MLNT

MLNT copied to clipboard

when I run the main code with my dataset, it comes to this error: line 116, in train targets_fast[idx] = targets[neighbor[random.randint(1,num_neighbor)]] IndexError: index 5 is out of bounds for dimension...

refuserMa

how can I run this code in CIFAR data?

2

since the pretrain size is 224 but cifar size is 32, so, directly use this code would cause the out size error, could you please tell me how can I...

AllenPu

GPU runs out of memory with --batch_num=32

8

Could you please help me out? When I use --batch_num=32, I cannot run the code on a single GPU. My GPU is Tesla P100-SXM2 16G. I only can run the...

mehrdadshoeiby

能告诉一下您用的是哪个pytorch版本吗？

5

我试过了0.3.1, 0.4.1和最新版本，都出现不同程度的错误（都发生在main.py），谢谢

Wongcheukwai

Can't detach views in-place.

5

`RuntimeError: Can't detach views in-place. Use detach() instead` I have no idea why it can't detach views in-place. Any way to get around this problem? thanks! pytorch 1.3.1

Oasis1307

consistent_loss did not sum among the M synthetic noisy data ?

1

yuanwei0908

Dear author. Why are you updating class_loss and consistent_loss at the same time? In Algorithm1, it seems that its processing is decoupled. I'm sorry if I have misunderstood.

htmap

It seems that the current version do not contain iterative training? Or I miss it?

Liangqiong