This is a person, vehicle, bike detector that is based on MobileNetV2 backbone with ATSS head for 864x480 resolution.
Metric | Value |
---|---|
AP @ [ IoU=0.50:0.95 ] | 0.336 (internal test set) |
GFlops | 6.550 |
MParams | 2.416 |
Source framework | PyTorch* |
Average Precision (AP) is defined as an area under the precision/recall curve.
Name: input
, shape: 1, 3, 480, 864
- An input image in the format B, C, H, W
, where:
Expected color order is BGR.
boxes
is a blob with shape: N, 5
, where N is the number of detected bounding boxes. For each detection, the description has the format: [x_min
, y_min
, x_max
, y_max
, conf
], where:x_min
, y_min
) - coordinates of the top left bounding box cornerx_max
, y_max
) - coordinates of the bottom right bounding box corner.conf
- confidence for the predicted classlabels
is a blob with shape: N
, where N is the number of detected bounding boxes. The value of each label is equal to predicted class ID (0 - vehicle, 1 - person, 2 - non-vehicle).[*] Other names and brands may be claimed as the property of others.