This is a segmentation network to classify each pixel into four classes: BG, road, curb, mark.
The quality metrics calculated on 500 images from "Mighty AI" dataset that was converted for four class classification task are:
TP- number of true positive pixels for given class
FN- number of false negative pixels for given class
FP- number of false positive pixels for given class
GT- number of ground truth pixels for given class
A blob with a
BGR image and the shape
1, 3, 512, 896 in the format
B, C, H, W, where:
B– batch size
C– number of channels
H– image height
W– image width
The output is a blob with the shape
1, 4, 512, 896 in the format
B, C, H, W. It can be treated as a four-channel feature map, where each channel is a probability of one of the classes: BG, road, curb, mark.
[*] Other names and brands may be claimed as the property of others.