卷积神经网络的进一步理解

最近又再次学习了一些卷积神经网络，有了一些深层的理解

1、工具安装

安装tensorflow和keras又花了一番功夫，找到了一篇还不错的安装博客，链接如下：
Anaconda下安装Tensorflow和Keras的安装教程
现在使用比较多
值得注意的是
我们使用anaconda进行安装，因为keras还需要这几个库的支持，然后再安装上面链接的那一篇博客安装。
pip install numpy
pip install matplotlib
pip install scipy
pip install tensorflow
pip install keras

2、理解和感悟

(1) 优化器Optimizer

其中，优化器有以下这些
深度学习——优化器算法Optimizer详解（BGD、SGD、MBGD、Momentum、NAG、Adagrad、Adadelta、RMSprop、Adam）
当然比较常用的是SGD，即随机梯度下降算法。
随机梯度下降b站教程

(2)Alex经典cnn网络

AlexNet的整个网络结构就是由5个卷积层和3个全连接层组成的，深度总共8层

# 导包
import keras
from keras.models import Sequential
from keras.layers import Dense,Activation,Dropout,Flatten,Conv2D,MaxPool2D
from keras.layers.normalization import BatchNormalization
import numpy as np
np.random.seed(1000)

# 获取数据
import tflearn.datasets.oxflower17 as oxflower17
x,y = oxflower17.load_data(one_hot=True)

# 定义AlexNet模型
model = Sequential()
# 1block
model.add(Conv2D(filters = 97,
                 kernel_size = (11,11),
                 strides = (4,4),
                 padding = "valid",
                 input_shape = (224,224,3)))
model.add(Activation("relu"))
model.add(MaxPool2D(pool_size = (2,2),
                    strides = (2,2),
                    padding = "valid"))
model.add(BatchNormalization())
# 2block
model.add(Conv2D(filters = 256,
                 kernel_size = (11,11),
                 strides = (1,1),
                 padding = "valid"))
model.add(Activation("relu"))
model.add(MaxPool2D(pool_size = (2,2),
                    strides = (2,2),
                    padding = "valid"))
model.add(BatchNormalization())
# 3 block
model.add(Conv2D(filters = 384,
                 kernel_size = (3,3),
                 strides = (1,1),
                 padding = "valid"))
model.add(Activation("relu"))
model.add(BatchNormalization())
# 4 block
model.add(Conv2D(filters = 384,
                 kernel_size = (3,3),
                 strides = (1,1),
                 padding = "valid"))
model.add(Activation("relu"))
model.add(BatchNormalization())
# 5 block
model.add(Conv2D(filters = 256,
                 kernel_size = (3,3),
                 strides = (1,1),
                 padding = "valid"))
model.add(Activation("relu"))
model.add(MaxPool2D(pool_size = (2,2),
                    strides = (2,2),
                    padding = "valid"))
model.add(BatchNormalization())
# 6 dense
model.add(Flatten())
model.add(Dense(4096, input_shape=(224*224*3,)))
model.add(Activation("relu"))
model.add(Dropout(0.4))
model.add(BatchNormalization())
# 7 dense
model.add(Dense(4096))
model.add(Activation("relu"))
model.add(Dropout(0.4))
model.add(BatchNormalization())
# 8 dense
model.add(Dense(17))
model.add(Activation("softmax"))

model.summary()

# compile
model.compile(loss = "categorical_crossentropy",
              optimizer = "adam",
              metrics = ["accuracy"])
# train
model.fit(x,
          y,
          batch_size = 32,
          epochs = 8,
          verbose = 1,
          validation_split = 0.3,
          shuffle = True)

(3)残差网络

ResNet中解决深层网络梯度消失的问题的核心结构是残差网络

残差网络增加了一个identity mapping（恒等映射），把当前输出直接传输给下一层网络（全部是1:1传输，不增加额外的参数），相当于走了一个捷径，跳过了本层运算，这个直接连接命名为"skip connection"。同时在反向传播过程中，也是将下一层网络的梯度直接传递给上一层网络，这样就解决了深层网络的梯度消失问题。

import keras
from keras.layers import Conv2D,Input

x = Input(shape=(224,224,3))
y = Conv2D(3,(3,3),padding="same")(x)

z = keras.layers.add([x,y])

from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np

model = ResNet50(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)

preds = model.predict(x)
# decode the results into a list of tuples (class, description, probability)
# (one such list for each sample in the batch)
print("Predicted:", decode_predictions(preds, top=3)[0])

b站学习视频点这里