summaryrefslogtreecommitdiff
path: root/models/rgb_part_net.py
AgeCommit message (Collapse)Author
2021-03-12Merge branch 'data_parallel' into data_parallel_py3.8Jordan Gong
# Conflicts: # models/hpm.py # models/model.py # models/rgb_part_net.py # utils/configuration.py # utils/triplet_loss.py
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
2021-03-05Merge branch 'data_parallel' into data_parallel_py3.8Jordan Gong
2021-03-05Calculate losses outside modulesJordan Gong
2021-03-02Merge branch 'data_parallel' into data_parallel_py3.8Jordan Gong
2021-03-02Fix DataParallel specific bugsJordan Gong
2021-03-01Merge branch 'data_parallel' into data_parallel_py3.8Jordan Gong
# Conflicts: # models/model.py # utils/configuration.py # utils/triplet_loss.py
2021-02-27Implement Batch Hard triplet loss and soft marginJordan Gong
2021-02-26Merge branch 'data_parallel' into data_parallel_py3.8Jordan Gong
# Conflicts: # models/part_net.py # models/rgb_part_net.py
2021-02-26Fix predict functionJordan Gong
2021-02-21Remove FConv blocksJordan Gong
2021-02-20Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/model.py # models/rgb_part_net.py
2021-02-20Separate triplet loss from modelJordan Gong
2021-02-18Merge branch 'master' into python3.8Jordan Gong
2021-02-18Implement adjustable input size and change some default configsJordan Gong
2021-02-18Decode mean appearance featureJordan Gong
2021-02-18Decode mean appearance featureJordan Gong
2021-02-15Revert "Memory usage improvement"Jordan Gong
This reverts commit be508061
2021-02-15Revert "Memory usage improvement"Jordan Gong
This reverts commit be508061
2021-02-14Merge branch 'master' into python3.8Jordan Gong
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
2021-02-09Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/rgb_part_net.py
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.
2021-02-08Merge 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
2021-01-23Transform all frames together in evaluationJordan Gong
2021-01-21Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # utils/configuration.py
2021-01-21Print average losses after 100 itersJordan Gong
2021-01-12Merge branch 'master' into python3.8Jordan Gong
# Conflicts: # models/model.py
2021-01-09Add prototype predict functionJordan Gong
2021-01-09Change auto-encoder input in evaluationJordan Gong
2021-01-07Type hint for python version lower than 3.9Jordan Gong
2021-01-07Add typical training script and some bug fixesJordan Gong
1. Resolve deprecated scheduler stepping issue 2. Make losses in the same scale(replace mean with sum in separate triplet loss, enlarge pose similarity loss 10x) 3. Add ReLU when compute distance in triplet loss 4. Remove classes except Model from `models` package init
2021-01-06Add TensorBoard supportJordan Gong
2021-01-05Implement Batch All Triplet LossJordan Gong
2021-01-05Change and improve weight initializationJordan Gong
1. Change initial weights for Conv layers 2. Find a way to init last fc in init_weights
2021-01-03Separate last fc matrix from weight init functionJordan Gong
Recursive apply will override other parameters too
2021-01-03Implement weight initializationJordan Gong
2021-01-03Update hyperparameter configuration, implement prototype fit functionJordan Gong
2021-01-03Add separate fully connected layersJordan Gong
2021-01-02Separate training and evaluatingJordan Gong
2021-01-02Correct feature dims after disentanglement and HPM backbone removalJordan Gong
1. Features used in HPM is decoded canonical embedding without transpose convolution 2. Decode pose embedding to image for Part Net 3. Backbone seems to be redundant, we can use feature map given by auto-decoder
2021-01-02Change type of pose similarity loss to tensorJordan Gong
2020-12-31Implement some parts of RGB-GaitPart wrapperJordan Gong
1. Triplet loss function and weight init function haven't been implement yet 2. Tuplize features returned by auto-encoder for later unpack 3. Correct comment error in auto-encoder 4. Swap batch_size dim and time dim in HPM and PartNet in case of redundant transpose 5. Find backbone problems in HPM and disable it temporarily 6. Make feature structure by HPM consistent to that by PartNet 7. Fix average pooling dimension issue and incorrect view change in HP
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-24 01:46:44 +0000