Coding-Party 基于飞桨的农作物智能识别系统

#!unzip /home/aistudio/data/data101323/data.zip

import paddleimport paddle.nn.functional as Fimport numpy as npimport cv2import jsonimport mathimport randomimport osfrom paddle.io import Dataset  # 导入Datasrt库filename = "AgriculturalDisease_trainingset/AgriculturalDisease_train_annotations.json"f_open = open(filename)
fileJson = json.load(f_open)

train_data = []for i in range(len(fileJson)):
    img1=cv2.imread("AgriculturalDisease_trainingset/images/"+fileJson[i]['image_id'])
    img2=cv2.resize(img1, (128,128), interpolation=cv2.INTER_AREA)/255
    r=[]
    g=[]
    b=[]

    r.append(img2[:, :, 0])
    g.append(img2[:, :, 1])
    b.append(img2[:, :, 2])

    one_data = np.concatenate((r,g,b),axis=0)
    one_data = paddle.to_tensor(one_data,dtype="float32")
    train_data.append([one_data,fileJson[i]['disease_class']])

filename = "AgriculturalDisease_validationset/AgriculturalDisease_validation_annotations.json"f_open = open(filename)
fileJson1 = json.load(f_open)
test_data = []for i in range(len(fileJson1)):

    img1=cv2.imread("AgriculturalDisease_validationset/images/"+fileJson1[i]['image_id'])
    img2=cv2.resize(img1, (128,128), interpolation=cv2.INTER_AREA)/255

    r=[]
    g=[]
    b=[]

    r.append(img2[:, :, 0])
    g.append(img2[:, :, 1])
    b.append(img2[:, :, 2])

    one_data = np.concatenate((r,g,b),axis=0)
    one_data = paddle.to_tensor(one_data,dtype="float32")
    test_data.append([one_data,fileJson1[i]['disease_class']])

from paddle.static import InputSpecimport paddle.nn.functional as Fprint("-------end readData--------")class MyDataset(Dataset):
    """
    步骤一：继承paddle.io.Dataset类
    """
    def __init__(self, mode='train'):
        """
        步骤二：实现构造函数，定义数据读取方式，划分训练和测试数据集
        """
        super(MyDataset, self).__init__()        if mode == 'train':
            self.data = train_data        else:
            self.data = test_data    def __getitem__(self, index):
        """
        步骤三：实现__getitem__方法，定义指定index时如何获取数据，并返回单条数据（训练数据，对应的标签）
        """
        data = self.data[index][0]
        label = self.data[index][1]        return data, label    def __len__(self):
        """
        步骤四：实现__len__方法，返回数据集总数目
        """
        return len(self.data)# s_tra_data,s_tra_label = split_data(train_data,train_label,batch_size=32)# s_tes_data,s_tes_label = split_data(test_data,test_label,batch_size=32)#数据读取train_loader = paddle.io.DataLoader(MyDataset("train"), batch_size=16, shuffle=True)
test_loader = paddle.io.DataLoader(MyDataset("test"), batch_size=16, shuffle=True)

epoch_num = 20 #训练轮数batch_size = 16 learning_rate = 0.0001 #学习率val_acc_history = []
val_loss_history = []def train(model):
    print('start training ... ')    # turn into training mode
    model.train()

    opt = paddle.optimizer.Adam(learning_rate=learning_rate,
                                parameters=model.parameters())    for epoch in range(epoch_num):
        acc_train = []        for batch_id, data in enumerate(train_loader()):
            x_data = data[0]
            y_data = paddle.to_tensor(data[1],dtype="int64")
            y_data = paddle.unsqueeze(y_data, 1)
            logits = model(x_data)
            loss = F.cross_entropy(logits, y_data)
            acc = paddle.metric.accuracy(logits, y_data)
            acc_train.append(acc.numpy())            if batch_id % 200 == 0 and batch_id != 0:                print("epoch: {}, batch_id: {}, loss is: {}".format(epoch, batch_id, loss.numpy()))
                avg_acc = np.mean(acc_train)                print("[train] accuracy: {}".format(avg_acc))
            loss.backward()
            opt.step()
            opt.clear_grad()        
        # evaluate model after one epoch
        model.eval()
        accuracies = []
        losses = []        for batch_id, data in enumerate(test_loader()):
            x_data = data[0]
            y_data = paddle.to_tensor(data[1],dtype="int64")
            y_data = paddle.unsqueeze(y_data, 1)

            logits = model(x_data)
            loss = F.cross_entropy(logits, y_data)
            acc = paddle.metric.accuracy(logits, y_data)
            accuracies.append(acc.numpy())
            losses.append(loss.numpy())

        avg_acc, avg_loss = np.mean(accuracies), np.mean(losses)        print("[test] accuracy/loss: {}/{}".format(avg_acc, avg_loss))
        val_acc_history.append(avg_acc)
        val_loss_history.append(avg_loss)
        model.train()

model = paddle.vision.models.resnet152(pretrained=True,num_classes=61)
train(model)  
path = "save_model"paddle.jit.save(model, path,input_spec=[InputSpec(shape=[16,3,128,128], dtype='float32')])