【Pytorch API笔记8】用torchvision.utils.save_image批量保存图像数据

将给定的Tensor保存成image文件。如果给定的是mini-batch tensor，那就用make-grid做成雪碧图，再保存。

例子：

import torch
import torchvision
from torchvision import datasets, transforms

def main():
    data_path = "./horse2zebra/images/"
    batch_size_per_gpu = 64
    normalize = transforms.Compose([
        transforms.ToTensor(),
    ])
    dataset = datasets.ImageFolder(data_path, transform=normalize)
    # sampler = torch.utils.data.DistributedSampler(dataset, shuffle=True)
    data_loader = torch.utils.data.DataLoader(
        dataset,
        batch_size=batch_size_per_gpu,
        num_workers=1,
    )
    image_batch, label_batch = next(iter(data_loader))
    torchvision.utils.save_image(image_batch, "./output_1.jpg")


# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    main()

将一个Batch内的数据，都保存下来，省的一个一个保存了。