搭積木般構建深度學習網絡 —— ResNet50完整代碼解析

這裏我們來看一下Keras中ResNet50的代碼。關於ResNet的理解可以參閱深度殘差網 點擊打開鏈接

首先我們需要載入將會使用到的庫文件

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

然後我們指定預訓練模型的權重路徑。權重可以從網上下載也可以是你自己此前訓練並保存的權重，如何保存訓練好的模型和權重可以參閱keras常見問題彙總 點擊打開鏈接

這裏提供網上預訓練的ResNet50參數下載

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'

在定義模型的主體結構前，如果你沒有閱讀本文開頭關於深度殘差網的鏈接文章，那麼我們簡單回顧一下它的模型結構。

現在我們可以來定義模型的主體結構部分。

首先我們來定義identity部分。輸入變量包括input_tensor：輸入張量；kenel_size：默認爲3；filters：整數列表；stage：當前階段標籤；block：當前塊標籤；返回塊的輸出張量。

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

然後我們定義卷積部分的塊。

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

接下來我們使用上述定義的兩種塊來構建ResNet的主體框架。我們先看一下模型構造圖再看相應的代碼。注意載入預訓練參數部分是可選的內容。

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

最後部分是文件運行主函數。

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))

我們可以將上述代碼應用到需要用ResNet模型的任何應用中，如果你對模型的理念和結構有所瞭解並找到合適的工具，那麼構建深度學習網絡模型就如同搭樂高積木一般簡單。