Training code
This release adds code to train NetVLAD on the Mapillary dataset + PCAing models using either Mapillary dataset or Pittsburgh (https://github.com/QVPR/Patch-NetVLAD/pull/20 and https://github.com/QVPR/Patch-NetVLAD/pull/39)
Bugfixes
- Support for Multi-GPU inference (https://github.com/QVPR/Patch-NetVLAD/pull/22 - thanks michaelschleiss)
- Fix in keypoint positions (https://github.com/QVPR/Patch-NetVLAD/commit/6005b555cf05414afac3f3c0203e22a249d05b91)
- Fix recalls when validating on Mapillary dataset (https://github.com/QVPR/Patch-NetVLAD/pull/44)
**Full Changelog**: https://github.com/QVPR/Patch-NetVLAD/compare/v0.1.5...v0.1.6