在 csv 中读取 PyTorch 中图像的标签答案

【问题标题】：Reading labels in csv for images in PyTorch在 csv 中读取 PyTorch 中图像的标签
【发布时间】：2021-07-05 22:13:33
【问题描述】：

我是 PyTorch 的新手。任务 - 创建训练、验证和测试类。

数据：

包含 2 列的 CSV 文件

其中 id 是存储在 train 和 test1 目录中的图片名称

到目前为止我的代码：

**import torch
import torch.nn as nn
import torch.optim as optim
import torch.utils.data
import torch.nn.functional as F
import torchvision
from torchvision import transforms
from PIL import Image
##transforms
transforms = transforms.Compose([
    transforms.Resize(64),
    transforms.ToTensor(),
    transforms.Normalize(mean = [0.485, 0.456, 0.406],
                        std = [0.229, 0.224, 0.225])
])
##dataloader
dataset_path = "C:/Users/nikit/OneDrive/Desktop/PyTorch/train/train"
dataset = torchvision.datasets.ImageFolder(root = train_data_path, transform = transforms)
val_split = 0.2
dataset_size = len(dataset)
val_size = int(test_split * dataset_size)
train_size = dataset_size - val_size
train_data, val_data = torch.utils.data.random_split(dataset, [train_size, test_size])
##define test 
test_data_path = "C:/Users/nikit/OneDrive/Desktop/PyTorch/test1/test1"
test_data = torchvision.datasets.ImageFolder(root = train_data_path, transform = transforms)
##data load
batch_size = 64
train_data_loader = torch.utils.data.DataLoader(train_data, batch_size = batch_size)
val_data_loader = torch.utils.data.DataLoader(val_data, batch_size = batch_size)
test_data_loader = torch.utils.data.DataLoader(test_data, batch_size = batch_size)**

请帮我将值与 csv 数据联系起来

【问题讨论】：

你读过tutorial for custom datasets吗？
对我来说没有多大意义
您必须实现自定义数据集。我建议你再读一遍。

标签： python machine-learning pytorch

【解决方案1】：

train_df = pd.DataFrame(columns=["img_name","label"])
train_df["img_name"] = os.listdir(path_train)
for idx, i in enumerate(os.listdir(path_train)):
    if "cat" in i:
        train_df["label"][idx] = 0
    if "dog" in i:
        train_df["label"][idx] = 1

train_df.to_csv (r'train_csv.csv', index = False, header=True)

【讨论】：