ShengcaiLiao QAConv Versions Save

• Simplified graph sampling
• Einstein summation for QAConv
• Hard triplet loss
• Adaptive epoch and learning rate scheduling
• Automatic mixed precision training

• Include a new sampler called Graph Sampler (GS).
• Remove the class memory based loss. Instead, a pairwise matching loss is implemented.
• This version is much more efficient in learning.

Include some popular data augmentation methods, and change the ranking.py implementation to the original open-reid version, so that it is more consistent to most other implementations (e.g. open-reid, torch-reid, fast-reid).

• Include the IBN-Net as backbone, and the RandPerson dataset.
• Include a pre-training function for a better initialization, so that the results are now more stable.

This is the ECCV 2020 version.