search

yjxiong / tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch
BSD 2-Clause "Simplified" License
1.07k stars 308 forks source link

what is the command of RGB and Flow modality fusion? Thanks！！ #118

Open chenxlin222 opened 4 years ago

chenxlin222 commented 4 years ago

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_bninception_rgb_checkpoint.pth --arch BNInception --save_scores "
  2. Or we can get the flow result from the command "python test_models.py ucf101 Flow ucf101_bninception_flow_checkpoint.pth --arch BNInception --save_scores --flowpref flow "
  3. but how can we fuse these two results?
yhc1994 commented 4 years ago

Hi did you find the solution?

zkyunqi commented 3 years ago

Me to, How to solve it?

Blueyao17 commented 2 years ago

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_bninception_rgb_checkpoint.pth --arch BNInception --save_scores "
  2. Or we can get the flow result from the command "python test_models.py ucf101 Flow ucf101_bninception_flow_checkpoint.pth --arch BNInception --save_scores --flowpref flow "
  3. but how can we fuse these two results?

Hello. Did you find the solution now?