AnomalyDetectionCVPR2018-Pytorch icon indicating copy to clipboard operation
AnomalyDetectionCVPR2018-Pytorch copied to clipboard

Pytorch version of - https://github.com/WaqasSultani/AnomalyDetectionCVPR2018

Results 19 AnomalyDetectionCVPR2018-Pytorch issues
Sort by recently updated
recently updated
newest added

Could you please provide the value of the training loss after the training was completed or maybe a plot of your training loss curve over the 20000 epochs? Thank you!

help wanted
good first issue
question

Hi @ekosman I am running this command: python AD_live_prediction.py --feature_extractor "r3d101_KM_200ep.pth" --feature_method "r3d101" --ad_model "D:\ucf\AnomalyDetectionCVPR2018-Pytorch-main\exps\models\epoch_10.pt" --clip_length "32" but I want that my web cam will keep on sending frames and...

**Describe the bug** A error occurred when I followed the instructions in the readme file to extract features of the ucf-crime dataset. ERROR: feature_extractor.py", line 108, in to_segments temp_vect =...

bug

I had a problem with r3d101 where I was getting a flat line. Has anyone else experienced the same issue? On the other hand, I had no problems using C3D...

bug

Dear Sir/Madam, While extracting feature I am getting error IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed. Will you please help me regrading this? ![Capture](https://github.com/ekosman/AnomalyDetectionCVPR2018-Pytorch/assets/148451689/6727fe47-4341-462d-8a5b-4382e6bde496)

referece video:https://drive.google.com/file/d/1Bd9pDYEZ-31Y-TaOEQSiraosIh09zUFa/view?usp=drive_link

bug

Hi! Sorry to bother you. Currently, I am experimenting with a different feature extractor. The output of the replaced feature extractor is 512. Also, I have printed the one video...

bug

Hi. Thank you for providing this useful feature! My question is, is it possible to apply the feature map (.npy) extracted from I3D and check the accuracy? The geometry extracted...

enhancement

Hi, Resnet 152 extracted features drive link is not correct, it is cracked. Kindly update the correct link. Thank you for your great Work.