com.intel.analytics.bigdl.optim
MeanAveragePrecisionObjectDetection
Related Doc:
package optim
the number of classes
only take topK confident predictions (-1 for all predictions)
the IOU thresholds
the type of MAP algorithm. (voc2007/voc2010/COCO)
skip calculating on a specific class (e.g. background) the class index starts from 0, or is -1 if no skipping
if check the IOU of segmentations instead of bounding boxes. If true, the output and target must have "masks" data
MeanAveragePrecision for Object Detection The class label begins with 0
The expected output from the last layer should be a Tensor[Float] or a Table If output is a tensor, it should be [num_of_batch X (1 + maxDetection * 6)] matrix The format of the matrix should be [<batch>, <batch>, ...], where each row vector is <batch> = [<size_of_batch>, <sample>,...]. Each sample has format: <sample> = <label, score, bbox x4> imgId is the batch number of the sample. imgId begins with 0. Multiple samples may share one imgId
If output is a table, it is a table of tables. output(i) is the results of the i-th image in the batch, where i = 1 to sizeof(batch) output(i) is a table, which contains the same keys (fields) of image info in the "target" Please refer to RoiMiniBatch/RoiImageInfo's documents. Besides, the inner tables also contain the scores for the detections in the image.
The "target" (Ground truth) is a table with the same structure of "output", except that it does not have "score" field