summaryrefslogtreecommitdiff
path: root/config.py
AgeCommit message (Collapse)Author
2021-03-12Merge branch 'master' into data_parallelJordan Gong
# Conflicts: # models/auto_encoder.py # models/model.py # models/rgb_part_net.py
2021-03-12Code refactoringJordan 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
2021-03-03Merge branch 'master' into data_parallelJordan Gong
2021-03-03Add L2 penalty to globalJordan Gong
2021-03-01Merge branch 'master' into data_parallelJordan Gong
# Conflicts: # models/model.py
2021-03-01New scheduler and new configJordan Gong
2021-02-28Implement 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.
2021-02-28Modify default parametersJordan Gong
1. Change ReLU to Leaky ReLU in decoder 2. Add 8-scale-pyramid in HPM
2021-02-27Implement Batch Hard triplet loss and soft marginJordan Gong
2021-02-26Update default configJordan Gong
2021-02-21Remove FConv blocksJordan Gong
2021-02-18Implement adjustable input size and change some default configsJordan Gong
2021-02-10Implement 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.
2021-02-08Code refactoring, modifications and new featuresJordan 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
2021-01-23Add late start support for non-disentangling partsJordan Gong
2021-01-21Bug fixesJordan Gong
1. Turn off autograd while decoding canonical and pose features 2. Change default batch size to (4, 8)
2021-01-14Enable optimizer fine tuningJordan Gong
2021-01-13Update config file and convert int to str when joiningJordan Gong
2021-01-13Add multiple checkpoints for different model and set default config valueJordan Gong
2021-01-12Some changes in hyperparameter configJordan Gong
1. Separate hyperparameter configs in model, optimizer and scheduler 2. Add more tunable hyperparameters in optimizer and scheduler
2021-01-07Change device config and add enable multi-GPU computingJordan 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
2021-01-03Update hyperparameter configuration, implement prototype fit functionJordan Gong
2020-12-27Change default dataset directoryJordan Gong
2020-12-27Make naming scheme consistentJordan Gong
Use `dir` instead of `path`
2020-12-26Add config file and corresponding type hintJordan Gong