基于pytorch水果图像识别系统，数据集使用Fruits 360,并将训练好的模型应用到图片识别界面中，具体代码实现

好的，这里给出一个基于 PyTorch 的水果图像识别系统的代码实现，包含数据集的下载、数据预处理、模型训练和应用到图片识别界面中。代码中使用的数据集为 Fruits 360，模型为 ResNet18。

### 1. 下载数据集

!wget https://github.com/Horea94/Fruit-Images-Dataset/archive/master.zip -O fruits.zip
!unzip fruits.zip

### 2. 数据预处理

import os
from PIL import Image
from torchvision import transforms

data_dir = './Fruit-Images-Dataset-master/Training'
classes = os.listdir(data_dir)
num_classes = len(classes)

class FruitDataset(Dataset):
    def __init__(self, data_dir, classes, transform=None):
        self.data_dir = data_dir
        self.classes = classes
        self.transform = transform
        self.images = []
        self.labels = []
        
        for i, cls in enumerate(classes):
            cls_dir = os.path.join(data_dir, cls)
            for img_name in os.listdir(cls_dir):
                img_path = os.path.join(cls_dir, img_name)
                self.images.append(img_path)
                self.labels.append(i)
    
    def __len__(self):
        return len(self.images)
    
    def __getitem__(self, idx):
        img_path = self.images[idx]
        label = self.labels[idx]
        img = Image.open(img_path)
        if self.transform:
            img = self.transform(img)
        return img, label

transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

train_dataset = FruitDataset(data_dir, classes, transform)
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=4)

### 3. 模型训练

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.models import resnet18

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

model = resnet18(pretrained=True)
model.fc = nn.Linear(512, num_classes)
model.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

num_epochs = 10

for epoch in range(num_epochs):
    running_loss = 0.0
    for i, (inputs, labels) in enumerate(train_loader):
        inputs = inputs.to(device)
        labels = labels.to(device)

        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

print('Finished Training')

### 4. 应用到图片识别界面中

import numpy as np
import matplotlib.pyplot as plt
from PIL import Image

model.eval()

img_path = './Fruit-Images-Dataset-master/Test/Apple Braeburn/26_100.jpg'
img = Image.open(img_path)
img = transform(img).unsqueeze(0)
img = img.to(device)

with torch.no_grad():
    outputs = model(img)
    _, predicted = torch.max(outputs.data, 1)

plt.imshow(np.array(Image.open(img_path)))
plt.title(classes[predicted.item()])
plt.show()

以上就是一个基于 PyTorch 的水果图像识别系统的完整代码实现。注意，由于该数据集的类别较多，所以模型训练需要较长时间，可以根据自己的需求适当调整训练时的参数。