yjxiong / tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

what is the command of RGB and Flow modality fusion? Thanks!!

chenxlin222 opened this issue · comments

when we get the scores of rgb stream in rgb.npz and flow stream in flow.npz, how can we get the fusion result with weights of 1:1.5 ?

Thank you very much!

For example:

  1. we can get the rgb result from the command "python test_models.py ucf101 RGB <ucf101_rgb_val_list> ucf101_bninception_rgb_checkpoint.pth --arch BNInception --save_scores <score_file_name>"
  2. Or we can get the flow result from the command "python test_models.py ucf101 Flow <ucf101_rgb_val_list> ucf101_bninception_flow_checkpoint.pth --arch BNInception --save_scores <score_file_name> --flow_pref flow_ "
  3. but how can we fuse these two results?

Hi did you find the solution?

Me to, How to solve it?

when we get the scores of rgb stream in rgb.npz and flow stream in flow.npz, how can we get the fusion result with weights of 1:1.5 ?

Thank you very much!

For example:

  1. we can get the rgb result from the command "python test_models.py ucf101 RGB <ucf101_rgb_val_list> ucf101_bninception_rgb_checkpoint.pth --arch BNInception --save_scores <score_file_name>"
  2. Or we can get the flow result from the command "python test_models.py ucf101 Flow <ucf101_rgb_val_list> ucf101_bninception_flow_checkpoint.pth --arch BNInception --save_scores <score_file_name> --flow_pref flow_ "
  3. but how can we fuse these two results?

Hello. Did you find the solution now?