Age | Commit message (Collapse) | Author | |
---|---|---|---|
2021-04-08 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-04-08 | Add stop step for scheduler | Jordan Gong | |
2021-04-07 | Revert cross-reconstruction loss factor and make image log steps adjustable | Jordan Gong | |
2021-04-06 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-04-06 | Network modification | Jordan Gong | |
This commit change the auto-encoder by removing fc and optimizing latent space features | |||
2021-03-25 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-03-25 | Bug fixes and refactoring | Jordan Gong | |
1. Correct trained model signature 2. Move `val_size` to system config | |||
2021-03-22 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-03-22 | Add embedding visualization and validate on testing set | Jordan Gong | |
2021-03-14 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-03-14 | Bug fix when transforming and new config | Jordan Gong | |
2021-03-12 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-03-12 | Code refactoring | Jordan Gong | |
1. Separate FCs and triplet losses for HPM and PartNet 2. Remove FC-equivalent 1x1 conv layers in HPM 3. Support adjustable learning rate schedulers | |||
2021-03-03 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-03-03 | Add L2 penalty to global | Jordan Gong | |
2021-03-01 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-03-01 | New scheduler and new config | Jordan Gong | |
2021-02-28 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-02-28 | Implement sum of loss default in [1] | Jordan Gong | |
[1]A. Hermans, L. Beyer, and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv preprint arXiv:1703.07737, 2017. | |||
2021-02-28 | Modify default parameters | Jordan Gong | |
1. Change ReLU to Leaky ReLU in decoder 2. Add 8-scale-pyramid in HPM | |||
2021-02-27 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-02-27 | Implement Batch Hard triplet loss and soft margin | Jordan Gong | |
2021-02-26 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-02-26 | Update default config | Jordan Gong | |
2021-02-21 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-02-21 | Remove FConv blocks | Jordan Gong | |
2021-02-18 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
2021-02-18 | Implement adjustable input size and change some default configs | Jordan Gong | |
2021-02-10 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-02-10 | Implement new sampling technique mentioned in GaitPart[1] | Jordan Gong | |
[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. | |||
2021-02-08 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-02-08 | Code refactoring, modifications and new features | Jordan Gong | |
1. Decode features outside of auto-encoder 2. Turn off HPM 1x1 conv by default 3. Change canonical feature map size from `feature_channels * 8 x 4 x 2` to `feature_channels * 2 x 16 x 8` 4. Use mean of canonical embeddings instead of mean of static features 5. Calculate static and dynamic loss separately 6. Calculate mean of parts in triplet loss instead of sum of parts 7. Add switch to log disentangled images 8. Change default configuration | |||
2021-01-23 | Add late start support for non-disentangling parts | Jordan Gong | |
2021-01-21 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-01-21 | Bug fixes | Jordan Gong | |
1. Turn off autograd while decoding canonical and pose features 2. Change default batch size to (4, 8) | |||
2021-01-14 | Enable optimizer fine tuning | Jordan Gong | |
2021-01-13 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-01-13 | Update config file and convert int to str when joining | Jordan Gong | |
2021-01-13 | Add multiple checkpoints for different model and set default config value | Jordan Gong | |
2021-01-12 | Merge branch 'python3.8' into python3.7 | Jordan Gong | |
# Conflicts: # utils/configuration.py | |||
2021-01-12 | Some changes in hyperparameter config | Jordan Gong | |
1. Separate hyperparameter configs in model, optimizer and scheduler 2. Add more tunable hyperparameters in optimizer and scheduler | |||
2021-01-12 | Remove TypeDict for python 3.7 | Jordan Gong | |
2021-01-07 | Change device config and add enable multi-GPU computing | Jordan Gong | |
1. Add `disable_acc` switch for disabling accelerator. When it is off, system will automatically choosing accelerator. 2. Enable multi-GPU training using torch.nn.DataParallel | |||
2021-01-03 | Update hyperparameter configuration, implement prototype fit function | Jordan Gong | |
2020-12-27 | Change default dataset directory | Jordan Gong | |
2020-12-27 | Make naming scheme consistent | Jordan Gong | |
Use `dir` instead of `path` | |||
2020-12-26 | Add config file and corresponding type hint | Jordan Gong | |