about your models.

[LeoGeralt]

Thanks for your sharing!I have a question about your models.In your model folder，there have two models named wresnet1024_cattn_tsm.py and wresnet2048_multiscale_cattn_tsmplus_layer6.py.What‘s the differences and connections between them?

[vt-le]

Thanks for your sharing!I have a question about your models.In your model folder，there have two models named wresnet1024_cattn_tsm.py and wresnet2048_multiscale_cattn_tsmplus_layer6.py.What‘s the differences and connections between them?

Hi, Thanks for your interest! We train the Ped2 dataset using the smaller model (1024), while the larger model (2048) is used for the Avenue and ShanghaiTech datasets.

[LeoGeralt]

Thank you for your reply! By the way, I would like to ask if the datasets have been processed by video cuboids, and during your training process, which round of models can generally achieve optimal results?

[LeoGeralt]

Thanks for your sharing!I have a question about your models.In your model folder，there have two models named wresnet1024_cattn_tsm.py and wresnet2048_multiscale_cattn_tsmplus_layer6.py.What‘s the differences and connections between them?

Hi, Thanks for your interest! We train the Ped2 dataset using the smaller model (1024), while the larger model (2048) is used for the Avenue and ShanghaiTech datasets.

Thank you for your reply! By the way, I would like to ask if the datasets have been processed by video cuboids, and during your training process, which round of models can generally achieve optimal results?