keras之-ResNet50

理論參考：https://blog.csdn.net/weixin_43624538/article/details/85049699

代碼：https://blog.csdn.net/u013093426/article/details/81166751

整體架構圖：

其中ID block x3表示該模塊是由3個Identity塊堆疊構成，該模型各層參數設置如下：

Zero-Padding: P = (3, 3)

Stage 1:

Conv2D:64個fileter， f = （7,7），strides = （2,2），name=conv1

BatchNorm：對channel標準化

MaxPooling: f = (3, 3), strides = (2, 2)

Stage 2：

Convolution block：filter = 3，size = [64,64,256], f = 3, s = 1, block = a

ID block 2x：filter = 3， size = [64,64,256], f = 3， block = b, c

Stage 3：

Convolution block：filter = 3，size = [128, 128, 512], f = 3, s = 2, block = a

ID block 3x：filter = 3， size = [128, 128, 512], f = 3， block = b, c,d

Stage 4：

Convolution block：filter = 3，size = [256, 256, 1024], f = 3, s = 2, block = a

ID block 5x：filter = 3， size = [256, 256, 1024], f = 3， block = b, c,d,e,f

Stage 5：

Convolution block：filter = 3，size = [512, 512, 2048], f = 3, s = 2, block = a

ID block 2x：filter = 3， size = [512, 512, 2048], f = 3， block = b, c

 

AveragePooling: f = (2, 2), name = "avg_pool"

Flatten:None

FC: softmax, name = 'fc' + str(classes)
————————————————
原文鏈接：https://blog.csdn.net/u013093426/article/details/81166751

import numpy as np
from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D
from keras.models import Model, load_model
import tensorflow as tf
from keras.initializers import glorot_uniform
import keras.backend as K
K.set_image_data_format('channels_last')
K.set_learning_phase(1)

def identity_block(X, f, filters, stage, block):
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    F1, F2, F3 = filters

    X_shortcut = X

    X = Conv2D(filters=F1, kernel_size=(1, 1), strides=(1, 1), padding='valid', name=conv_name_base + '2a',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2a')(X)
    X = Activation('relu')(X)

    X = Conv2D(filters=F2, kernel_size=(f, f), strides=(1, 1), padding='same', name=conv_name_base + '2b',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2b')(X)
    X = Activation('relu')(X)

    X = Conv2D(filters=F3, kernel_size=(1, 1), strides=(1, 1), padding='valid', name=conv_name_base + '2c',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2c')(X)

    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)

    return X


def convolutional_block(X, f, filters, stage, block, s=2):
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'
    F1, F2, F3 = filters

    X_shortcut = X

    X = Conv2D(filters=F1, kernel_size=(1, 1), strides=(s, s), name=conv_name_base + '2a',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2a')(X)
    X = Activation('relu')(X)

    X = Conv2D(filters=F2, kernel_size=(f, f), strides=(1, 1), padding='same', name=conv_name_base + '2b',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2b')(X)
    X = Activation('relu')(X)

    X = Conv2D(filters=F3, kernel_size=(1, 1), strides=(1, 1), name=conv_name_base + '2c',
               kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name=bn_name_base + '2c')(X)

    X_shortcut = Conv2D(F3, (1, 1), strides=(s, s), name=conv_name_base + '1',
                        kernel_initializer=glorot_uniform(seed=0))(X_shortcut)
    X_shortcut = BatchNormalization(axis=3, name=bn_name_base + '1')(X_shortcut)

    X = Add()([X, X_shortcut])
    X = Activation('relu')(X)

    return X
tf.reset_default_graph()

def ResNet50(input_shape=(64, 64, 3), classes=10):
    X_input = Input(input_shape)

    X = ZeroPadding2D((3, 3))(X_input)

    X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1', kernel_initializer=glorot_uniform(seed=0))(X)
    X = BatchNormalization(axis=3, name='bn_conv1')(X)
    X = Activation('relu')(X)
    X = MaxPooling2D((3, 3), strides=(2, 2))(X)

    X = convolutional_block(X, f=3, filters=[64, 64, 256], stage=2, block='a', s=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 = convolutional_block(X, f=3, filters=[128, 128, 512], stage=3, block='a', s=2)
    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 = convolutional_block(X, f=3, filters=[256, 256, 1024], stage=4, block='a', s=2)
    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 = convolutional_block(X, f=3, filters=[512, 512, 2048], stage=5, block='a', s=2)
    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((2, 2), name='avg_pool')(X)

    X = Flatten()(X)
    X = Dense(classes, activation='softmax', name='fc' + str(classes), kernel_initializer=glorot_uniform(seed=0))(X)

    model = Model(inputs=X_input, outputs=X, name='ResNet50')

    return model

import pickle
import PIL
from PIL import Image
from sklearn.model_selection import train_test_split

def load_file(filename):
    with open(filename, 'rb') as fo:
        data = pickle.load(fo, encoding='latin1')
    return data

n_size = 3000

def get_data():
    data = load_file('test_batch')
    img = data['data']
    img = np.reshape(img, (-1, 3, 32, 32 ))  # 只是測試，沒有采用循環導出全部圖像，這裏導出第10幅圖
    imgs =  np.zeros((n_size,64,64,3))
    for i in range(n_size):
        r = img[i][0]
        g = img[i][1]
        b = img[i][2]

        ir = Image.fromarray(r)
        ig = Image.fromarray(g)
        ib = Image.fromarray(b)
        temp = Image.merge("RGB", (ir, ig, ib))
        temp = temp.resize((64,64))
        imgs[i] = temp
    imgs = imgs.astype(np.int)
    labels = np.zeros((n_size,10))
    for i, lb in enumerate(data['labels'][:n_size]):
        labels[i][lb] = 1
    return imgs,labels