                      min_size=197,
                                      data_format=K.image_data_format(),
                                      include_top=include_top)

    if input_tensor is None:
        img_input = Input(shape=input_shape)
    else:
        if not K.is_keras_tensor(input_tensor):
            img_input = Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor
    if K.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1

    x = ZeroPadding2D((3, 3))(img_input)
    x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
    x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)

    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')

    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')

    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')

    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

    x = AveragePooling2D((7, 7), name='avg_pool')(x)

    if include_top:
        x = Flatten()(x)
        x = Dense(classes, activation='softmax', name='fc1000')(x)
    else:
        if pooling == 'avg':
            x = GlobalAveragePooling2D()(x)
        elif pooling == 'max':
            x = GlobalMaxPooling2D()(x)

    if input_tensor is not None:
        inputs = get_source_inputs(input_tensor)
    else:
        inputs = img_input

    model = Model(inputs, x, name='resnet50')


    if weights == 'imagenet':
        if include_top:
            weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
                                    WEIGHTS_PATH,
                                    cache_subdir='models',
                                    md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
        else:
            weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                    WEIGHTS_PATH_NO_TOP,
                                    cache_subdir='models',
                                    md5_hash='a268eb855778b3df3c7506639542a6af')
        model.load_weights(weights_path)
        if K.backend() == 'theano':
            layer_utils.convert_all_kernels_in_model(model)

        if K.image_data_format() == 'channels_first':
            if include_top:
                maxpool = model.get_layer(name='avg_pool')
                shape = maxpool.output_shape[1:]
                dense = model.get_layer(name='fc1000')
                layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')

            if K.backend() == 'tensorflow':
                warnings.warn('You are using the TensorFlow backend, yet you '
                              'are using the Theano '
                              'image data format convention '
                              '(`image_data_format="channels_first"`). '
                              'For best performance, set '
                              '`image_data_format="channels_last"` in '
                              'your Keras config '
                              'at ~/.keras/keras.json.')
    return model

最后部分是文件运行主函数。

if __name__ == '__main__':
    model = ResNet50(include_top=True, weights='imagenet')

    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('Predicted:', decode_predictions(preds))

我们可以将上述代码应用到需要用ResNet模型的任何应用中，如果你对模型的理念和结构有所了解并找到合适的工具，那么构建深度学习网络模型就如同搭乐高积木一般简单。