summaryrefslogtreecommitdiff
path: root/models/model.py
AgeCommit message (Collapse)Author
2021-05-17Model modificationHEADmasterJordan Gong
Reduce channels in the auto-encoder and add more layers
2021-04-10Calculate pose similarity loss and canonical consistency loss of each part ↵Jordan Gong
after pooling
2021-04-08Add stop step for schedulerJordan Gong
2021-04-07Revert cross-reconstruction loss factor and make image log steps adjustableJordan Gong
2021-04-03Revert "Normalize triplet losses"Jordan Gong
This reverts commit 99d1b18a
2021-03-27Normalize triplet lossesJordan Gong
2021-03-25Bug fixes and refactoringJordan Gong
1. Correct trained model signature 2. Move `val_size` to system config
2021-03-23Fix indexing bugs in validation dataset selectorJordan Gong
2021-03-22Add embedding visualization and validate on testing setJordan Gong
2021-03-16Set *_iter as *_iters in defaultJordan Gong
2021-03-15Remove redundant wrapper given by dataloaderJordan Gong
2021-03-15Fix redundant gallery_dataset_meta assignmentJordan Gong
2021-03-15Support transforming on training datasetsJordan Gong
2021-03-12Fix a typo when record none-zero countsJordan Gong
2021-03-12Make evaluate method staticJordan Gong
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
2021-03-10Bug fixesJordan Gong
1. Resolve reference problems when parsing dataset selectors 2. Transform gallery using different models
2021-03-04Replace detach with no_grad in evaluationJordan Gong
2021-03-04Set seed for reproducibilityJordan Gong
2021-03-02Record learning rate every stepJordan Gong
2021-03-02Fix bugs in new schedulerJordan Gong
2021-03-01New scheduler and new configJordan Gong
2021-03-01Move pairs variable to localJordan 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.
2021-02-28Log n-ile embedding distance and normJordan Gong
2021-02-27Implement Batch Hard triplet loss and soft marginJordan Gong
2021-02-26Fix predict functionJordan Gong
2021-02-20Separate triplet loss from modelJordan Gong
2021-02-19Allow evaluate unfinished modelJordan Gong
2021-02-18Implement adjustable input size and change some default configsJordan Gong
2021-02-18Decode mean appearance featureJordan Gong
2021-02-16Split transform and evaluate methodJordan Gong
2021-02-15Revert "Memory usage improvement"Jordan Gong
This reverts commit be508061
2021-02-14Memory usage improvementJordan Gong
This update separates input data to two batches, which reduces ~30% memory usage.
2021-02-14Prepare for DataParallelJordan Gong
2021-02-10Save scheduler state_dictJordan Gong
2021-02-09Improve performance when disentanglingJordan 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.
2021-02-09Some optimizationsJordan Gong
1. Scheduler will decay the learning rate of auto-encoder only 2. Write learning rate history to tensorboard 3. Reduce image log frequency
2021-02-08Code 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
2021-01-23Remove the third term in canonical consistency lossJordan Gong
2021-01-23Add late start support for non-disentangling partsJordan Gong
2021-01-23Evaluation bug fixes and code reviewJordan Gong
1. Return full cached clip in evaluation 2. Add multi-iter checkpoints support in evaluation 3. Remove duplicated code while transforming
2021-01-22Handle unexpected restore iterJordan Gong
1. Skip finished model before load it 2. Raise error when restore iter is greater than total iter
2021-01-21Print average losses after 100 itersJordan Gong
2021-01-14Enable optimizer fine tuningJordan Gong
2021-01-14Remove DataParallelJordan 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
2021-01-12Move the model to GPU before constructing optimizerJordan 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
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-23 17:30:15 +0000