.item

[LotusWhu]

{'trade_off': 1.0, 'name': 'JAN'}
Traceback (most recent call last):
File "train.py", line 288, in
transfer_classification(config)
File "train.py", line 222, in transfer_classification
print image_classification_test(dset_loaders["target"], nn.Sequential(base_network, bottleneck_layer, classifier_layer), test_10crop=prep_dict["target"]["test_10crop"], gpu=use_gpu)
File "train.py", line 107, in image_classification_test
accuracy = torch.sum(torch.squeeze(predict).float() == all_label).item() / float(all_label.size()[0])
AttributeError: 'int' object has no attribute 'item'

when I remove the .item(), it works well, just wondering anyone meet the similar issue.

[sy565612345]

It may be an issue of different pytorch versions.
When you use lower versions, the result is an int so you should remove '.item()'.
But the same result may become a tensor in higher version, and you will need '.item()'.