Skip to content

Latest commit

 

History

History
37 lines (21 loc) · 1.15 KB

README.md

File metadata and controls

37 lines (21 loc) · 1.15 KB

SOLO

The code is an unofficial pytorch implementation of SOLO: Segmenting Objects by Locations

Install

The code is based on mmdetection. Please check Install.md for installation instructions.

Training

Follows the same way as mmdetection.

single GPU: python tools/train.py configs/solo/r50.py

multi GPU (for example 8): ./tools/dist_train.sh configs/solo/r50.py 8

Notes

The code only implements the simplest version of SOLO:

  • without CoordConv
  • using vanilla SOLO instead of Decoupled SOLO
  • 3x training schedule
  • using the default FPN featuremaps: in the paper it is with different specific strides and instance scale selection
  • implemented the simplest mask-nms: as the authors did not describe it in detail in the paper, the implemented nms is slow, will improve it in the future.
  • still in progress

Results

After training 36 epochs on the coco dataset using the resnet-50 backbone, the mAP is 0.221 on COCO val2017 dataset:

Both good and bad results: