Skip to content

Latest commit

 

History

History
30 lines (15 loc) · 1.67 KB

nms_pipeline.md

File metadata and controls

30 lines (15 loc) · 1.67 KB

Pipeline of Non-Maximum Suppression and Benchmark

This document shows the whole pipeline for post-processing model output: performing Non-Maximum Suppression (NMS), and benchmarking using BSDS500 dataset.

Model Output

The model output on test dataset is saved in RCF-pytorch/tmp/RCF.

Non-Maximum Suppression

For both RCF and HED, the model output only shows a probablity map of edge pixels, so an NMS is neccessary for evaluation on dataset benchmark.

Solving dependencies

Both of the authors of HED and RCF provides some code for doing NMS. The code depends on Pictor's Edge Detection Toolbox, and Buenaposada's Matlab Toolbox. Then all those toolboxes should also be installed (or not, see notes below).

Notes:

  1. Important: Piotr's Matlab Toolbox is deprecated due to a int type problem mentioned here.
  2. For win64/linux64 systems, the binaries are already included, so there is no need to install/compile the libraries using mex.
  3. The libraries for NMS in the toolbox is private, so a wrapper for edgesNmsMex should be written in edges/.

Performing NMS

Modify the paths in the /rcf/examples/rcf/edges_nms.m file, and simply run the MATLAB script. The output edges will be saved in the path you choose.

Benchmarking