Typo in saveFeatures function in temporalnet_multicam.py

[lidongwangriver]

Fall-Detection-with-CNNs-and-Optical-Flow/temporalnet_multicam.py

Line 206 in 98f8338

y_images = glob.glob(not_fall + '/flow_x*.jpg')

y_images = glob.glob(not_fall + '/flow_x*.jpg') should be '/flow_y*.jpg'

Question:
whether the Extracted features and labels for Multicam were extracted with this script?
I tried to reproduce and got very bad sensitivity(less than 50%) with those (Extracted features and labels) , not sure whether it caused by wrong features

[AdrianNunez]

Yes, it is a typo, I have already fixed it, thank you.

whether the Extracted features and labels for Multicam were extracted with this script?

Sorry, I do not remember.

I tried to reproduce and got very bad sensitivity(less than 50%) with those (Extracted features and labels) , not sure whether it caused by wrong features

It may be the case, as the vertical flow should be the most important one for the classification.

[af-doom]

Thank you for your research. Is the extracted feature of the multicam dataset downloaded through the link correct? I tried to reproduce temporalent_ Combined.py has a very bad result (about 50% accuracy)