Hi! I am trying to carry out temporal action localization for THUMOS14 dataset. I already have RGB plus OF frames using dense flow. I am using pre-trained model given for test_localizer.py
However, I am unable to interpret results in pickle file.
What I want my output to be like this-
Video 1 -> [pred_action_start pred_action_end] (in seconds or frame number anything is fine)
.
.
.
How to modify testing script to get such kind of output? Thank you.
Hi! I am trying to carry out temporal action localization for THUMOS14 dataset. I already have RGB plus OF frames using dense flow. I am using pre-trained model given for test_localizer.py
However, I am unable to interpret results in pickle file.
What I want my output to be like this- Video 1 -> [pred_action_start pred_action_end] (in seconds or frame number anything is fine) . . .
How to modify testing script to get such kind of output? Thank you.