Questions about tgt
NaomiEX opened this issue · comments
Hi, great work, it's very interesting! I was wondering why
- tgt is set as a zero tensor?. Seeing as this is eventually used as the query in the decoder I'm interested in why it was fixed as zero instead of something learnable?
- Also I'm quite confused about the purpose of this code.
@NaomiEX Sorry for late response.
- The tgt is context embedding of object queries, which are zero initialized in the first decoder layer. I tried the learnable embedding before, it had no improvement.
- You can ignore it, I just adopt the same operation as the memory embedding. If you don't do this operation, the performance will be the same.
thank you so much for your quick response!