ttt-plus-plus

ttt-plus-plus copied to clipboard

covariance function in cifar/discrepancy.py seems strange

2

I'm confused of how the covariance is calculated in the code, the result of covariance function is different from what np.cov gives. I'm sorry if I have misunderstood.

Cascol-Chen

Can you release the pre-train model of VisDA-C and corresponding test-time training code?

1

Can you release the pre-train model of VisDA-C and corresponding test-time training code?

Dyb3438

Multi-epoch training was performed on the test set.

1

There is a discrepancy about test-time adaptation in this code that has me wondering. When adaptation operation runs on the test set, [TTT](https://github.com/yueatsprograms/ttt_cifar_release/blob/master/test_calls/test_adapt.py) and [Tent](https://github.com/DequanWang/tent/blob/master/cifar10c.py) perform only one epoch instead...

Dyb3438

Compare ttt++ with tent and shot, with classifier frozen.

Meng-Lingjun-xjtu