search

gdwang08 / Jigsaw-VAD

Code for the paper entitled "Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles" (ECCV 2022)
GNU General Public License v3.0
56 stars 8 forks source link

Dataset file structure and details #13

Closed ZhangHuixin1103 closed 1 year ago

ZhangHuixin1103 commented 1 year ago

Howdy!

Thanks for your great work!

I wish to get the full file structure in /irip/wangguodong_2020/projects/datasets/vad/.

What your code (dataset part) indicates seems to be slightly different from the original datasets, so I'm curious about the modifications you did to the datasets.

(I actually saw your avenue.zip in another issue. Would you mind sharing more? ^^ )

gdwang08 commented 1 year ago

the dataset structure as follows:

vad/ --avenue/ ----avenue.mat ----testing/ ----01/ ------0000.jpg ------1438.jpg ----21/ ----training/ ------01/ --------0000.jpg --------1363.jpg ------16

--ped2/ ----ped2.mat ----testing/ ------01/ ------000.jpg ------179.jpg ------12/ ----training/ ------01/ ------16/

--shanghaitech/ ----testing/ ------01_0014/ --------000.jpg --------264.jpg ------01_0015/ ----training/ ------01_001/ --------000000.jpg --------000001.jpg ------13_007 ----frame_masks/ ------01_0014.npy ------12_0175.npy ----pixel_masks/ ------01_0014.npy ------12_0175.npy

ZhangHuixin1103 commented 1 year ago

Thanks !