- [2022-3-22]: **
v0.2.2
has been released:- Fix some bugs.
- [2021-11-3]: **
v0.2.0
has been released:- New features:
- Change the format of
link
configuration.
- Change the format of
- New features:
- [2021-10-27]: **
v0.1.4
has been released:- New features:
- Add contrastive representation learning methods (MoCo-V2).
- New features:
- [2021-10-24]: **
v0.1.2
has been released:- New features:
- Add distributed (DDP) support.
- New features:
- [2021-10-7]: **
v0.1.1
has been released:- New features:
- Change the Cars196 loading method.
- New features:
- [2021-9-15]: **
v0.1.0
has been released:- New features:
- output_wrapper and pipeline setting are decomposed for convenience.
- Pipeline will be stored in the experiment folder using a directed graph.
- New features:
- [2021-9-13]: **
v0.0.1
has been released:- New features:
config.yaml
will be created to store the configuration in the experiment folder.**
- New features:
- [2021-9-6]:
v0.0.0
has been released.
GeDML is an easy-to-use generalized deep metric learning library, which contains:
- State-of-the-art DML algorithms: We contrain 18+ losses functions and 6+ sampling strategies, and divide these algorithms into three categories (i.e., collectors, selectors, and losses).
- Bridge bewteen DML and SSL: We attempt to bridge the gap between deep metric learning and self-supervised learning through specially designed modules, such as
collectors
. - Auxiliary modules to assist in building: We also encapsulates the upper interface for users to start programs quickly and separates the codes and configs for managing hyper-parameters conveniently.
pip install gedml
CUDA_VISIBLE_DEVICES=0 python demo.py \
--data_path <path_to_data> \
--save_path <path_to_save> \
--eval_exclude f1_score NMI AMI \
--device 0 --batch_size 128 --test_batch_size 128 \
--setting proxy_anchor --splits_to_eval test --embeddings_dim 128 \
--lr_trunk 0.0001 --lr_embedder 0.0001 --lr_collector 0.01 \
--dataset cub200 --delete_old \
CUDA_VISIBLE_DEVICES=0 python demo.py \
--data_path <path_to_data> \
--save_path <path_to_save> \
--eval_exclude f1_score NMI AMI \
--device 0 --batch_size 128 --test_batch_size 128 \
--setting mocov2 --splits_to_eval test --embeddings_dim 128 \
--lr_trunk 0.015 --lr_embedder 0.015 \
--dataset imagenet --delete_old \
If you want to use our code to conduct DML or CRL experiments, please refer to the up-to-date and most detailed configurations below: 👇
- If you use the command line, you can run
sample_run.sh
to try this project. - If you debug with VS Code, you can refer to
launch.json
to set.vscode
.
Use ParserWithConvert
to get parameters
>>> from gedml.launcher.misc import ParserWithConvert
>>> csv_path = ...
>>> parser = ParserWithConvert(csv_path=csv_path, name="...")
>>> opt, convert_dict = parser.render()
Use ConfigHandler
to create all objects.
>>> from gedml.launcher.creators import ConfigHandler
>>> link_path = ...
>>> assert_path = ...
>>> param_path = ...
>>> config_handler = ConfigHandler(
convert_dict=convert_dict,
link_path=link_path,
assert_path=assert_path,
params_path=param_path,
is_confirm_first=True
)
>>> config_handler.get_params_dict()
>>> objects_dict = config_handler.create_all()
Use manager
to automatically call trainer
and tester
.
>>> from gedml.launcher.misc import utils
>>> manager = utils.get_default(objects_dict, "managers")
>>> manager.run()
Or directly use trainer
and tester
.
>>> from gedml.launcher.misc import utils
>>> trainer = utils.get_default(objects_dict, "trainers")
>>> tester = utils.get_default(objects_dict, "testers")
>>> recorder = utils.get_default(objects_dict, "recorders")
# start to train
>>> utils.func_params_mediator(
[objects_dict],
trainer.__call__
)
# start to test
>>> metrics = utils.func_params_mediator(
[
{"recorders": recorder},
objects_dict,
],
tester.__call__
)
For more information, please refer to: 👉 Docs 📖
Some specific guidances:
We will continually update the optimal parameters of different configs in TsinghuaCloud
This project is modular in design. The pipeline diagram is as follows:
method | description |
---|---|
BaseCollector | Base class |
DefaultCollector | Do nothing |
ProxyCollector | Maintain a set of proxies |
MoCoCollector | paper: Momentum Contrast for Unsupervised Visual Representation Learning |
SimSiamCollector | paper: Exploring Simple Siamese Representation Learning |
HDMLCollector | paper: Hardness-Aware Deep Metric Learning |
DAMLCollector | paper: Deep Adversarial Metric Learning |
DVMLCollector | paper: Deep Variational Metric Learning |
method | description |
---|---|
CrossEntropyLoss | Cross entropy loss for unsupervised methods |
LargeMarginSoftmaxLoss | paper: Large-Margin Softmax Loss for Convolutional Neural Networks |
ArcFaceLoss | paper: ArcFace: Additive Angular Margin Loss for Deep Face Recognition |
CosFaceLoss | paper: CosFace: Large Margin Cosine Loss for Deep Face Recognition |
method | description |
---|---|
ContrastiveLoss | paper: Learning a Similarity Metric Discriminatively, with Application to Face Verification |
MarginLoss | paper: Sampling Matters in Deep Embedding Learning |
TripletLoss | paper: Learning local feature descriptors with triplets and shallow convolutional neural networks |
AngularLoss | paper: Deep Metric Learning with Angular Loss |
CircleLoss | paper: Circle Loss: A Unified Perspective of Pair Similarity Optimization |
FastAPLoss | paper: Deep Metric Learning to Rank |
LiftedStructureLoss | paper: Deep Metric Learning via Lifted Structured Feature Embedding |
MultiSimilarityLoss | paper: Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning |
NPairLoss | paper: Improved Deep Metric Learning with Multi-class N-pair Loss Objective |
SignalToNoiseRatioLoss | paper: Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning |
PosPairLoss | paper: Exploring Simple Siamese Representation Learning |
method | description |
---|---|
ProxyLoss | paper: No Fuss Distance Metric Learning Using Proxies |
ProxyAnchorLoss | paper: Proxy Anchor Loss for Deep Metric Learning |
SoftTripleLoss | paper: SoftTriple Loss: Deep Metric Learning Without Triplet Sampling |
method | description |
---|---|
BaseSelector | Base class |
DefaultSelector | Do nothing |
DenseTripletSelector | Select all triples |
DensePairSelector | Select all pairs |
- KevinMusgrave / pytorch-metric-learning
- KevinMusgrave / powerful-benchmarker
- Confusezius / Deep-Metric-Learning-Baselines
- facebookresearch / moco
- PatrickHua / SimSiam
- ujjwaltiwari / Deep_Variational_Metric_Learning
- idstcv / SoftTriple
- wzzheng / HDML
- google-research / simclr
- kunhe / FastAP-metric-learning
- wy1iu / LargeMargin_Softmax_Loss
- tjddus9597 / Proxy-Anchor-CVPR2020
- facebookresearch / deit
- assert parameters.
- write github action to automate unit-test, package publish and docs building.
- add cross-validation splits protocol.
- distributed tester for matrix-form input.
- add metrics module.
- how to improve the running efficiency.
- re-define pipeline setting!!!
- simplify distribution setting!!