-
I see that the default weight of flow loss is 0, which means no flow loss. Does it means when there is no flow loss, it can have a result of 85.6%? So how many performance improvement of the litenet?
-
hello, thanks for the great work, could you tell me what does the data mean in the skeleton_based_anomaly_detection\data\HR-ShanghaiTech\training\trajectories\00\01_001 file?
I'am afraid I can't figu…
-
-
` logging.info("load/iter/cuda: {} vs {} vs {} seconds; iter: {}".format(load_time, iter_time, net.cudaTimer.tot_time, net.cudaTimer.calls))
net.cudaTimer.tot_time = 0`
When I run the code ,…
-
I follow your code and use default parameters, on shanghaitech only get auc 63.7
`dataset = shanghaitech, loss file = /home/dingxia/data/shanghaitech.pkl, auc = 0.6370342604726742`
in order to get…
-
Hi!
First of all, thank you very much for sharing your code! It's a great work.
My question is if the network could be use with binary images as input.
Thanks a lot!
Best regards.
-
I implement in pytorch and follow your settings and get 61.9 auc on shanghaitech, using only rgb. can you show your auc of it?
If I use three-stream, training of svm will terminate because of excess…
-
progress | sum | jmap | lmap | joff | lpos | lneg | speed
Running validation... Traceback (most recent call las…
-
Please provide the pre-trained models for ShanghaiTech dataset
-
Dear,
You previously helped me with sending the Shanghaitech dataset. Now, I am need of Wroldexpo'10 dataset and UCSD dataset.
Let me explain you a scenario about UCF_CC_50 dataset. I have 50 ima…