You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The BUG lead the cross-att in decoder using NO casual mask, while self-att using casual mask. Fortunately there is no information leak in informer, but still totally different with what you wrote in the paper.
The text was updated successfully, but these errors were encountered:
slczgwh
changed the title
Wrong att-mask in decoder
BUG:Wrong att-mask in decoder
Feb 26, 2021
Please refer to Figure 1. In decoder, we use masked multi-head prob-sparse self-attention and multi-head cross attention, so we use casual mask in self-attention and no casual mask in cross-attention. Since we utilize generative inference to generate prediction results, the causal mask in decoder is actually not critical. But you can also use mask in cross-attention ,and choose to use prob attn or full attn freely.
A BUG when creating model:
Informer2020/models/model.py
Lines 50 to 53 in a87092b
The BUG lead the cross-att in decoder using NO casual mask, while self-att using casual mask. Fortunately there is no information leak in informer, but still totally different with what you wrote in the paper.
The text was updated successfully, but these errors were encountered: