summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2021-02-08Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # utils/configuration.py
2021-02-08Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/hpm.py # models/layers.py # models/model.py # models/rgb_part_net.py # utils/configuration.py
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
2021-01-23Transform all frames together in evaluationJordan Gong
2021-01-23Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # models/model.py
2021-01-23Type hint fixesJordan Gong
2021-01-23Merge branch 'master' into python3.8Jordan 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
2021-01-21Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # utils/configuration.py
2021-01-21A type hint fixJordan Gong
2021-01-21Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # utils/configuration.py
2021-01-21Print average losses after 100 itersJordan Gong
2021-01-21Bug fixesJordan Gong
1. Turn off autograd while decoding canonical and pose features 2. Change default batch size to (4, 8)
2021-01-20Bump up version for scikit-learnJordan Gong
2021-01-14Enable optimizer fine tuningJordan Gong
2021-01-14Update startup scriptJordan Gong
2021-01-14Merge branch 'python3.8' into python3.7Jordan Gong
2021-01-14Remove DataParallelJordan Gong
2021-01-14Merge branch 'python3.8' into python3.7Jordan Gong
2021-01-14Remove DataParallelJordan Gong
2021-01-13Remove more stuffJordan Gong
2021-01-13Tensorboard typo fixJordan Gong
2021-01-13Add server startup scriptJordan Gong
2021-01-13Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # utils/configuration.py
2021-01-13Merge branch 'master' into python3.8Jordan Gong
2021-01-13Update config file and convert int to str when joiningJordan Gong
2021-01-13Type hint fixesJordan Gong
2021-01-13Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/model.py
2021-01-13Add multiple checkpoints for different model and set default config valueJordan Gong
2021-01-12Merge branch 'python3.8' into python3.7Jordan Gong
2021-01-12Delete empty filesJordan Gong
2021-01-12Merge branch 'master' into python3.8Jordan Gong
2021-01-12Move the model to GPU before constructing optimizerJordan Gong
2021-01-12Some type hint fixesJordan Gong
2021-01-12Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # utils/configuration.py
2021-01-12Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # utils/configuration.py
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
2021-01-12Merge branch 'python3.8' into python3.7Jordan Gong
# Conflicts: # models/model.py
2021-01-12Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/model.py # utils/dataset.py
2021-01-12Some type hint fixesJordan Gong
2021-01-12Remove TypeDict for python 3.7Jordan Gong
2021-01-12Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/model.py
2021-01-12Print result after evaluationJordan Gong
2021-01-12Typo correct in evaluate functionJordan Gong
2021-01-12Bump up version for tqdmJordan Gong
2021-01-11Add evaluation script, code review and fix some bugsJordan Gong
1. Add new `train_all` method for one shot calling 2. Print time used in 1k iterations 3. Correct label dimension in predict function 4. Transpose distance matrix for convenient indexing 5. Sort dictionary before generate signature 6. Extract visible CUDA setting function
2021-01-11Implement evaluatorJordan Gong