llmpass
commented
1 year ago yes
jackxx33 @.***> 于2023年2月28日周二 05:41写道：
Is the extra frame from the decoder just get the average of the adjacent features from the encoder? if i % 2 == 0: y[:, i, :, :, :] = x[:, i//2] else: y[:, i, :, :, :] = (x[:, i//2] + x[:, i//2 + 1]) / 2
— Reply to this email directly, view it on GitHub https://github.com/llmpass/RSTT/issues/12, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAHUDC3IBHWGWKUUS3PRY4LWZX6BTANCNFSM6AAAAAAVKXW42E . You are receiving this because you are subscribed to this thread.Message ID: @.***>
-- Luming Liang Ph.D. Department of Electrical Engineering & Computer Science, Colorado School of Mines https://sites.google.com/site/lumingliangshomepage http://www.escience.cn/people/LumingLiang/index.html;jsessionid=447C38DFA70347AD3E1DD4C1A3D4B64A-n2
Hello,Is the extra frame from the decoder just get the average of the adjacent features from the encoder? if i % 2 == 0: y[:, i, :, :, :] = x[:, i//2] else: y[:, i, :, :, :] = (x[:, i//2] + x[:, i//2 + 1]) / 2