樹莓派基於tensorflow的數字識別

樹莓派基於tensorflow的數字識別

目前博主只試過python3.7.3+tensorflow1.13.1版本，其它tensorflow版本的還沒試

一、安裝tensorflow環境

• 檢查python環境

python3 --version
pip3 --version

• 更新軟件源

sudo apt update
sudo apt upgrade

• 執行安裝相應環境

sudo apt-get install python3-pip python3-dev

• 若使用pip3 install tensorflow==1.13.1安裝可能需要等待漫長的時間，可以先在網上下載 tensorflow-1.13.1-cp37-none-linux_armv7l.whl，然后復制到樹莓派系統上，再執行以下代碼可以安裝成功

sudo pip3 install tensorflow-1.13.1-cp37-none-linux_armv7l.whl

• 運行以下程序檢驗環境是否安裝成功

import tensorflow as tf
hello = tf.constant(“Hello, World!”)
sess = tf.Session()
print(sess.run(hello))

• 解決numpy和h5py的依賴

sudo apt install libatlas-base-dev
sudo apt install libhdf5-dev
sudo apt install python-h5py

• 安裝numpy和h5py

sudo pip3 install h5py
sudo pip3 install numpy

• 配置opencv2環境

sudo apt-get install build-essential cmake git pkg-config
sudo apt install build-essential cmake git pkg-config libgtk-3-dev libcanberra-gtk*
sudo apt install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev libxvidcore-dev libx264-dev
sudo apt install libjpeg-dev libpng-dev libtiff-dev gfortran openexr libatlas-base-dev opencl-headers
sudo apt install python3-dev python3-numpy libtbb2 libtbb-dev libdc1394-22-dev
sudo apt-get install libjpeg8-dev
sudo apt-get install libtiff5-dev
sudo apt-get install libjasper-dev
sudo apt-get install libpng12-dev
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
sudo apt-get install libgtk2.0-dev
sudo apt-get install libatlas-base-dev gfortran

• 安裝opencv2

// 下載OpenCV
sudo apt-get install libopencv-dev
sudo apt-get install python-opencv

 

二、程序分析

• 項目文件結構，生成模型放置在model文件夾，測試數據集在testimage，訓練數據集在trainimage，mnist.py為訓練模型程序，main.py為部署模型程序

• mnist.py部分程序分析
• 導入庫（使用tensorflow框架）

# -*- coding: UTF-8 -*-
import tensorflow as tf
import tensorflow.keras as keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Flatten, Dense, Conv2D, MaxPooling2D, Dropout, MaxPool2D
from tensorflow.keras.datasets import mnist
from tensorflow.keras import backend as K
import json

 

• 設置參數（batch_size為每次訓練所選取的樣本數，epochs為訓練次數）

# 設置參數
batch_size = 128
num_classes = 10
epochs = 10
 
# 輸入數據維度
img_rows, img_cols = 28, 28

 

• 構造神經網絡模型（損失函數使用交叉熵損失函數，優化器使用adam，衡量模型指標為准確率）

# 構建網絡
model = Sequential()
# 第一個卷積層，32個卷積核，大小５x5，卷積模式SAME,激活函數relu,輸入張量的大小
model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same', activation='relu',
                 input_shape=(28, 28, 1)))
model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same', activation='relu'))
# 池化層,池化核大小２x2
model.add(MaxPool2D(pool_size=(2, 2)))
# 隨機丟棄四分之一的網絡連接，防止過擬合
model.add(Dropout(0.25))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same', activation='relu'))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same', activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.25))
# 全連接層,展開操作，
model.add(Flatten())
# 添加隱藏層神經元的數量和激活函數
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.25))
# 輸出層
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

• 模型及其參數保存（保存格式為h5）

with open('model.json', 'w') as outfile:
    json.dump(model.to_json(), outfile)
 
model_file = 'model.h5'
model.save(model_file)

 

• 部署模型程序分析
• 導入庫（numpy、tensorflow、matplotlib、cv2、picamera）

# -*- coding: UTF-8 -*-
import numpy as np
import tensorflow as tf
import tensorflow.keras as keras
from tensorflow.keras.preprocessing.image import img_to_array, load_img
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from PIL import Image
import cv2
import os
from picamera import PiCamera
from time import sleep

 

• 加載模型model.h5

#load model
model_file = './model/model.h5'
model_file = model_file
print(type(model_file))
global model
model = keras.models.load_model(model_file)

 

• 調用picamera庫來連接樹莓派的攝像頭，並通過攝像頭拍攝一張分辨率為480*480的圖片，將其保存至“/home/pi/Desktop/camera/tf_keras_mnist/image_28.jpg”

# 調用打開攝像頭庫
camera = PiCamera()
# 設置照片分辨率為480*480
camera.resolution = (480, 480)
camera.start_preview()
sleep(2)
camera.capture('/home/pi/Desktop/camera/tf_keras_mnist/image_28.jpg')
camera.stop_preview()
print("Collect Image Finish!")
img_file = './image_28.jpg'

 

• 讀取“./image_28.jpg”位置的圖片，並將其分辨率更改為28*28，使得滿足模型參數輸入要求

img_array = cv2.imread(img_file, cv2.IMREAD_GRAYSCALE)
resized_image = cv2.resize(img_array, (28, 28))
 
img = Image.fromarray(np.uint8(resized_image))
img.save('output.jpg')
img = mpimg.imread(img_file)

 

• 把28*28分辨率的圖片通過img_to_array把其矩陣中的參數由整數值變為浮點數的數組，再把所得數組放進已訓練好的模型中，最后將會輸出一個預測值

img = img_to_array(load_img(img_file, target_size=(28, 28), color_mode="grayscale")) / 255.
img = np.expand_dims(img, axis=0)
code = model.predict_classes(img)[0]
print("Predict Result: ", code)

 

 全代碼區

# -*- coding: UTF-8 -*-
import numpy as np
import tensorflow as tf
import tensorflow.keras as keras
from tensorflow.keras.preprocessing.image import img_to_array, load_img
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from PIL import Image
import cv2
import os
from picamera import PiCamera
from time import sleep

#load model
model_file = './model/model.h5'
model_file = model_file
print(type(model_file))
global model
model = keras.models.load_model(model_file)


def preditc():
    print("Get ready to capture images and place the camera")
    count = 5
    while count >= 1:
        print("Count Down: ", count, "s")
        count = count - 1
        sleep(1)

    # 調用打開攝像頭庫
    camera = PiCamera()
    # 設置照片分辨率為480*480
    camera.resolution = (480, 480)
    camera.start_preview()
    sleep(2)
    camera.capture('/home/pi/Desktop/camera/tf_keras_mnist/image_28.jpg')
    camera.stop_preview()
    print("Collect Image Finish!")
    img_file = './image_28.jpg'

    img_array = cv2.imread(img_file, cv2.IMREAD_GRAYSCALE)
    resized_image = cv2.resize(img_array, (28, 28))

    img = Image.fromarray(np.uint8(resized_image))
    img.save('output.jpg')
    img = mpimg.imread(img_file)

    img = img_to_array(load_img(img_file, target_size=(28, 28), color_mode="grayscale")) / 255.
    img = np.expand_dims(img, axis=0)
    code = model.predict_classes(img)[0]
    print("Predict Result: ", code)

    plt.imshow(np.real(img).squeeze())
    plt.show()


# 主函數
if __name__ == '__main__':
    preditc()