大部分的pytorch入門教程，都是使用torchvision裡面的資料進行訓練和測試。如果我們是自己的圖片資料，又該怎麼做呢？

一、我的資料

我在學習的時候，使用的是fashion-mnist。這個資料比較小，我的電腦沒有GPU，還能吃得消。關於fashion-mnist資料，可以百度，也可以 點此 瞭解一下，資料就像這個樣子：

但是下載下來是一種二進位制檔案，並不是圖片，因此我先轉換成了圖片。

我先解壓gz檔案到e:/fashion_mnist/資料夾

然後執行程式碼：

import os
from skimage import io
import torchvision.datasets.mnist as mnist

root
 
="E:/fashion_mnist/"
train_set = (
    mnist.read_image_file(os.path.join(root, 'train-images-idx3-ubyte')),
    mnist.read_label_file(os.path.join(root, 'train-labels-idx1-ubyte'))
        )
test_set = (
    mnist.read_image_file(os.path.join(root, 't10k-images-idx3-ubyte')),
    mnist.read_label_file(os.path.join(root, 
 
't10k-labels-idx1-ubyte'))
        )
print("training set :",train_set[0].size())
print("test set :",test_set[0].size())

def convert_to_img(train=True):
    if(train):
        f=open(root+'train.txt','w')
        data_path=root+'/train/'
        if(not os.path.exists(data_path)):
            os.makedirs(data_path)
        
 
for i, (img,label) in enumerate(zip(train_set[0],train_set[1])):
            img_path=data_path+str(i)+'.jpg'
            io.imsave(img_path,img.numpy())
            f.write(img_path+' '+str(label)+'\n')
        f.close()
    else:
        f = open(root + 'test.txt', 'w')
        data_path = root + '/test/'
        if (not os.path.exists(data_path)):
            os.makedirs(data_path)
        for i, (img,label) in enumerate(zip(test_set[0],test_set[1])):
            img_path = data_path+ str(i) + '.jpg'
            io.imsave(img_path, img.numpy())
            f.write(img_path + ' ' + str(label) + '\n')
        f.close()

convert_to_img(True)
convert_to_img(False)

這樣就會在e:/fashion_mnist/目錄下分別生成train和test資料夾，用於存放圖片。還在該目錄下生成了標籤檔案train.txt和test.txt.

二、進行CNN分類訓練和測試

先要將圖片讀取出來，準備成torch專用的dataset格式，再通過Dataloader進行分批次訓練。

程式碼如下：

import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image
root="E:/fashion_mnist/"

# -----------------ready the dataset--------------------------
def default_loader(path):
    return Image.open(path).convert('RGB')
class MyDataset(Dataset):
    def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
        fh = open(txt, 'r')
        imgs = []
        for line in fh:
            line = line.strip('\n')
            line = line.rstrip()
            words = line.split()
            imgs.append((words[0],int(words[1])))
        self.imgs = imgs
        self.transform = transform
        self.target_transform = target_transform
        self.loader = loader

    def __getitem__(self, index):
        fn, label = self.imgs[index]
        img = self.loader(fn)
        if self.transform is not None:
            img = self.transform(img)
        return img,label

    def __len__(self):
        return len(self.imgs)

train_data=MyDataset(txt=root+'train.txt', transform=transforms.ToTensor())
test_data=MyDataset(txt=root+'test.txt', transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64)


#-----------------create the Net and training------------------------

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Sequential(
            torch.nn.Conv2d(3, 32, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2))
        self.conv2 = torch.nn.Sequential(
            torch.nn.Conv2d(32, 64, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2)
        )
        self.conv3 = torch.nn.Sequential(
            torch.nn.Conv2d(64, 64, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(2)
        )
        self.dense = torch.nn.Sequential(
            torch.nn.Linear(64 * 3 * 3, 128),
            torch.nn.ReLU(),
            torch.nn.Linear(128, 10)
        )

    def forward(self, x):
        conv1_out = self.conv1(x)
        conv2_out = self.conv2(conv1_out)
        conv3_out = self.conv3(conv2_out)
        res = conv3_out.view(conv3_out.size(0), -1)
        out = self.dense(res)
        return out


model = Net()
print(model)

optimizer = torch.optim.Adam(model.parameters())
loss_func = torch.nn.CrossEntropyLoss()

for epoch in range(10):
    print('epoch {}'.format(epoch + 1))
    # training-----------------------------
    train_loss = 0.
    train_acc = 0.
    for batch_x, batch_y in train_loader:
        batch_x, batch_y = Variable(batch_x), Variable(batch_y)
        out = model(batch_x)
        loss = loss_func(out, batch_y)
        train_loss += loss.data[0]
        pred = torch.max(out, 1)[1]
        train_correct = (pred == batch_y).sum()
        train_acc += train_correct.data[0]
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    print('Train Loss: {:.6f}, Acc: {:.6f}'.format(train_loss / (len(
        train_data)), train_acc / (len(train_data))))

    # evaluation--------------------------------
    model.eval()
    eval_loss = 0.
    eval_acc = 0.
    for batch_x, batch_y in test_loader:
        batch_x, batch_y = Variable(batch_x, volatile=True), Variable(batch_y, volatile=True)
        out = model(batch_x)
        loss = loss_func(out, batch_y)
        eval_loss += loss.data[0]
        pred = torch.max(out, 1)[1]
        num_correct = (pred == batch_y).sum()
        eval_acc += num_correct.data[0]
    print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(
        test_data)), eval_acc / (len(test_data))))

打印出來的網路模型：

訓練和測試結果：

原文連結

https://www.cnblogs.com/denny402/p/7520063.html