This model presents a person attributes classification algorithm analysis scenario. It produces probability of person attributions existing on the sample and a position of two point on sample, which can be used for color prob (like, color picker in graphical editors)
|Pedestrian pose||Standing person|
|Min object width||80 pixels|
|Supported attributes||is_male, has_bag, has_backpack, has hat, has longsleeves, has longpants, has longhair, has coat_jacket|
1, 3, 160, 80 in the format
1, C, H, W, where:
C- number of channels
H- image height
W- image width
The expected color order is
1, 8, 1, 1across eight attributes: [
has_coat_jacket]. Value > 0.5 means that an attribute is present.
1, 2, 1, 1. It is location of point with top color.
1, 2, 1, 1. It is location of point with bottom color.
[*] Other names and brands may be claimed as the property of others.