用python搭建一個花卉識別系統(tǒng)

更新時間：2021年06月19日 15:31:18 作者：python研究者

這學(xué)期修了一門機器視覺的選修課，課設(shè)要是弄一個花卉識別的神經(jīng)網(wǎng)絡(luò)，所以我網(wǎng)上找了開源代碼進行了修改，最后成功跑起來，結(jié)果只有一個準(zhǔn)確率（94%）既然都跑了這個神經(jīng)網(wǎng)絡(luò)的代碼，那么干脆就把這個神經(jīng)網(wǎng)絡(luò)真正的使用起來，把這個神經(jīng)網(wǎng)絡(luò)弄成一個可視化界面

一.開源神經(jīng)網(wǎng)絡(luò)(AlexNet)

1.獲取數(shù)據(jù)集

使用步驟如下：
* （1）在data_set文件夾下創(chuàng)建新文件夾"flower_data"
* （2）點擊鏈接下載花分類數(shù)據(jù)集download.tensorflow.org/example\_im…
* （3）解壓數(shù)據(jù)集到flower_data文件夾下
* （4）執(zhí)行"split_data.py"腳本自動將數(shù)據(jù)集劃分成訓(xùn)練集train和驗證集val

split_data.py

import os
from shutil import copy, rmtree
import random
 
 
def mk_file(file_path: str):
    if os.path.exists(file_path):
        # 如果文件夾存在，則先刪除原文件夾在重新創(chuàng)建
        rmtree(file_path)
    os.makedirs(file_path)
 
 
def main():
    # 保證隨機可復(fù)現(xiàn)
    random.seed(0)
 
    # 將數(shù)據(jù)集中10%的數(shù)據(jù)劃分到驗證集中
    split_rate = 0.1
 
    # 指向你解壓后的flower_photos文件夾
    cwd = os.getcwd()
    data_root = os.path.join(cwd, "flower_data")
    origin_flower_path = os.path.join(data_root, "flower_photos")
    assert os.path.exists(origin_flower_path)
    flower_class = [cla for cla in os.listdir(origin_flower_path)
                    if os.path.isdir(os.path.join(origin_flower_path, cla))]
 
    # 建立保存訓(xùn)練集的文件夾
    train_root = os.path.join(data_root, "train")
    mk_file(train_root)
    for cla in flower_class:
        # 建立每個類別對應(yīng)的文件夾
        mk_file(os.path.join(train_root, cla))
 
    # 建立保存驗證集的文件夾
    val_root = os.path.join(data_root, "val")
    mk_file(val_root)
    for cla in flower_class:
        # 建立每個類別對應(yīng)的文件夾
        mk_file(os.path.join(val_root, cla))
 
    for cla in flower_class:
        cla_path = os.path.join(origin_flower_path, cla)
        images = os.listdir(cla_path)
        num = len(images)
        # 隨機采樣驗證集的索引
        eval_index = random.sample(images, k=int(num*split_rate))
        for index, image in enumerate(images):
            if image in eval_index:
                # 將分配至驗證集中的文件復(fù)制到相應(yīng)目錄
                image_path = os.path.join(cla_path, image)
                new_path = os.path.join(val_root, cla)
                copy(image_path, new_path)
            else:
                # 將分配至訓(xùn)練集中的文件復(fù)制到相應(yīng)目錄
                image_path = os.path.join(cla_path, image)
                new_path = os.path.join(train_root, cla)
                copy(image_path, new_path)
            print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing bar
        print()
 
    print("processing done!")
 
 
if __name__ == '__main__':
    main()

2.神經(jīng)網(wǎng)絡(luò)模型

model.py

import torch.nn as nn
import torch
 
class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        # 用nn.Sequential()將網(wǎng)絡(luò)打包成一個模塊，精簡代碼
        self.features = nn.Sequential(   # 卷積層提取圖像特征
            nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[48, 55, 55]
            nn.ReLU(inplace=True), 									# 直接修改覆蓋原值，節(jié)省運算內(nèi)存
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[48, 27, 27]
            nn.Conv2d(48, 128, kernel_size=5, padding=2),           # output[128, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 13, 13]
            nn.Conv2d(128, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 128, kernel_size=3, padding=1),          # output[128, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 6, 6]
        )
        self.classifier = nn.Sequential(   # 全連接層對圖像分類
            nn.Dropout(p=0.5),			   # Dropout 隨機失活神經(jīng)元，默認比例為0.5
            nn.Linear(128 * 6 * 6, 2048),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            nn.Linear(2048, num_classes),
        )
        if init_weights:
            self._initialize_weights()
            
	# 前向傳播過程
    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)	# 展平后再傳入全連接層
        x = self.classifier(x)
        return x
        
	# 網(wǎng)絡(luò)權(quán)重初始化，實際上 pytorch 在構(gòu)建網(wǎng)絡(luò)時會自動初始化權(quán)重
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):                            # 若是卷積層
                nn.init.kaiming_normal_(m.weight, mode='fan_out',   # 用（何）kaiming_normal_法初始化權(quán)重
                                        nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)                    # 初始化偏重為0
            elif isinstance(m, nn.Linear):            # 若是全連接層
                nn.init.normal_(m.weight, 0, 0.01)    # 正態(tài)分布初始化
                nn.init.constant_(m.bias, 0)          # 初始化偏重為0

3.訓(xùn)練神經(jīng)網(wǎng)絡(luò)

train.py

# 導(dǎo)入包
import torch
import torch.nn as nn
from torchvision import transforms, datasets, utils
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim
from model import AlexNet
import os
import json
import time
 
# 使用GPU訓(xùn)練
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
with open(os.path.join("train.log"), "a") as log:
    log.write(str(device)+"\n")
 
#數(shù)據(jù)預(yù)處理
data_transform = {
    "train": transforms.Compose([transforms.RandomResizedCrop(224),       # 隨機裁剪，再縮放成 224×224
                                 transforms.RandomHorizontalFlip(p=0.5),  # 水平方向隨機翻轉(zhuǎn)，概率為 0.5, 即一半的概率翻轉(zhuǎn), 一半的概率不翻轉(zhuǎn)
                                 transforms.ToTensor(),
                                 transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),
 
    "val": transforms.Compose([transforms.Resize((224, 224)),  # cannot 224, must (224, 224)
                               transforms.ToTensor(),
                               transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}
 
#導(dǎo)入、加載 訓(xùn)練集
# 導(dǎo)入訓(xùn)練集
#train_set = torchvision.datasets.CIFAR10(root='./data', 	 # 數(shù)據(jù)集存放目錄
#										 train=True,		 # 表示是數(shù)據(jù)集中的訓(xùn)練集
#                                        download=True,  	 # 第一次運行時為True，下載數(shù)據(jù)集，下載完成后改為False
#                                        transform=transform) # 預(yù)處理過程
# 加載訓(xùn)練集                              
#train_loader = torch.utils.data.DataLoader(train_set, 	  # 導(dǎo)入的訓(xùn)練集
#										   batch_size=50, # 每批訓(xùn)練的樣本數(shù)
#                                          shuffle=False,  # 是否打亂訓(xùn)練集
#                                          num_workers=0)  # num_workers在windows下設(shè)置為0
 
 
# 獲取圖像數(shù)據(jù)集的路徑
data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  		# get data root path 返回上上層目錄
image_path = data_root + "/jqsj/data_set/flower_data/"  				 		# flower data_set path
 
# 導(dǎo)入訓(xùn)練集并進行預(yù)處理
train_dataset = datasets.ImageFolder(root=image_path + "/train",		
                                     transform=data_transform["train"])
train_num = len(train_dataset)
 
# 按batch_size分批次加載訓(xùn)練集
train_loader = torch.utils.data.DataLoader(train_dataset,	# 導(dǎo)入的訓(xùn)練集
                                           batch_size=32, 	# 每批訓(xùn)練的樣本數(shù)
                                           shuffle=True,	# 是否打亂訓(xùn)練集
                                           num_workers=0)	# 使用線程數(shù)，在windows下設(shè)置為0
 
#導(dǎo)入、加載 驗證集
# 導(dǎo)入驗證集并進行預(yù)處理
validate_dataset = datasets.ImageFolder(root=image_path + "/val",
                                        transform=data_transform["val"])
val_num = len(validate_dataset)
 
# 加載驗證集
validate_loader = torch.utils.data.DataLoader(validate_dataset,	# 導(dǎo)入的驗證集
                                              batch_size=32, 
                                              shuffle=True,
                                              num_workers=0)
 
# 存儲 索引：標(biāo)簽 的字典
# 字典，類別：索引 {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
# 將 flower_list 中的 key 和 val 調(diào)換位置
cla_dict = dict((val, key) for key, val in flower_list.items())
 
# 將 cla_dict 寫入 json 文件中
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
    json_file.write(json_str)
 
#訓(xùn)練過程
net = AlexNet(num_classes=5, init_weights=True)  	  # 實例化網(wǎng)絡(luò)（輸出類型為5，初始化權(quán)重）
net.to(device)									 	  # 分配網(wǎng)絡(luò)到指定的設(shè)備（GPU/CPU）訓(xùn)練
loss_function = nn.CrossEntropyLoss()			 	  # 交叉熵損失
optimizer = optim.Adam(net.parameters(), lr=0.0002)	  # 優(yōu)化器（訓(xùn)練參數(shù)，學(xué)習(xí)率）
 
save_path = './AlexNet.pth'
best_acc = 0.0
 
for epoch in range(150):
    ########################################## train ###############################################
    net.train()     					# 訓(xùn)練過程中開啟 Dropout
    running_loss = 0.0					# 每個 epoch 都會對 running_loss  清零
    time_start = time.perf_counter()	# 對訓(xùn)練一個 epoch 計時
    
    for step, data in enumerate(train_loader, start=0):  # 遍歷訓(xùn)練集，step從0開始計算
        images, labels = data   # 獲取訓(xùn)練集的圖像和標(biāo)簽
        optimizer.zero_grad()	# 清除歷史梯度
        
        outputs = net(images.to(device))				 # 正向傳播
        loss = loss_function(outputs, labels.to(device)) # 計算損失
        loss.backward()								     # 反向傳播
        optimizer.step()								 # 優(yōu)化器更新參數(shù)
        running_loss += loss.item()
        
        # 打印訓(xùn)練進度（使訓(xùn)練過程可視化）
        rate = (step + 1) / len(train_loader)           # 當(dāng)前進度 = 當(dāng)前step / 訓(xùn)練一輪epoch所需總step
        a = "*" * int(rate * 50)
        b = "." * int((1 - rate) * 50)
        with open(os.path.join("train.log"), "a") as log:
              log.write(str("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss))+"\n")
        print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")
    print()
    with open(os.path.join("train.log"), "a") as log:
              log.write(str('%f s' % (time.perf_counter()-time_start))+"\n")
    print('%f s' % (time.perf_counter()-time_start))
 
    ########################################### validate ###########################################
    net.eval()    # 驗證過程中關(guān)閉 Dropout
    acc = 0.0  
    with torch.no_grad():
        for val_data in validate_loader:
            val_images, val_labels = val_data
            outputs = net(val_images.to(device))
            predict_y = torch.max(outputs, dim=1)[1]  # 以output中值最大位置對應(yīng)的索引（標(biāo)簽）作為預(yù)測輸出
            acc += (predict_y == val_labels.to(device)).sum().item()    
        val_accurate = acc / val_num
        
        # 保存準(zhǔn)確率最高的那次網(wǎng)絡(luò)參數(shù)
        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)
        with open(os.path.join("train.log"), "a") as log:
              log.write(str('[epoch %d] train_loss: %.3f  test_accuracy: %.3f \n' %
              (epoch + 1, running_loss / step, val_accurate))+"\n")
        print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f \n' %
              (epoch + 1, running_loss / step, val_accurate))
with open(os.path.join("train.log"), "a") as log:
      log.write(str('Finished Training')+"\n")
print('Finished Training')

訓(xùn)練結(jié)果后，準(zhǔn)確率是94%

訓(xùn)練日志如下：

4.對模型進行預(yù)測

predict.py

import torch

接著對其中一個花卉圖片進行識別，其結(jié)果如下：

可以看到只有一個識別結(jié)果（daisy雛菊）和準(zhǔn)確率1.0是100%（范圍是0~1，所以1對應(yīng)100%）

為了方便使用這個神經(jīng)網(wǎng)絡(luò)，接著我們將其開發(fā)成一個可視化的界面操作

二、花卉識別系統(tǒng)搭建（flask）

1.構(gòu)建頁面：

2.調(diào)用神經(jīng)網(wǎng)絡(luò)模型

main.py

# coding:utf-8
 
from flask import Flask, render_template, request, redirect, url_for, make_response, jsonify
from werkzeug.utils import secure_filename
import os
import time
 
 
###################
#模型所需庫包
import torch
from model import AlexNet
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import json
 
# read class_indict
try:
    json_file = open('./class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)
 
# create model
model = AlexNet(num_classes=5)
# load model weights
model_weight_path = "./AlexNet.pth"
#, map_location='cpu'
model.load_state_dict(torch.load(model_weight_path, map_location='cpu'))
 
# 關(guān)閉 Dropout
model.eval()
 
###################
from datetime import timedelta
# 設(shè)置允許的文件格式
ALLOWED_EXTENSIONS = set(['png', 'jpg', 'JPG', 'PNG', 'bmp'])
 
def allowed_file(filename):
    return '.' in filename and filename.rsplit('.', 1)[1] in ALLOWED_EXTENSIONS
 
app = Flask(__name__)
# 設(shè)置靜態(tài)文件緩存過期時間
app.send_file_max_age_default = timedelta(seconds=1)
 
#圖片裝換操作
def tran(img_path):
     # 預(yù)處理
    data_transform = transforms.Compose(
        [transforms.Resize((224, 224)),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
 
    # load image
    img = Image.open("pgy2.jpg")
    #plt.imshow(img)
    # [N, C, H, W]
    img = data_transform(img)
    # expand batch dimension
    img = torch.unsqueeze(img, dim=0)
    return img
    
 
@app.route('/upload', methods=['POST', 'GET'])  # 添加路由
def upload():
    path=""
    if request.method == 'POST':
        f = request.files['file']
        if not (f and allowed_file(f.filename)):
            return jsonify({"error": 1001, "msg": "請檢查上傳的圖片類型，僅限于png、PNG、jpg、JPG、bmp"})
 
        basepath = os.path.dirname(__file__)  # 當(dāng)前文件所在路徑
        path = secure_filename(f.filename)
        upload_path = os.path.join(basepath, 'static/images', secure_filename(f.filename))  # 注意：沒有的文件夾一定要先創(chuàng)建，不然會提示沒有該路徑
        # upload_path = os.path.join(basepath, 'static/images','test.jpg')  #注意：沒有的文件夾一定要先創(chuàng)建，不然會提示沒有該路徑
        print(path)
 
        img = tran('static/images'+path)
        ##########################
        #預(yù)測圖片
        with torch.no_grad():
            # predict class
            output = torch.squeeze(model(img))     # 將輸出壓縮，即壓縮掉 batch 這個維度
            predict = torch.softmax(output, dim=0)
            predict_cla = torch.argmax(predict).numpy()
            res = class_indict[str(predict_cla)]
            pred = predict[predict_cla].item()
            #print(class_indict[str(predict_cla)], predict[predict_cla].item())
        res_chinese = ""
        if res=="daisy":
            res_chinese="雛菊"
        if res=="dandelion":
            res_chinese="蒲公英"
        if res=="roses":
            res_chinese="玫瑰"
        if res=="sunflower":
            res_chinese="向日葵"
        if res=="tulips":
            res_chinese="郁金香"
 
        #print('result:', class_indict[str(predict_class)], 'accuracy:', prediction[predict_class])
        ##########################
        f.save(upload_path)
        pred = pred*100
        return render_template('upload_ok.html', path=path, res_chinese=res_chinese,pred = pred, val1=time.time())
 
    return render_template('upload.html')
 
if __name__ == '__main__':
    # app.debug = True
    app.run(host='127.0.0.1', port=80,debug = True)

3.系統(tǒng)識別結(jié)果

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>李運辰-花卉識別系統(tǒng)v1.0</title>
	<link rel="stylesheet" type="text/css" href="../static/css/bootstrap.min.css" rel="external nofollow" >
	<link rel="stylesheet" type="text/css" href="../static/css/fileinput.css" rel="external nofollow" >
    <script src="../static/js/jquery-2.1.4.min.js"></script>
	
    <script src="../static/js/bootstrap.min.js"></script> 
	<script src="../static/js/fileinput.js"></script> 
	<script src="../static/js/locales/zh.js"></script> 
</head>
<body>
    <h1  align="center">李運辰-花卉識別系統(tǒng)v1.0</h1>
	<div align="center">
    <form action="" enctype='multipart/form-data' method='POST'>
        <input type="file" name="file" class="file"  data-show-preview="false" style="margin-top:20px;"/>
        <br>
        <input type="submit" value="上傳" class="button-new btn btn-primary" style="margin-top:15px;"/>
    </form>
	<p  style="size:15px;color:blue;">識別結(jié)果:{{res_chinese}}</p>
	</br>
	<p  style="size:15px;color:red;">準(zhǔn)確率:{{pred}}%</p>
    <img src="{{ './static/images/'+path }}" width="400" height="400" alt=""/>
	</div>
</body>
</html>