图片数据的读取

最新推荐文章于 2024-05-27 16:57:33 发布

ErrorMaker...

最新推荐文章于 2024-05-27 16:57:33 发布

阅读量177

点赞数

分类专栏： pytorch 文章标签：深度学习 python pytorch

本文链接：https://blog.csdn.net/qq_22667507/article/details/120538730

版权

pytorch 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

#训练数据增强，测试和验证数据只需转化为tensor

train_transform = transforms.Compose([transforms.Resize((224,224)),
                                         transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, -.406],[0.229, 0.224, 0.225])])
test_transform = transforms.Compose([transforms.Resize((224,224)),transforms.ToTensor(),])

batch_size = 128

train_set = DatasetFolder("food-11/training/labeled", loader=lambda x: Image.open(x), extensions="jpg", transform=train_transform)
valid_set = DatasetFolder("food-11/validation", loader=lambda x: Image.open(x), extensions="jpg", transform=test_transform)
unlabeled_set = DatasetFolder("food-11/training/unlabeled", loader=lambda x: Image.open(x), extensions="jpg", transform=train_transform)
test_set = DatasetFolder("food-11/testing", loader=lambda x: Image.open(x), extensions="jpg", transform=test_transform)

# Construct data loaders.
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True, num_workers=0, pin_memory=True)
valid_loader = DataLoader(valid_set, batch_size=batch_size, shuffle=True, num_workers=0, pin_memory=True)
test_loader = DataLoader(test_set, batch_size=batch_size, shuffle=False)