search

Echo0125 / MAT-Memory-and-Anticipation-Transformer

[ICCV 2023] Official implementation of Memory-and-Anticipation Transformer for Online Action Understanding
Apache License 2.0
44 stars 3 forks source link

Cannot reproduce THUMOS Kinetics result #5

Closed jun297 closed 9 months ago

jun297 commented 9 months ago

Hi, I trained a model from scratch as written in readme, however, my mAP is only 69 ~ 69.5, which is lower than the reported performance 71.6 (I used kinetics for THUMOS) and LSTR

does this difference come from inference mode?

Did you get the result by running the script? my torch version is 1.13.1+cu117

jun297 commented 9 months ago

I guess the difference comes from the inference mode in batch inference mode, I could get 71.3 ~ 71.6 mAP