case classDecodeOutput() extends ImageProcessing with Product with Serializable
Decode the detection output
The output of the model prediction is a 1-dim tensor
The first element of tensor is the number(K) of objects detected,
followed by [label score x1 y1 x2 y2] * K
For example, if there are 2 detected objects, then K = 2, the tensor may
looks like
2, 1, 0.5, 10, 20, 50, 80, 3, 0.3, 20, 10, 40, 70
After decoding, it returns a 2-dim tensor, each row represents a detected object
1, 0.5, 10, 20, 50, 80
3, 0.3, 20, 10, 40, 70
Decode the detection output The output of the model prediction is a 1-dim tensor The first element of tensor is the number(K) of objects detected, followed by [label score x1 y1 x2 y2] * K For example, if there are 2 detected objects, then K = 2, the tensor may looks like
2, 1, 0.5, 10, 20, 50, 80, 3, 0.3, 20, 10, 40, 701, 0.5, 10, 20, 50, 80 3, 0.3, 20, 10, 40, 70