fjchange / object_centric_VAD

An Tensorflow Re-Implement of CVPR 2019 "Object-centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video"
MIT License
95 stars 30 forks source link

test.py 使用文件输出异常分数非常高 #14

Open nobody-cheng opened 4 years ago

nobody-cheng commented 4 years ago

你好,我使用test.py文件输出的时候了很大的异常值 python test.py --gpu 0 --dataset avenue --model_path /data/share/imageAlgorithm/zhangcheng/code/object_centric_VAD/CAE/avenue --dataset_folder /data/share/imageAlgorithm/data/FutureFramePredictionForAnomalyDetection/avenue/testing/frames/ --svm_model /data/share/imageAlgorithm/zhangcheng/code/object_centric_VAD/SVM/avenue.m

Snipaste_2020-06-18_18-34-25

画图使用的是vis_psnr.py文件,得到不好的数据和图,对于avenue数据集的6号测试视频 Snipaste_2020-06-18_18-33-33

nobody-cheng commented 4 years ago

--class_add False is invalid

horizonly commented 3 years ago

我是同样的问题,请问你解决了吗