在AWS上部署简单的目标检测项目
- 前提条件
- 实验环境
- 下载相关库
- 项目结构
- 具体步骤
- 创建项目结构
- 编写py文件
- 编写HTML文件
- 运行项目
前提条件
- 掌握创建一个AWS EC2实例
- 掌握使用SSH连接AWS虚机
- 掌握在AWS上部署Flask项目，并用外网访问
- 知道Python实现一个简单的目标检测
实验环境
- Ubuntu 16.04 LTS
- Python 3.5.2
- Tesorflow 2.3.0
- Flask 1.1.1
- Numpy 1.18.5
- Opencv 3.4.2
下载相关库
sudo pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple numpy==1.18.5
sudo pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple opencv-python==3.4.2.16 opencv-contrib-python==3.4.2.16
sudo pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple flask
sudo pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow==2.3.0
项目结构
├─Flask_obj_detection
│ ├─static
│ │ └─images
│ │ └─LeNet_classify_model.h5
│ ├─templates
│ │ └─upload.html
│ │ └─upload_success.html
│ ├─flask_app.py
│ ├─SelectSearch.py
具体步骤
创建项目结构
mkdir Flask_obj_detection
cd Flask_obj_detection
mkdir static templates
cd static
mkdir images
编写py文件
vi SelectSearch.py
其内容如下：
import sys
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import os
def detect(path,detected_path,weight_path):
# 读取图片
img = cv2.imread(path)
# print(img)
# 按比例缩放图片
newHeight = 200
newWidth = int( img.shape[1] * 200 / img.shape[0] )
img = cv2.resize( img, (newWidth, newHeight) )
# 创建选择性搜索分割对象
ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()
# 设置输入图像，我们将运行分割
ss.setBaseImage( img )
# 快速但低召回选择性搜索方法
ss.switchToSelectiveSearchFast()
# 高召回但慢选择性搜索方法
# ss.switchToSelectiveSearchQuality()
# 运行选择性搜索分割输入图像
rects = ss.process()
# print(rects)
# print( 'Total Number of Region Proposals: {}'.format( len( rects ) ) )
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck']
# 加载创建完全相同的模型，包括其权重和优化程序
loaded_model = tf.keras.models.load_model(weight_path)
while True:
# 创建原始图像的副本
new_img = img.copy()
# print(new_img)
region_score = []
max_rect = 0
max_name = ""
max_score = 0
# 重复所有的区域建议
for i, rect in enumerate( rects ):
x, y, w, h = rect # 预测框的左上角坐标(x,y)以及框的宽w,高h
pre_img = new_img[y:y+h,x:x+w]
pre_img = cv2.resize(pre_img,(32,32))
pre_img = (np.expand_dims(pre_img,0))
# 输入的图片维度为(1,32,32,3)
pred_arr = loaded_model.predict(pre_img)
# 预测标签
pre_label = np.argmax(pred_arr[0])
# 预测得分
score = np.max(pred_arr[0])
# 预测类名
class_name = class_names[pre_label]
if score > max_score:
max_rect = rect
max_name = class_name
max_score = score
# region_score.append([rect,class_name,score])
print([max_rect,max_name,max_score])
x,y,w,h = max_rect
# cv2.rectangle(new_img, (x, y), (x + w, y + h), (0, 255, 0), 1, cv2.LINE_AA )
cv2.rectangle(new_img, (x, y), (x + w, y + h), (0, 255, 0), 2, cv2.LINE_AA)
font = cv2.FONT_HERSHEY_SIMPLEX
text = max_name+" "+str(max_score*100)[0:4]+"%"
cv2.putText(new_img, text, (x, y-5), font, 0.5, (0,0,255), 2)
# 显示输出
# cv2.imshow("Output", new_img)
cv2.imwrite(detected_path, new_img)
break
# 等待按键输入
# k = cv2.waitKey( 0 ) & 0xFF
# q键
# if k == 113:
# break
# 关闭所有窗口
cv2.destroyAllWindows()
vi flask_app.py
其内容如下：
from flask import (Flask, render_template, request, flash, redirect, url_for, make_response, jsonify)
from werkzeug.utils import secure_filename
import os
import time
from datetime import timedelta
from SelectSearch import detect
ALLOWED_EXTENSIONS = set(["png","jpg","JPG","PNG", "bmp"])
def is_allowed_file(filename):
return '.' in filename and filename.rsplit('.', 1)[1] in ALLOWED_EXTENSIONS
app = Flask(__name__)
# 静态文件缓存过期时间
app.send_file_max_age_default = timedelta(seconds=1)
@app.route("/upload",methods = ['POST', 'GET'])
def upload():
if request.method == "POST":
f = request.files['file']
if not ( f and is_allowed_file(f.filename)):
return jsonify({
"error":1001, "msg":"请检查上传的图片类型，仅限于png、PNG、jpg、JPG、bmp"
})
basepath = os.path.dirname(__file__)
upload_path = os.path.join(basepath, "static/images",secure_filename(f.filename))
f.save(upload_path)
img_path = upload_path
detected_path = os.path.join(basepath, "static/images", "output" + secure_filename(f.filename))
weight_path = os.path.join(basepath, "static", "LeNet_classify_model.h5")
print(upload_path,detected_path)
detect(img_path,detected_path,weight_path)
# return render_template("upload_ok.html", userinput = user_input, val1=time.time(), path = detected_path)
path = "./images/" + "output" + secure_filename(f.filename)
print(path)
return render_template("upload_success.html", path = path, val1 = time.time()) #渲染模板，显示图片检测结果
return render_template("upload.html", path = "./images/test.jpg")
if __name__ == "__main__":
app.run(host='0.0.0.0', port=5000)
编写HTML文件
vi upload.html
其内容如下：
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>目标检测</title>
</head>
<body align="center">
<h1>目标检测</h1>
<img src="{{ url_for('static', filename= path,_t=val1) }}" width="400" height="400" alt="图片"/>
<form action="" enctype='multipart/form-data' method='POST'>
<input type="file" name="file" style="margin-top:20px;"/>
<input type="submit" value="检测图片" class="button-new" style="margin-top:15px;"/>
</form>
</body>
</html>
vi upload_success.html
其内容如下：
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>目标检测</title>
</head>
<body align="center">
<h1>目标检测</h1>
<img src="{{ url_for('static', filename= path,_t=val1) }}" width="400" height="400" alt="图片"/>
<form action="" enctype='multipart/form-data' method='POST'>
<input type="file" name="file" style="margin-top:20px;"/>
<input type="submit" value="检测图片" class="button-new" style="margin-top:15px;"/>
</form>
</body>
</html>
运行项目
python3 flask_app.py
# 或者
export FLASK_APP=flask_app.py
flask run --host=0.0.0.0
