I want to use CrevNet for abnormal event detection of video. I convert Avenue dataset to 256x256x1 according to convert_kth.lua, get this error
then, I convert avenue to 64x64x1, it can work, but get this result
I want to know, which training parameters need to be modified.
I want to use CrevNet for abnormal event detection of video. I convert Avenue dataset to 256x256x1 according to convert_kth.lua, get this error
then, I convert avenue to 64x64x1, it can work, but get this result
![image](https://user-images.githubusercontent.com/45116477/101754311-93316180-3b0e-11eb-8acc-22d62a5a72bc.png)
I want to know, which training parameters need to be modified.![image](https://user-images.githubusercontent.com/45116477/101754741-09ce5f00-3b0f-11eb-8240-3c6efaca7373.png)