Resnet50源碼-tensorflow解析
原理解析：何凱明論文PPT-秒懂原理
項目地址：Resnet50源碼
參考keras中的源碼進行解析
先加載一些庫的文件
from __future__ import print_function
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然後添加預訓練的權重（採用網上的resnet50進行舉例）
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'
簡單瞭解下殘差網絡的原理圖
然後我們可以開始定義結構的主體，首先定義identity(x)
def identity_block(input_tensor, kernel_size, filters, stage, block):
"""The identity block is the block that has no conv layer at shortcut.
# Arguments
input_tensor: input tensor #輸入變量#
kernel_size: defualt 3, the kernel size of middle conv layer at main path #卷積核的大小#
filters: list of integers, the filterss of 3 conv layer at main path #卷積核的數目#
stage: integer, current stage label, used for generating layer names #當前階段的標籤#
block: 'a','b'..., current block label, used for generating layer names #當前塊的標籤#
# Returns
Output tensor for the block. #返回塊的輸出變量#
"""
filters1, filters2, filters3 = filters #濾波器的名稱#
if K.image_data_format() == 'channels_last': #代表圖像通道維的位置#
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) #卷積層，BN層，激活函數#
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定義卷積層的結構
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
"""conv_block is the block that has a conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
# Returns
Output tensor for the block.
Note that from stage 3, the first conv layer at main path is with strides=(2,2)
And the shortcut should have strides=(2,2) as well
"""
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現在讓我們用定義好的兩種塊去構建resnet50的主體結構，先看一下其原理結構圖：
看了原理圖之後開始構建框架圖：
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000): #這裏採用的權重是imagenet，可以更改，種類爲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')
# Determine proper input shape
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) #對圖片界面填充0，保證特徵圖的大小#
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x) #定義卷積層#
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x) #批標準化#
x = Activation('relu')(x) #激活函數#
x = MaxPooling2D((3, 3), strides=(2, 2))(x) #最大池化層#
#stage2#
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')
#stage3#
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')
#stage4#
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')
#stage5#
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) #平均池化層#
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)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
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搭建完主體結構之後，便可以開始進行測試了。
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))作爲一名深度學習領域的新手，我的建議是大家可以在掌握原理的前提之後，開始看論文的源碼之後，在把resnet網絡的主體結構自己在重新coding 一下，這樣不僅加深自己的理解，同時也會使自己具備看代碼的耐心，避免之後看到龐大的代碼庫便心生怯意，同時大家不懂的地方可以在下方評論。