如何将自定义图像数据集及对应CSV标签载入PyTorch或Keras
自定义数据集加载实现方案
前提说明:假设你的标签CSV结构为文件名,标签两列,训练图像文件夹、训练标签CSV、测试图像文件夹、测试标签CSV路径已提前配置。
方案1:Keras/TensorFlow 实现
直接封装load_data函数即可实现你想要的调用效果,代码示例如下:
import os import cv2 import pandas as pd import numpy as np def load_custom_data(train_img_dir, train_label_path, test_img_dir, test_label_path, img_size=(28,28), is_grayscale=True): # 加载训练集 train_label_df = pd.read_csv(train_label_path) train_images = [] train_labels = [] for _, row in train_label_df.iterrows(): img_path = os.path.join(train_img_dir, row['filename']) # 读入图片 if is_grayscale: img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE) else: img = cv2.cvtColor(cv2.imread(img_path), cv2.COLOR_BGR2RGB) # 统一尺寸 img = cv2.resize(img, img_size) train_images.append(img) train_labels.append(row['label']) # 转成numpy数组,和MNIST返回格式对齐 train_images = np.array(train_images) train_labels = np.array(train_labels) # 加载测试集逻辑和训练集完全一致 test_label_df = pd.read_csv(test_label_path) test_images = [] test_labels = [] for _, row in test_label_df.iterrows(): img_path = os.path.join(test_img_dir, row['filename']) if is_grayscale: img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE) else: img = cv2.cvtColor(cv2.imread(img_path), cv2.COLOR_BGR2RGB) img = cv2.resize(img, img_size) test_images.append(img) test_labels.append(row['label']) test_images = np.array(test_images) test_labels = np.array(test_labels) return (train_images, train_labels), (test_images, test_labels)
调用方式和你想要的MNIST加载逻辑完全一致:
# 替换成你自己的路径 TRAIN_IMG_DIR = r"你的训练图像文件夹路径" TRAIN_LABEL_PATH = r"你的训练标签CSV路径" TEST_IMG_DIR = r"你的测试图像文件夹路径" TEST_LABEL_PATH = r"你的测试标签CSV路径" (train_images, train_labels), (test_images, test_labels) = load_custom_data( TRAIN_IMG_DIR, TRAIN_LABEL_PATH, TEST_IMG_DIR, TEST_LABEL_PATH )
方案2:PyTorch 实现
你可以继承PyTorch的Dataset类封装自定义数据集,再封装加载函数即可:
import os import cv2 import pandas as pd from torch.utils.data import Dataset, DataLoader class CustomImageDataset(Dataset): def __init__(self, img_dir, label_path, img_size=(28,28), is_grayscale=True, transform=None): self.img_dir = img_dir self.label_df = pd.read_csv(label_path) self.img_size = img_size self.is_grayscale = is_grayscale self.transform = transform def __len__(self): return len(self.label_df) def __getitem__(self, idx): img_path = os.path.join(self.img_dir, self.label_df.iloc[idx, 0]) if self.is_grayscale: image = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE) else: image = cv2.cvtColor(cv2.imread(img_path), cv2.COLOR_BGR2RGB) image = cv2.resize(image, self.img_size) label = self.label_df.iloc[idx, 1] if self.transform: image = self.transform(image) return image, label def load_custom_data(train_img_dir, train_label_path, test_img_dir, test_label_path, batch_size=32, transform=None): train_dataset = CustomImageDataset(train_img_dir, train_label_path, transform=transform) test_dataset = CustomImageDataset(test_img_dir, test_label_path, transform=transform) train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True) test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False) return train_loader, test_loader
调用方式:
# 替换成你自己的路径 TRAIN_IMG_DIR = r"你的训练图像文件夹路径" TRAIN_LABEL_PATH = r"你的训练标签CSV路径" TEST_IMG_DIR = r"你的测试图像文件夹路径" TEST_LABEL_PATH = r"你的测试标签CSV路径" train_loader, test_loader = load_custom_data(TRAIN_IMG_DIR, TRAIN_LABEL_PATH, TEST_IMG_DIR, TEST_LABEL_PATH)
如果不需要DataLoader,也可以参考Keras的实现逻辑直接返回张量格式的训练、测试数据和标签,和MNIST的调用格式完全对齐。
另外你之前写的代码存在缩进错误,img_array = cv2.imread(...)这行需要缩进在第二层for循环内,否则会报错。
内容的提问来源于stack exchange,提问作者Chi Tung Wong
相关产品推荐
相关产品推荐

