Having Troubles Training TwoStream ATGC about pedestrianactionbenchmark HOT 2 CLOSED

Hi @PaulAdamastor,
Thank you for your interest in our work.

I'm not getting this error when I run the code of both models. Are you using the latest annotations and data loading functions (pie_data.py and jaad_data.py)?

To use I3D with the optical flow you can modify the C3D config as follows: change the model to I3D and obs_input_type to [local_context_flow]. Any type with visual features should work if you append _flow to it.
However, the code expects the optical flow to be precomputed. We used FlowNet2.

from pedestrianactionbenchmark.

Hi @PaulAdamastor, Thank you for your interest in our work.

I'm not getting this error when I run the code of both models. Are you using the latest annotations and data loading functions (pie_data.py and jaad_data.py)?

To use I3D with the optical flow you can modify the C3D config as follows: change the model to I3D and obs_input_type to [local_context_flow]. Any type with visual features should work if you append _flow to it. However, the code expects the optical flow to be precomputed. We used FlowNet2.

hello
Thank you for your excellent work
When I use I3D, the error is as follows：FileNotFoundError: [Errno 2] No such file or directory:'JAAD/optical_flow/video_0001/00522.flo'
According to your reply, what I understand is to use flownet to generate .flo files for JAAD first, and then use I3D.yaml for training. Am I right?But I don't quite understand how to use flownet to generate the optical flow file of JAAD, can you explain in more detail?
thank you very much

from pedestrianactionbenchmark.