Xu
Xu
sorry, I don't have the dataset either ---Original--- From: "lvandoit"
sorry ，dont get ---Original--- From: "seamanj"
The informative part is mask_h*x. It is part of " ax = weight_s * mask_h * x " Thanks.
It is a kind of method to add noise. You can also refer to the code of TS2Vec.
Hi, The first question, the $\eta$ is not directly implemented in the code because we use random perturbation as the noise. This part is added to the feature of the...
Yes, it is in AutoTCL_CoST.py, line 148.
Yeah, the reg_loss is about H(V*), and regular is the temporal loss.