search

HuiGuanLab / ms-sl

Source code of our MM'22 paper Partially Relevant Video Retrieval
Apache License 2.0
51 stars 7 forks source link

Inquiry about some comparison #6

Closed xjtupanda closed 1 year ago

xjtupanda commented 1 year ago

Hello! I'm trying to benchmark my model with the models reported in your paper. Could you share some details on computing FLOPs and memory consumption, as in Table 5? Some libraries like OpCounter? How about memory consumption? Did you also compute inference speed in the form of xx instances/second?

xjtupanda commented 1 year ago

Any simple script to compute on MS-SL? I think at the inference stage, it's computing a score by calling the "get_pred_from_raw_query" function.