Age | Commit message (Collapse) | Author | |
---|---|---|---|
2020-12-31 | Make super class constructor revoke consistent | Jordan Gong | |
2020-12-30 | Combine FPFE and TFA to GaitPart | Jordan Gong | |
2020-12-30 | Add pooling options in HPM | Jordan Gong | |
According to [1], we can use GAP and GMP together, or one of both in ablation study. [1]Y. Fu et al., “Horizontal pyramid matching for person re-identification,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2019, vol. 33, pp. 8295–8302. | |||
2020-12-27 | Refine auto-encoder | Jordan Gong | |
1. Wrap fully connected layers 2. Introduce hyperparameter tuning in constructor | |||
2020-12-27 | Adopt type hinting generics in standard collections (PEP 585) | Jordan Gong | |
2020-12-24 | Implement Horizontal Pyramid Matching (HPM) | Jordan Gong | |
2020-12-24 | Change the usage of layers and reorganize relations of layers | Jordan Gong | |
1. Add batch normalization and activation to layers 2. VGGConv2d and FocalConv2d inherits to BasicConv2d; DCGANConvTranspose2d inherits to BasicConvTranspose2d | |||
2020-12-23 | Refactor and refine auto-encoder | Jordan Gong | |
1. Wrap Conv2d 3x3-padding-1 to VGGConv2d 2. Wrap ConvTranspose2d 4x4-stride-4-padding-1 to DCGANConvTranspose2d 3. Turn off bias in conv since the employment of batch normalization | |||
2020-12-23 | Wrap Conv1d no bias layer | Jordan Gong | |
2020-12-23 | Remove redundant Leaky ReLU in FocalConv2d | Jordan Gong | |
2020-12-23 | Split modules to different files | Jordan Gong | |