Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Conflicts:
# models/model.py
|
|
|
|
|
|
|
|
|
|
[1]A. Hermans, L. Beyer, and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv preprint arXiv:1703.07737, 2017.
|
|
|
|
1. Change ReLU to Leaky ReLU in decoder
2. Add 8-scale-pyramid in HPM
|
|
|
|
|
|
# Conflicts:
# models/model.py
|
|
|
|
|
|
|
|
|
|
# Conflicts:
# models/model.py
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
This reverts commit be508061
|
|
This update separates input data to two batches, which reduces ~30% memory usage.
|
|
|
|
|
|
[1]C. Fan et al., “GaitPart: Temporal Part-Based Model for Gait Recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 14225–14233.
|
|
|