qaic-smart-nms¶

The executable tool can be used on the output of partitioned object detection models with the help of the configuration file specified for that model. The “qaic-smart-nms“ tool requires model outputs, network-descriptor, and model-information as inputs. The information needs to be provided via a YAML configuration file to “qaic-smart-nms“. It outputs boxes, labels, scores, and counts in .bin files as outputs inside the directory specified in “abp-output-directory“ inside the user-config file.

Example usage for the resnet34-ssd model:

$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/qti-aic/tools/smart-nms/
$ cd /opt/qti-aic/tools/smart-nms
$ ./qaic-smart-nms --config ./src/examples/configs/user-config-resnet34ssd.yml

The tool also outputs “infer-output.txt“ inside the same output directory. The content of infer-output.txt will be a comma path to each output.

Example:

./ smart_nms_output/boxes-activation-0-inf-1.bin, ./smart_nms_output/scores-activation-0-inf-1.bin, ./ smart_nms_output/labels-activation-0-inf-1.bin, ./ smart_nms_output/counts-activation-0-inf-1.bin

The following table lists qaic-smart-nms argument details.

The qaic-smart-nms (output Interpretations) are:

• boxes-activation-0-inf-1.bin: This file contains all box_coordinates[x,y,x,y] for all batches in flat format. Example: If yolov3 is executed with batch-size = 4, (that is, four images), and in each image, there are 4, 10, 2, 21 detections respectively that are run under a single thread, then boxes-activation-0-inf-{index}.bin will have (4+10+2+21) * 4, which is 148 float32 values.

  Underlying datatype: raw / float32

• scores-activation-0-inf-1.bin: This file contains all scores for all batches in flat format. Example: If yolov3 is executed with batch-size = 4, (that is, four images), and in each image, there are 4, 10, 2, 21 detections respectively that are run under a single thread, then scores-activation-0-inf-{index}.bin will have (4+10+2+21), which is 37 float32 values.

  Underlying datatype: raw / float32

• labels-activation-0-inf-1.bin: This file contains class-idx for every box in boxes-activation-0-inf-{index}.bin in flat format. Example: If yolov3 is executed with batch-size = 4, (that is, four images), and in each image, there are 4, 10, 2, 21 detections respectively, that are run under a single thread, then labels-activation-0-inf-{index}.bin will have (4+10+2+21), which is 37 float32 values.

  Underlying datatype: raw / float32

• counts-activation-0-inf-1.bin: This file contains counts of detection for each batch format. Example: If yolov3 is executed with batch-size = 4, (that is, four images), and in each image, there are 4, 10, 2, 21 detections respectively that are run under a single thread, then counts-activation-0-inf-{index}.bin will have four float32 values: 4,10,2,21.

  Underlying datatype: raw / float32