[英]Dumping Image data and load using pytorch dataloader
I want to dump the data so that I can load it back for training my model.我想转储数据,以便可以将其加载回来以训练我的 model。
My code snipped for dumping the data:我的代码被截断以转储数据:
for batch_idx, (image, label) in enumerate(dataloader):
image, label = image.to(device), label.to(device)
perturbed_image = attack.perturb(image, label)
#---------- Classifier ----------
predict_A = classifier(perturbed_image)
pred_label = torch.max(predict_A.data, 1)[1]
if pred_label != label:
adv_data.append( (perturbed_image.to("cpu"), label.to("cpu")) )
Is there any other way I can dump it correctly so as to load it in the torch.utils.data.DataLoader
.有没有其他方法可以正确转储它以便将其加载到
torch.utils.data.DataLoader
中。
The most straight forward approach would be to use torch.save
to save the actual tensors of perturbed_image
and label
as binary files, and then use a custom Dataset
.最直接的方法是使用
torch.save
将perturbed_image
和label
的实际张量保存为二进制文件,然后使用自定义Dataset
。 Note that the saved tensors are not single image/label, but rather batches of images/labels.请注意,保存的张量不是单个图像/标签,而是成批的图像/标签。 Your new custom
Dataset
should account for it.您的新自定义
Dataset
应该考虑到它。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.