『AI达人创造营』基于PaddleHub实现常见鱼类分类及微信小程序部署

# 解压缩数据!unzip -oq -d images data/data103322/images.zip

# 数据加载和预处理import osimport paddleimport numpy as npimport paddlehub.vision.transforms as T# 定义数据集class FishDataset(paddle.io.Dataset):
    def __init__(self, dataset_dir, transforms, mode='train'):
        # 数据集存放路径
        self.dataset_dir = dataset_dir        # 数据增强
        self.transforms = transforms        # 分类数
        self.label_lst = []
        self.num_classes= self.get_label()
        self.mode = mode        # 根据mode读取对应的数据集
        if self.mode == 'train':
            self.file = 'train_list.txt'
        elif self.mode == 'test':
            self.file = 'test_list.txt'
        else:
            self.file = 'validate_list.txt'
        self.file = os.path.join(self.dataset_dir, self.file)        with open(self.file, 'r') as f:
            self.data = f.read().split('\n')[:-1]    
    def get_label(self):
        # 获取分类数
        with open(os.path.join(dataset_dir, 'label_list.txt'), 'r') as f:
            labels = f.readlines()        for idx, label in enumerate(labels):
            dic = {}
            dic['label_name'] = label.split('\n')[0]
            dic['label_id'] = idx
            self.label_lst.append(dic)        return len(self.label_lst)    def __getitem__(self, idx):
        img_path, label = self.data[idx].split(' ')
        img_path = os.path.join(self.dataset_dir, img_path)
        im = self.transforms(img_path)        return im, int(label)    
    def __len__(self):
        return len(self.data)# 定义数据增强train_Transforms = T.Compose([
                T.Resize((256, 256)),
                T.CenterCrop(224),
                T.RandomHorizontalFlip(),
                T.Normalize()
                ], to_rgb=True)
eval_Transforms = T.Compose([
                T.Resize((256, 256)),
                T.CenterCrop(224),
                T.Normalize()
                ], to_rgb=True)# 读取数据集dataset_dir = 'images/images'fish_train = FishDataset(dataset_dir, train_Transforms)
fish_validate = FishDataset(dataset_dir, eval_Transforms, mode='validate')print('训练集的图片数量: {}'.format(len(fish_train)))print('验证集的图片数量: {}'.format(len(fish_validate)))print('分类数: {}'.format(len(fish_train.label_lst)))

# label_id转labelid2label = {}for i in fish_train.label_lst:
     id2label[i['label_id']] = i['label_name']print(id2label)

# 鱼类英文名转中文en2zh = {'Cuttlefish': '墨鱼', 'Turbot': '多宝鱼', 'Hairtail': '带鱼', 'Grouper': '石斑鱼', 'Saury': '秋刀鱼', 'Octopus': '章鱼', 'Red_fish': '红鱼', 'Tilapia_mossambica': '罗非鱼', 'Variegated_carp': '胖头鱼', 'Grass_Carp': '草鱼', 'Silverfish': '银鱼', 'Herring': '青鱼', 'Horsehead_fish': '马头鱼', 'Squid': '鱿鱼', 'Catfish': '鲇鱼', 'Perch': '鲈鱼', 'Abalone': '鲍鱼', 'Salmon': '鲑鱼', 'Silver_carp': '鲢鱼', 'Carp': '鲤鱼', 'Crucian_carp': '鲫鱼', 'Silvery_pomfret': '鲳鱼', 'Bream': '鲷鱼', 'Plaice': '鲽鱼', 'Parabramis_pekinensis': '鳊鱼', 'Eel': '鳗鱼', 'Yellow_croaker': '黄鱼', 'Ricefield_eel': '黄鳝', 'Snakehead': '黑鱼', 'Bibcock_fish': '龙头鱼'}print(en2zh)

from PIL import Imageimport matplotlib.pyplot as plt

path = 'images/images/train'plt.figure(figsize=(30, 8))for idx, name in enumerate(en2zh.keys()):    for fpath, dirname, fname in os.walk(os.path.join(path, name)):
        plt.subplot(3, 10, idx+1)
        img = Image.open(os.path.join(fpath, fname[0]))
        plt.title(name)
        plt.imshow(img)

import paddlefrom paddle.vision.models import resnet50# 设置pretrained参数为True，可以加载resnet50在imagenet数据集上的预训练模型model = paddle.Model(resnet50(pretrained=True, num_classes=len(fish_train.label_lst)))

from paddle.optimizer import Momentumfrom paddle.regularizer import L2Decayfrom paddle.nn import CrossEntropyLossfrom paddle.metric import Accuracy# 配置优化器optimizer = Momentum(learning_rate=0.001,
                     momentum=0.9,
                     weight_decay=L2Decay(1e-4),
                     parameters=model.parameters())# 进行训练前准备model.prepare(optimizer, CrossEntropyLoss(), Accuracy(topk=(1, 5)))# 启动训练model.fit(fish_train,
          fish_validate,
          epochs=50,
          batch_size=8,
          save_dir="./output")

if not os.path.exists('final'):
    os.mkdir('final')# 将final.pdparams复制到final文件夹!cp output/final.pdparams final

# 模型评估，根据prepare接口配置的loss和metric进行返回result = model.evaluate(fish_validate)print(result)

# 批量预测from paddle.static import InputSpec# 加载final模型参数inputs = InputSpec([None, 1*1*3*224*224], 'float32', 'x')
labels = InputSpec([None, 30], 'int32', 'x')
model = paddle.Model(resnet50(num_classes=len(fish_train.label_lst)), inputs, labels)# 加载模型参数model.load('final/final.pdparams')# 定义优化器optimizer = Momentum(learning_rate=0.001,
                     momentum=0.9,
                     weight_decay=L2Decay(1e-4),
                     parameters=model.parameters())# 进行预测前准备model.prepare(optimizer, CrossEntropyLoss(), Accuracy(topk=(1, 5)))# 加载测试集数据fish_test = FishDataset(dataset_dir, eval_Transforms, mode='test')# 进行预测操作result = model.predict(fish_test)# 定义画图方法def show_img(idx, predict):
    with open(os.path.join(dataset_dir, 'test_list.txt')) as f:
        data = f.readlines()
    plt.figure()    print('predict: {}'.format(predict))
    img = Image.open(os.path.join(dataset_dir, data[idx].split()[0]))
    plt.imshow(img)
    plt.show()# 抽样展示indexs = [2, 15, 38, 100]for idx in indexs:
    show_img(idx, en2zh[id2label[np.argmax(result[0][idx])]])

# 单张图片预测# 读取单张图片image = paddle.to_tensor(fish_test[80][0]).reshape([1, 1, 3, 224, 224])
image_id = 80# 单张图片预测result = model.predict(image)# 可视化结果show_img(image_id, en2zh[id2label[np.argmax(result)]])

! tree work/

!pip install --upgrade paddlehub

# 安装模型!hub install work/fish_predict/

# 预测import paddlehub as hub
my_fish_predict = hub.Module(name="fish_predict")
my_fish_predict.fish_predict('images/images/test/Hairtail/137.jpg')

# 通过POST请求实现预测import requestsimport jsonimport cv2import base64def cv2_to_base64(image):
    data = cv2.imencode('.png', image)[1]    return base64.b64encode(data.tobytes()).decode('utf-8')# 发送HTTP请求data = {'img_b64': cv2_to_base64(cv2.imread("images/images/test/Hairtail/137.jpg"))}
headers = {"Content-type": "application/json",           "Connection": "close"}
url = "http://0.0.0.0:8866/predict/fish_predict"r = requests.post(url=url, headers=headers, data=json.dumps(data))# 打印预测结果print(r)print(r.json()['results'].encode('utf-8').decode('unicode_escape'))

<br/>