Age | Commit message (Collapse) | Author | |
---|---|---|---|
2021-04-04 | Merge branch 'disentangling_only' into disentangling_only_py3.8 | Jordan Gong | |
# Conflicts: # models/model.py # utils/configuration.py # utils/sampler.py | |||
2021-04-04 | Remove triplet sampler | Jordan Gong | |
2021-04-03 | Merge branch 'disentangling_only' into disentangling_only_py3.8 | Jordan Gong | |
# Conflicts: # models/model.py | |||
2021-04-03 | Merge branch 'master' into disentangling_only | Jordan Gong | |
# Conflicts: # config.py # models/hpm.py # models/layers.py # models/model.py # models/part_net.py # models/rgb_part_net.py # test/part_net.py # utils/configuration.py # utils/triplet_loss.py | |||
2021-04-03 | Revert "Normalize triplet losses" | Jordan Gong | |
This reverts commit 99d1b18a | |||
2021-03-27 | Normalize triplet losses | Jordan Gong | |
2021-03-25 | Bug fixes and refactoring | Jordan Gong | |
1. Correct trained model signature 2. Move `val_size` to system config | |||
2021-03-23 | Fix indexing bugs in validation dataset selector | Jordan Gong | |
2021-03-22 | Add embedding visualization and validate on testing set | Jordan Gong | |
2021-03-16 | Set *_iter as *_iters in default | Jordan Gong | |
2021-03-15 | Remove redundant wrapper given by dataloader | Jordan Gong | |
2021-03-15 | Fix redundant gallery_dataset_meta assignment | Jordan Gong | |
2021-03-15 | Support transforming on training datasets | Jordan Gong | |
2021-03-12 | Fix a typo when record none-zero counts | Jordan Gong | |
2021-03-12 | Make evaluate method static | Jordan Gong | |
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 | |||
2021-03-10 | Bug fixes | Jordan Gong | |
1. Resolve reference problems when parsing dataset selectors 2. Transform gallery using different models | |||
2021-03-04 | Replace detach with no_grad in evaluation | Jordan Gong | |
2021-03-04 | Set seed for reproducibility | Jordan Gong | |
2021-03-02 | Record learning rate every step | Jordan Gong | |
2021-03-02 | Fix bugs in new scheduler | Jordan Gong | |
2021-03-01 | New scheduler and new config | Jordan Gong | |
2021-03-01 | Move pairs variable to local | Jordan Gong | |
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 | Log n-ile embedding distance and norm | Jordan Gong | |
2021-02-27 | Implement Batch Hard triplet loss and soft margin | Jordan Gong | |
2021-02-26 | Fix predict function | Jordan Gong | |
2021-02-20 | Separate triplet loss from model | Jordan Gong | |
2021-02-19 | Merge branch 'python3.8' into disentangling_only_py3.8 | Jordan Gong | |
# Conflicts: # models/hpm.py # models/layers.py # models/model.py # models/part_net.py # models/rgb_part_net.py # utils/configuration.py | |||
2021-02-19 | New branch with auto-encoder only | Jordan Gong | |
2021-02-19 | Merge branch 'master' into python3.8 | Jordan Gong | |
2021-02-19 | Allow evaluate unfinished model | Jordan Gong | |
2021-02-18 | Merge branch 'master' into python3.8 | Jordan Gong | |
2021-02-18 | Implement adjustable input size and change some default configs | Jordan Gong | |
2021-02-18 | Decode mean appearance feature | Jordan Gong | |
2021-02-16 | Merge branch 'master' into python3.8 | Jordan Gong | |
# Conflicts: # models/model.py | |||
2021-02-16 | Split transform and evaluate method | Jordan Gong | |
2021-02-15 | Revert "Memory usage improvement" | Jordan Gong | |
This reverts commit be508061 | |||
2021-02-15 | Revert "Memory usage improvement" | Jordan Gong | |
This reverts commit be508061 | |||
2021-02-14 | Merge branch 'master' into python3.8 | Jordan Gong | |
2021-02-14 | Memory usage improvement | Jordan Gong | |
This update separates input data to two batches, which reduces ~30% memory usage. | |||
2021-02-14 | Prepare for DataParallel | Jordan Gong | |
2021-02-10 | Merge branch 'master' into python3.8 | Jordan Gong | |
2021-02-10 | Save scheduler state_dict | Jordan Gong | |
2021-02-09 | Merge branch 'master' into python3.8 | Jordan Gong | |
# Conflicts: # models/rgb_part_net.py | |||
2021-02-09 | Improve performance when disentangling | Jordan Gong | |
This is a HUGE performance optimization, up to 2x faster than before. Mainly because of the replacement of randomized for-loop with randomized tensor. | |||
2021-02-09 | Some optimizations | Jordan Gong | |
1. Scheduler will decay the learning rate of auto-encoder only 2. Write learning rate history to tensorboard 3. Reduce image log frequency | |||
2021-02-08 | Merge branch 'master' into python3.8 | Jordan Gong | |
# Conflicts: # models/hpm.py # models/layers.py # models/model.py # models/rgb_part_net.py # 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 | Remove the third term in canonical consistency loss | Jordan Gong | |