学习# DigitalSreeni# Python

DIP-Python tutorials for image processing and machine learning(70-71)-Deep Learning

学习自 Youtube 博主 DigitalSreeni。

正文

70 - An overview of deep learning and neural networks

png

传统的机器学习：提取特征然后生成模型

png

CNN 深度卷积网络：输入-卷积层-池化层-全连接层

png

卷积层和池化层可以有很多层。

png
python
INPUT_SHAPE =(64,64,3) #change to (SIZE, SIZE, 3)
inp = keras.layersInput(shape=INPUT SHAPE)
conv1 = keras.layers.Conv2D(32, kernel_size=(3, 3), activation='relu', padding='same')(inp)
pool1 = keras.layers.MaxPooling2D(pool size=(2, 2))(conv1)
norm1 = keras.layers.BatchNormalization(axis=-1)(pool1)
drop1 = keras.layers.Dropout(rate=0.2)(norm1)
conv2 = keras.layers.Conv2D(32, kernel_size=(3, 3), activation='relu', padding='same')(drop1)
pool2 = keras.layers.MaxPooling2D(poo size=(2, 2))(conv2)
norm2 = keras.layers.BatchNormalization(axis = -1)(pool2)
drop2 = keras.layers.Dropout(rate=0.2)(norm2)
flat = keras.layers.Flatten()(drop2)
hidden1 = keras.layers.Dense(512, activation='relu')(flat)
norm3 = keras.layers.BatchNormalization(axis = -1)(hidden1)
drop3 = keras.layers.Dropout(rate=0.2)(norm3)
hidden2 = keras.layers.Dense(256, activation='relu')(drop3)
norm4 = keras.layers.BatchNormalization(axis = -1)(hidden2)
drop4 = keras.layers.Dropout(rate=0.2)(norm4)
 
out = keras.layers.Dense(2, activation='sigmoid')(drop4)  # units=1gives error
model = keras.Model(inputs=inp, outputs=out)model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

A few keywords to understand:

png

TensorFlow and Keras

  • TensorFlow
    • TensorFlow is the most famous library used in production for deep learning models.
    • TensorFlow is not that easy to use.
  • Keras
    • Keras is a high level API built on TensorFlow (also on Theano)
    • Keras is more user-friendly than TensorFlow -allows you to quickly build and test networks with minimal effort.
png
  • 卷积和池化
png

BatchNormalization

  • Normalization is important to keep the values in input and hidden layers within certain range.
  • Normalizing usually improves training speed.
  • Batch normalization allows each layer of a network to learn by itself a little bit more independently of other layers.
  • We can use higher learning rates because batch normalization makes sure that there's noactivation that's gone really high or really low.
png

Dropout（通常是将权重设为 0）

  • The term "dropout" refers to dropping out neurons at random in a neural network.
  • Dropout is needed to prevent over-fitting.
png

Flattening

  • The flattening step creates a long vector that is needed as input to the artificial neural network.
png

Dense layer

  • Input (features)
  • Hidden Layers (lots of layers ~ "deep learning")
    • neuron (Weight, bias and activation function)
  • Output (prediction)
png

Activation: Biological Neuron reference 参考生物的神经元

png png

Optimizer:Adam

  • Optimizer → choice of optimizer algorithm → good results in minutes or hours or days.

    • 优化器 → 优化器算法的选择 → 在几分钟或几小时或几天内取得好的结果。

  • Adam optimization is an extension to stochastic gradient descent.

    • Adam 优化是对随机梯度下降的延伸。

  • Adam is most often used for CNN.

png

Loss Functions - Categorical cross-entropy 交叉熵损失函数

  • A loss function (or cost function) is a method of evaluating how well your algorithm models your dataset.
  • Good prediction → low value for loss (Bad → high loss value)
  • Cross-entropy loss function is commonly used for CNN.
  • Mean square error is an example of basic loss function for linear regression.
png

Epoch and other terms

  • When data is too big we need to break into smaller batches so the computer can handle.

  • One epoch is when an ENTIRE dataset is passed forward and backward through the neural network ONCE.

    • 一个 epoch 是指一个完整的数据集通过神经网络向前和向后传递一次。

  • Batch Size is the number of training samples in 1 Forward/1 Backward pass.

    • Batch Size 是指 1 个前向 / 1 个后向通道中的训练样本数。

  • Number of iterations = Number of passes

    • 迭代次数 = 通过次数

  • Example : lf we have 100 training samples and Batch size is set to 25, it will take 4 iterations to complete 1 Epoch.

    • 例子：如果我们有 100 个训练样本，批量大小设置为 25，则需要 4 次迭代来完成一个周期。

What is the right numbers of epochs?

No one knows, depends on the problem!

71 - Malarial cell classification using CNN

python
import numpy as np
import cv2
import os
from PIL import Image
import keras
 
np.random.seed(1000)
os.environ['KERAS_BACKEND'] = 'tensorflow'  # 将后端设为 tensorflow，如果你想，也可设成 theano
  • 尝试导入输入(500 个未收感染的细胞，500 个被感染的细胞)
python
image_directory = 'cell_images2/'
SIZE = 64
dataset = []
label = []
  • 导入被感染的细胞，设为标签0
python
parasitized_images = os.listdir(image_directory + 'Parasitized/')
for i, image_name in enumerate(parasitized_images):
    if image_name.split('.')[1] == 'png':  # 如果是 PNG 格式，则读取它
        image = cv2.imread(image_directory + 'Parasitized/' + image_name)  # 读取图片，以 np.array格式
        image = Image.fromarray(image, 'RGB')  # 将 array 格式转换为 image 格式
        image = image.resize((SIZE, SIZE))  # 变换大小
        dataset.append(np.array(image))  # 录入数据集
        label.append(0)  # 录入标签
  • 导入未被感染的细胞，设为标签1
python
uninfected_images = os.listdir(image_directory + 'Uninfected/')
for i, image_name in enumerate(uninfected_images):
    if image_name.split('.')[1] == 'png':
        image = cv2.imread(image_directory + 'Uninfected/' + image_name)
        image = Image.fromarray(image, 'RGB')
        image = image.resize((SIZE, SIZE))
        dataset.append(np.array(image))
        label.append(1)

  • 设置 CNN

    • 2 conv and pool layers. with some normalization and drops in between.

  • 输入层

python
INPUT_SHAPE = (SIZE, SIZE, 3)
inp = keras.layers.Input(shape=INPUT_SHAPE)
python
conv1 = keras.layers.Conv2D(32, kernel_size=(3, 3),
                            activation='relu', padding='same')(inp)
python
pool1 = keras.layers.MaxPooling2D(pool_size=(2, 2))(conv1)
python
norm1 = keras.layers.BatchNormalization(axis=-1)(pool1)
python
drop1 = keras.layers.Dropout(rate=0.2)(norm1)
  • 卷积层 2
python
conv2 = keras.layers.Conv2D(32, kernel_size=(3, 3),
                            activation='relu', padding='same')(drop1)
  • 池化层 2
python
pool2 = keras.layers.MaxPooling2D(pool_size=(2, 2))(conv2)
  • Normalization 2
python
norm2 = keras.layers.BatchNormalization(axis=-1)(pool2)
  • Dropout 2
python
drop2 = keras.layers.Dropout(rate=0.2)(norm2)
  • Flatten 层 Flatten layer
    • Flatten the matrix to get it ready for dense.
python
flat = keras.layers.Flatten()(drop2)
python
hidden1 = keras.layers.Dense(512, activation='relu')(flat)
  • Normalization 3
python
norm3 = keras.layers.BatchNormalization(axis=-1)(hidden1)
  • Dropout 3
python
drop3 = keras.layers.Dropout(rate=0.2)(norm3)
  • 隐藏层 2
python
hidden2 = keras.layers.Dense(256, activation='relu')(drop3)
  • Normalization 4
python
norm4 = keras.layers.BatchNormalization(axis=-1)(hidden2)
  • Drop 4
python
drop4 = keras.layers.Dropout(rate=0.2)(norm4)
  • 输出层
python
out = keras.layers.Dense(2, activation='sigmoid')(drop4)
python
model = keras.Model(inputs=inp, outputs=out)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
python
from tensorflow.keras import utils
from keras.utils.vis_utils import model_to_dot
 
utils.plot_model(model, 'model1.png',show_shapes=True,show_dtype=True,show_layer_names=True)
png
python
model.summary()
Model: "model"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
===============================================================
 input_1 (InputLayer)        [(None, 64, 64, 3)]       0         
                                                                 
 conv2d (Conv2D)             (None, 64, 64, 32)        896       
                                                                 
 max_pooling2d (MaxPooling2D  (None, 32, 32, 32)       0         
 )                                                               
                                                                 
 batch_normalization (BatchN  (None, 32, 32, 32)       128       
 ormalization)                                                   
                                                                 
 dropout (Dropout)           (None, 32, 32, 32)        0         
                                                                 
 conv2d_1 (Conv2D)           (None, 32, 32, 32)        9248      
                                                                 
 max_pooling2d_1 (MaxPooling  (None, 16, 16, 32)       0         
 2D)                                                             
                                                                 
 batch_normalization_1 (Batc  (None, 16, 16, 32)       128       
 hNormalization)                                                 
                                                                 
 dropout_1 (Dropout)         (None, 16, 16, 32)        0         
                                                                 
 flatten (Flatten)           (None, 8192)              0         
                                                                 
 dense (Dense)               (None, 512)               4194816   
                                                                 
 batch_normalization_2 (Batc  (None, 512)              2048      
 hNormalization)                                                 
                                                                 
 dropout_2 (Dropout)         (None, 512)               0         
                                                                 
 dense_1 (Dense)             (None, 256)               131328    
                                                                 
 batch_normalization_3 (Batc  (None, 256)              1024      
 hNormalization)                                                 
                                                                 
 dropout_3 (Dropout)         (None, 256)               0         
                                                                 
 dense_2 (Dense)             (None, 2)                 514       
                                                                 
===============================================================
Total params: 4,340,130
Trainable params: 4,338,466
Non-trainable params: 1,664
_________________________________________________________________

卷积神经网络的参数计算_qian99的博客-CSDN博客_卷积神经网络参数

网络层(输入)输入神经元个数sizestride输出参数量
input64x64x3（长 x 宽 x 通道数）64x64x30
conv2d64x64x3323x3164x64x3232x3x3x3+32=896
max_pooling2d64x64x322x2None(64/2)x(64/2)x320
batch_normalization32x32x3232x32x32128
dropout32x32x3232x32x320
conv2d_132x32x32323x3132x32x3232x3x3x32+32=9248
max_pooling2d_132x32x322x21(32/2)x(32/2)x320
batch_normalization_116x16x3216x16x32128
dropout_116x16x3216x16x320
flatten16x16x3216x16x32=81920
dense81925125128192x512+512=4194816
batch_normalization_25125122048
dropout_25125120
dense_1512256256512x256+256=131328
batch_normalization_32562561024
dropout_32562560
dense_225622256x2+2=514
  • 设置测试集和训练集，开始训练
python
from sklearn.model_selection import train_test_split
from keras.utils import to_categorical
 
X_train, X_test, y_train, y_test = train_test_split(dataset, 
                                                    to_categorical(np.array(label)),
                                                    test_size = 0.20,
                                                    random_state = 0)
python
history = model.fit(np.array(X_train), y_train, batch_size=64, verbose=1, epochs=25, validation_split=0.1, shuffle=False)
Epoch 1/25
12/12 [============================] - 9s 99ms/step - loss: 0.9405 - accuracy: 0.6444 - val_loss: 31.2568 - val_accuracy: 0.5625
Epoch 2/25
12/12 [==========================] - 0s 37ms/step - loss: 0.5048 - accuracy: 0.7472 - val_loss: 23.6857 - val_accuracy: 0.5625
Epoch 3/25
12/12 [==========================] - 0s 37ms/step - loss: 0.3281 - accuracy: 0.8417 - val_loss: 17.8224 - val_accuracy: 0.5625
Epoch 4/25
12/12 [==========================] - 0s 37ms/step - loss: 0.2036 - accuracy: 0.9250 - val_loss: 14.3039 - val_accuracy: 0.5625
Epoch 5/25
12/12 [==========================] - 0s 37ms/step - loss: 0.1568 - accuracy: 0.9431 - val_loss: 13.0039 - val_accuracy: 0.5625
Epoch 6/25
12/12 [==========================] - 0s 37ms/step - loss: 0.1074 - accuracy: 0.9694 - val_loss: 7.4553 - val_accuracy: 0.5625
Epoch 7/25
12/12 [==========================] - 0s 37ms/step - loss: 0.0858 - accuracy: 0.9778 - val_loss: 3.5444 - val_accuracy: 0.5500
Epoch 8/25
12/12 [==========================] - 0s 37ms/step - loss: 0.0608 - accuracy: 0.9819 - val_loss: 4.7493 - val_accuracy: 0.5500
Epoch 9/25
12/12 [==========================] - 0s 37ms/step - loss: 0.0632 - accuracy: 0.9764 - val_loss: 4.7916 - val_accuracy: 0.5625
Epoch 10/25
12/12 [==========================] - 0s 36ms/step - loss: 0.0432 - accuracy: 0.9889 - val_loss: 1.9020 - val_accuracy: 0.5875
Epoch 11/25
12/12 [==========================] - 0s 36ms/step - loss: 0.0489 - accuracy: 0.9847 - val_loss: 2.2950 - val_accuracy: 0.5750
Epoch 12/25
12/12 [==========================] - 0s 37ms/step - loss: 0.0458 - accuracy: 0.9861 - val_loss: 0.8035 - val_accuracy: 0.7625
Epoch 13/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0264 - accuracy: 0.9958 - val_loss: 1.4798 - val_accuracy: 0.6500
Epoch 14/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0244 - accuracy: 0.9931 - val_loss: 1.6248 - val_accuracy: 0.6625
Epoch 15/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0160 - accuracy: 0.9958 - val_loss: 1.2913 - val_accuracy: 0.7125
Epoch 16/25
12/12 [==========================] - 0s 39ms/step - loss: 0.0169 - accuracy: 0.9958 - val_loss: 1.4256 - val_accuracy: 0.6875
Epoch 17/25
12/12 [==========================] - 0s 40ms/step - loss: 0.0114 - accuracy: 0.9986 - val_loss: 1.2699 - val_accuracy: 0.7000
Epoch 18/25
12/12 [==========================] - 0s 39ms/step - loss: 0.0158 - accuracy: 0.9972 - val_loss: 0.7563 - val_accuracy: 0.7875
Epoch 19/25
12/12 [==========================] - 0s 39ms/step - loss: 0.0133 - accuracy: 0.9972 - val_loss: 0.6219 - val_accuracy: 0.8500
Epoch 20/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0194 - accuracy: 0.9958 - val_loss: 0.7935 - val_accuracy: 0.8500
Epoch 21/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0174 - accuracy: 0.9972 - val_loss: 2.8081 - val_accuracy: 0.5625
Epoch 22/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0188 - accuracy: 0.9931 - val_loss: 0.6510 - val_accuracy: 0.8000
Epoch 23/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0340 - accuracy: 0.9903 - val_loss: 1.6654 - val_accuracy: 0.6250
Epoch 24/25
12/12 [==========================] - 0s 38ms/step - loss: 0.0248 - accuracy: 0.9931 - val_loss: 0.8992 - val_accuracy: 0.7625
Epoch 25/25
12/12 [============================] - 0s 38ms/step - loss: 0.0201 - accuracy: 0.9917 - val_loss: 2.0561 - val_accuracy: 0.7250
  • 查看结果
python
print("Test_Accuracy: {:.2f}%".format(model.evaluate(np.array(X_test), np.array(y_test))[1]*100))
7/7 [==============================] - 0s 17ms/step - loss: 1.7793 - accuracy: 0.6950
Test_Accuracy: 69.50%
python
import matplotlib.pyplot as plt
 
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))
t = f.suptitle('CNN Performance', fontsize=12)
f.subplots_adjust(top=0.85, wspace=0.3)
 
# 绘制训练 & 验证的准确率值
max_epoch = len(history.history['accuracy'])+1
epoch_list = list(range(1,max_epoch))
ax1.plot(epoch_list, history.history['accuracy'], label='Train Accuracy')
ax1.plot(epoch_list, history.history['val_accuracy'], label='Validation Accuracy')
ax1.set_xticks(np.arange(1, max_epoch, 5))
ax1.set_ylabel('Accuracy Value')
ax1.set_xlabel('Epoch')
ax1.set_title('Accuracy')
l1 = ax1.legend(loc="best")
 
# 绘制训练 & 验证的损失值
ax2.plot(epoch_list, history.history['loss'], label='Train Loss')
ax2.plot(epoch_list, history.history['val_loss'], label='Validation Loss')
ax2.set_xticks(np.arange(1, max_epoch, 5))
ax2.set_ylabel('Loss Value')
ax2.set_xlabel('Epoch')
ax2.set_title('Loss')
l2 = ax2.legend(loc="best")
png

可以推断出 epoch 次数过多，出现了过拟合现象。

  • 保存模型
python
model.save('malaria_cnn.h5')
png