This model presents a vehicle attributes classification algorithm for a traffic analysis scenario.
|Car pose||Front facing cars|
|Min object width||72 pixels|
|Supported colors||White, gray, yellow, red, green, blue, black|
|Supported types||Car, van, truck, bus|
Color average accuracy: 82.71%
Type average accuracy: 87.34%
input , shape: [1x3x72x72] - an input image in following format [1xCxHxW], where:
Expected color order: BGR.
color, shape: [1, 7] - probabilities across seven color classes [
type, shape: [1, 4] - probabilities across four type classes [
[*] Other names and brands may be claimed as the property of others.