├── .idea
├── .gitignore
├── UnTrack.iml
├── inspectionProfiles
│ └── profiles_settings.xml
├── modules.xml
└── vcs.xml
├── Depthtrack_workspace
├── config.yaml
├── list.txt
└── trackers.ini
├── README.md
├── RGBE_workspace
└── test_rgbe_mgpus.py
├── RGBT_workspace
├── attributes_RGBT234.xlsx
└── test_rgbt_mgpus.py
├── download_vot.py
├── environment.yaml
├── eval_all.sh
├── eval_rgbd.sh
├── eval_rgbe.sh
├── eval_rgbt.sh
├── eval_rgbtlasher.sh
├── eval_rgbvotd.sh
├── experiments
└── untrack
│ ├── deep_rgbd.yaml
│ ├── deep_rgbe.yaml
│ ├── deep_rgbt.yaml
│ └── deep_rgbx.yaml
├── install.sh
├── lib
├── __init__.py
├── __pycache__
│ ├── __init__.cpython-310.pyc
│ └── __init__.cpython-37.pyc
├── config
│ └── untrack
│ │ ├── __pycache__
│ │ └── config.cpython-37.pyc
│ │ └── config.py
├── models
│ ├── __init__.py
│ ├── __pycache__
│ │ └── __init__.cpython-37.pyc
│ ├── layers
│ │ ├── MoE_prompt.py
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── MoE_prompt.cpython-37.pyc
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── attn.cpython-37.pyc
│ │ │ ├── attn_blocks.cpython-37.pyc
│ │ │ ├── frozen_bn.cpython-37.pyc
│ │ │ ├── head.cpython-37.pyc
│ │ │ ├── patch_embed.cpython-37.pyc
│ │ │ └── rpe.cpython-37.pyc
│ │ ├── attn.py
│ │ ├── attn_blocks.py
│ │ ├── frozen_bn.py
│ │ ├── head.py
│ │ ├── patch_embed.py
│ │ └── rpe.py
│ └── untrack
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ ├── __init__.cpython-37.pyc
│ │ ├── attention.cpython-37.pyc
│ │ ├── base_backbone.cpython-37.pyc
│ │ ├── ostrack.cpython-37.pyc
│ │ ├── ostrack_prompt.cpython-37.pyc
│ │ ├── utils.cpython-37.pyc
│ │ ├── vit.cpython-37.pyc
│ │ ├── vit_ce.cpython-37.pyc
│ │ ├── vit_ce_prompt.cpython-37.pyc
│ │ └── vit_prompt.cpython-37.pyc
│ │ ├── attention.py
│ │ ├── base_backbone.py
│ │ ├── ostrack.py
│ │ ├── ostrack_prompt.py
│ │ ├── test_gradient.py
│ │ ├── utils.py
│ │ ├── vit.py
│ │ ├── vit_ce.py
│ │ ├── vit_ce_prompt.py
│ │ └── vit_prompt.py
├── test
│ ├── evaluation
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── data.cpython-37.pyc
│ │ │ ├── datasets.cpython-37.pyc
│ │ │ ├── environment.cpython-37.pyc
│ │ │ ├── local.cpython-37.pyc
│ │ │ ├── running.cpython-37.pyc
│ │ │ ├── tracker.cpython-37.pyc
│ │ │ └── votdataset.cpython-37.pyc
│ │ ├── data.py
│ │ ├── datasets.py
│ │ ├── environment.py
│ │ ├── local.py
│ │ ├── running.py
│ │ ├── tracker.py
│ │ ├── votdataset.py
│ │ └── vtuavdataset.py
│ ├── parameter
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── untrack.cpython-37.pyc
│ │ │ └── vipt.cpython-37.pyc
│ │ └── untrack.py
│ ├── tracker
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── basetracker.cpython-37.pyc
│ │ │ ├── data_utils.cpython-37.pyc
│ │ │ ├── ostrack.cpython-37.pyc
│ │ │ ├── untrack.cpython-37.pyc
│ │ │ ├── vipt.cpython-37.pyc
│ │ │ └── vis_utils.cpython-37.pyc
│ │ ├── basetracker.py
│ │ ├── data_utils.py
│ │ ├── ostrack.py
│ │ ├── untrack.py
│ │ └── vis_utils.py
│ ├── utils
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── hann.cpython-37.pyc
│ │ │ └── params.cpython-37.pyc
│ │ ├── _init_paths.py
│ │ ├── hann.py
│ │ ├── load_text.py
│ │ └── params.py
│ └── vot
│ │ ├── __pycache__
│ │ ├── untrack_baseline.cpython-37.pyc
│ │ ├── untrack_class.cpython-37.pyc
│ │ ├── vipt_baseline.cpython-37.pyc
│ │ ├── vipt_class.cpython-37.pyc
│ │ ├── vot.cpython-37.pyc
│ │ └── vot22_utils.cpython-37.pyc
│ │ ├── untrack_baseline.py
│ │ ├── untrack_class.py
│ │ ├── vot.py
│ │ └── vot22_utils.py
├── train
│ ├── __init__.py
│ ├── __pycache__
│ │ ├── __init__.cpython-310.pyc
│ │ ├── __init__.cpython-37.pyc
│ │ ├── _init_paths.cpython-310.pyc
│ │ ├── _init_paths.cpython-37.pyc
│ │ ├── base_functions.cpython-37.pyc
│ │ └── train_script.cpython-37.pyc
│ ├── _init_paths.py
│ ├── actors
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── base_actor.cpython-37.pyc
│ │ │ ├── untrack.cpython-37.pyc
│ │ │ └── vipt.cpython-37.pyc
│ │ ├── base_actor.py
│ │ └── untrack.py
│ ├── admin
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-310.pyc
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── environment.cpython-310.pyc
│ │ │ ├── environment.cpython-37.pyc
│ │ │ ├── local.cpython-37.pyc
│ │ │ ├── multigpu.cpython-310.pyc
│ │ │ ├── multigpu.cpython-37.pyc
│ │ │ ├── settings.cpython-310.pyc
│ │ │ ├── settings.cpython-37.pyc
│ │ │ ├── stats.cpython-310.pyc
│ │ │ ├── stats.cpython-37.pyc
│ │ │ ├── tensorboard.cpython-310.pyc
│ │ │ └── tensorboard.cpython-37.pyc
│ │ ├── environment.py
│ │ ├── local.py
│ │ ├── multigpu.py
│ │ ├── settings.py
│ │ ├── stats.py
│ │ └── tensorboard.py
│ ├── base_functions.py
│ ├── data
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── image_loader.cpython-37.pyc
│ │ │ ├── loader.cpython-37.pyc
│ │ │ ├── processing.cpython-37.pyc
│ │ │ ├── processing_utils.cpython-37.pyc
│ │ │ ├── sampler.cpython-37.pyc
│ │ │ ├── transforms.cpython-37.pyc
│ │ │ └── wandb_logger.cpython-37.pyc
│ │ ├── bounding_box_utils.py
│ │ ├── image_loader.py
│ │ ├── loader.py
│ │ ├── processing.py
│ │ ├── processing_utils.py
│ │ ├── sampler.py
│ │ ├── transforms.py
│ │ └── wandb_logger.py
│ ├── data_specs
│ │ ├── README.md
│ │ ├── depthtrack_train.txt
│ │ ├── depthtrack_val.txt
│ │ ├── got10k_train_full_split.txt
│ │ ├── got10k_train_split.txt
│ │ ├── got10k_val_split.txt
│ │ ├── got10k_vot_exclude.txt
│ │ ├── got10k_vot_train_split.txt
│ │ ├── got10k_vot_val_split.txt
│ │ ├── lasher_all.txt
│ │ ├── lasher_train.txt
│ │ ├── lasher_val.txt
│ │ ├── lasot_train_split.txt
│ │ ├── trackingnet_classmap.txt
│ │ └── visevent_train.txt
│ ├── dataset
│ │ ├── COCO_tool.py
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ │ ├── COCO_tool.cpython-37.pyc
│ │ │ ├── __init__.cpython-37.pyc
│ │ │ ├── base_image_dataset.cpython-37.pyc
│ │ │ ├── base_video_dataset.cpython-37.pyc
│ │ │ ├── coco.cpython-37.pyc
│ │ │ ├── coco_seq.cpython-37.pyc
│ │ │ ├── coco_seq_lmdb.cpython-37.pyc
│ │ │ ├── depth_utils.cpython-37.pyc
│ │ │ ├── depthtrack.cpython-37.pyc
│ │ │ ├── got10k.cpython-37.pyc
│ │ │ ├── got10k_lmdb.cpython-37.pyc
│ │ │ ├── imagenetvid.cpython-37.pyc
│ │ │ ├── imagenetvid_lmdb.cpython-37.pyc
│ │ │ ├── lasher.cpython-37.pyc
│ │ │ ├── lasot.cpython-37.pyc
│ │ │ ├── lasot_lmdb.cpython-37.pyc
│ │ │ ├── tracking_net.cpython-37.pyc
│ │ │ ├── tracking_net_lmdb.cpython-37.pyc
│ │ │ └── visevent.cpython-37.pyc
│ │ ├── base_image_dataset.py
│ │ ├── base_video_dataset.py
│ │ ├── coco.py
│ │ ├── coco_seq.py
│ │ ├── coco_seq_lmdb.py
│ │ ├── depth_utils.py
│ │ ├── depthtrack.py
│ │ ├── got10k.py
│ │ ├── got10k_lmdb.py
│ │ ├── imagenetvid.py
│ │ ├── imagenetvid_lmdb.py
│ │ ├── lasher.py
│ │ ├── lasot.py
│ │ ├── lasot_lmdb.py
│ │ ├── open_set.py
│ │ ├── tracking_net.py
│ │ ├── tracking_net_lmdb.py
│ │ └── visevent.py
│ ├── run_training.py
│ ├── train_script.py
│ └── trainers
│ │ ├── __init__.py
│ │ ├── __pycache__
│ │ ├── __init__.cpython-37.pyc
│ │ ├── base_trainer.cpython-37.pyc
│ │ └── ltr_trainer.cpython-37.pyc
│ │ ├── base_trainer.py
│ │ └── ltr_trainer.py
├── utils
│ ├── __init__.py
│ ├── __pycache__
│ │ ├── __init__.cpython-37.pyc
│ │ ├── box_ops.cpython-37.pyc
│ │ ├── ce_utils.cpython-37.pyc
│ │ ├── focal_loss.cpython-37.pyc
│ │ ├── heapmap_utils.cpython-37.pyc
│ │ ├── lmdb_utils.cpython-37.pyc
│ │ ├── misc.cpython-37.pyc
│ │ └── tensor.cpython-37.pyc
│ ├── box_ops.py
│ ├── ce_utils.py
│ ├── focal_loss.py
│ ├── heapmap_utils.py
│ ├── lmdb_utils.py
│ ├── merge.py
│ ├── misc.py
│ └── tensor.py
└── vis
│ ├── __init__.py
│ ├── __pycache__
│ ├── __init__.cpython-37.pyc
│ ├── plotting.cpython-37.pyc
│ ├── utils.cpython-37.pyc
│ └── visdom_cus.cpython-37.pyc
│ ├── plotting.py
│ ├── utils.py
│ └── visdom_cus.py
├── requirements.txt
├── tracking
├── __pycache__
│ └── _init_paths.cpython-37.pyc
├── _init_paths.py
├── create_default_local_file.py
├── test.py
└── train.py
└── train.sh
/.idea/.gitignore:
--------------------------------------------------------------------------------
1 | # Default ignored files
2 | /shelf/
3 | /workspace.xml
4 |
--------------------------------------------------------------------------------
/.idea/UnTrack.iml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
10 |
11 |
12 |
13 |
14 |
--------------------------------------------------------------------------------
/.idea/inspectionProfiles/profiles_settings.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
--------------------------------------------------------------------------------
/.idea/modules.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
--------------------------------------------------------------------------------
/.idea/vcs.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
--------------------------------------------------------------------------------
/Depthtrack_workspace/config.yaml:
--------------------------------------------------------------------------------
1 | registry:
2 | - ./trackers.ini
3 | stack: ./votrgbd2021.yaml
4 |
--------------------------------------------------------------------------------
/Depthtrack_workspace/list.txt:
--------------------------------------------------------------------------------
1 | pot_indoor
2 | cube05_indoor
3 | book03_indoor
4 | cup12_indoor
5 | toy02_indoor
6 | human02_indoor
7 | ball15_wild
8 | cat01_indoor
9 | bag02_indoor
10 | duck03_wild
11 | ball18_indoor
12 | ball20_indoor
13 | shoes02_indoor
14 | flag_indoor
15 | toy09_indoor
16 | cup01_indoor
17 | bottle04_indoor
18 | card_indoor
19 | ukulele01_indoor
20 | mobilephone03_indoor
21 | cube02_indoor
22 | cup02_indoor
23 | file01_indoor
24 | notebook01_indoor
25 | yogurt_indoor
26 | lock02_indoor
27 | beautifullight02_indoor
28 | toiletpaper01_indoor
29 | pigeon01_wild
30 | cube03_indoor
31 | ball06_indoor
32 | roller_indoor
33 | colacan03_indoor
34 | backpack_indoor
35 | bag01_indoor
36 | ball11_wild
37 | hand01_indoor
38 | stick_indoor
39 | earphone01_indoor
40 | cup04_indoor
41 | ball01_wild
42 | pigeon02_wild
43 | adapter01_indoor
44 | pigeon04_wild
45 | dumbbells01_indoor
46 | ball10_wild
47 | glass01_indoor
48 | squirrel_wild
49 | bandlight_indoor
50 | developmentboard_indoor
51 |
--------------------------------------------------------------------------------
/Depthtrack_workspace/trackers.ini:
--------------------------------------------------------------------------------
1 | [untrack_deep] #
2 | label = untrack_deep
3 | protocol = traxpython
4 |
5 | command = untrack_baseline
6 |
7 | # Specify a path to trax python wrapper if it is not visible (separate by ; if using multiple paths)
8 | paths = /home/zwu/Tracking/lib/test/vot
9 |
10 | # Additional environment paths
11 | # env_PATH = ${PATH}
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # UnTrack CVPR 2024
2 |
3 | Official implementation of "Single-Model and Any-Modality for Video Object Tracking" CVPR 2024 ([arxiv](https://arxiv.org/abs/2311.15851))
4 |
5 | We propose Un-Track, a Unified Tracker of a single set of parameters for any modality, which learns their common latent space with only the RGB-X pairs. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture and without the need for modality-specific fine-tuning.
6 |
7 | # Results
8 |
9 | Our ckpt can be found here ([Google Drive](https://drive.google.com/file/d/13GqlmhCKDl6jWJFvAsijuhOXD3kGJqqv/view?usp=sharing))
10 |
11 | Put the ckpt into the "models" folder.
12 |
13 | You should then be able to obtain our UnTrack results, which can also be downloaded here ([Google Drive](https://drive.google.com/file/d/1ruCYxvXnmtmfQQxV4t_JAsU9bneyPqIT/view?usp=sharing))
14 |
15 | A comparison against [ViPT](https://github.com/jiawen-zhu/ViPT) (SOTA specialized method) and [SeqTrack](https://github.com/microsoft/VideoX/tree/master/SeqTrack) (SOTA Tracker) can found in the following video:
16 |
17 | [](https://www.youtube.com/watch?v=MNvKQCeMLxg)
18 |
19 |
20 |
21 | ## Notes
22 |
23 | Our shared embedding is somehow similar to a Mixture of Experts (MoE) model.
24 |
25 | The difference is that we manually force the network to pick the best expert, according to the sensor prior, for feature processing.
26 |
27 | We have also developed a generalist and blind tracker, where the MoE is formally introduced and dynamically assigns the most appropriate expert for feature processing.
28 |
29 | More details can be found in the [[Preprint](https://arxiv.org/pdf/2405.17773)] or [[GitHub](https://github.com/supertyd/XTrack)]
30 |
31 | # Acknowledgments
32 | This repository is heavily based on [ViPT](https://github.com/jiawen-zhu/ViPT) and [OSTrack](https://github.com/botaoye/OSTrack). Thanks to their great work!
33 |
--------------------------------------------------------------------------------
/RGBT_workspace/attributes_RGBT234.xlsx:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/RGBT_workspace/attributes_RGBT234.xlsx
--------------------------------------------------------------------------------
/environment.yaml:
--------------------------------------------------------------------------------
1 | name: untrack
2 | channels:
3 | - pytorch
4 | - nvidia
5 | - defaults
6 | dependencies:
7 | - _libgcc_mutex=0.1=main
8 | - _openmp_mutex=5.1=1_gnu
9 | - blas=1.0=mkl
10 | - brotlipy=0.7.0=py37h27cfd23_1003
11 | - bzip2=1.0.8=h7b6447c_0
12 | - ca-certificates=2023.05.30=h06a4308_0
13 | - certifi=2022.12.7=py37h06a4308_0
14 | - cffi=1.15.1=py37h5eee18b_3
15 | - chardet=4.0.0=py37h06a4308_1003
16 | - cryptography=39.0.1=py37h9ce1e76_0
17 | - cuda-cudart=11.7.99=0
18 | - cuda-cupti=11.7.101=0
19 | - cuda-libraries=11.7.1=0
20 | - cuda-nvrtc=11.7.99=0
21 | - cuda-nvtx=11.7.91=0
22 | - cuda-runtime=11.7.1=0
23 | - cudatoolkit=10.2.89=hfd86e86_1
24 | - ffmpeg=4.3=hf484d3e_0
25 | - freetype=2.12.1=h4a9f257_0
26 | - giflib=5.2.1=h5eee18b_3
27 | - gmp=6.2.1=h295c915_3
28 | - gnutls=3.6.15=he1e5248_0
29 | - idna=3.4=py37h06a4308_0
30 | - intel-openmp=2021.4.0=h06a4308_3561
31 | - jpeg=9e=h5eee18b_1
32 | - lame=3.100=h7b6447c_0
33 | - lcms2=2.12=h3be6417_0
34 | - ld_impl_linux-64=2.38=h1181459_1
35 | - lerc=3.0=h295c915_0
36 | - libcublas=11.10.3.66=0
37 | - libcufft=10.7.2.124=h4fbf590_0
38 | - libcufile=1.7.0.149=0
39 | - libcurand=10.3.3.53=0
40 | - libcusolver=11.4.0.1=0
41 | - libcusparse=11.7.4.91=0
42 | - libdeflate=1.17=h5eee18b_0
43 | - libffi=3.4.4=h6a678d5_0
44 | - libgcc-ng=11.2.0=h1234567_1
45 | - libgomp=11.2.0=h1234567_1
46 | - libiconv=1.16=h7f8727e_2
47 | - libidn2=2.3.4=h5eee18b_0
48 | - libnpp=11.7.4.75=0
49 | - libnvjpeg=11.8.0.2=0
50 | - libpng=1.6.39=h5eee18b_0
51 | - libstdcxx-ng=11.2.0=h1234567_1
52 | - libtasn1=4.19.0=h5eee18b_0
53 | - libtiff=4.5.0=h6a678d5_2
54 | - libunistring=0.9.10=h27cfd23_0
55 | - libuv=1.44.2=h5eee18b_0
56 | - libwebp=1.2.4=h11a3e52_1
57 | - libwebp-base=1.2.4=h5eee18b_1
58 | - lz4-c=1.9.4=h6a678d5_0
59 | - mkl=2021.4.0=h06a4308_640
60 | - mkl-service=2.4.0=py37h7f8727e_0
61 | - mkl_fft=1.3.1=py37hd3c417c_0
62 | - mkl_random=1.2.2=py37h51133e4_0
63 | - ncurses=6.4=h6a678d5_0
64 | - nettle=3.7.3=hbbd107a_1
65 | - ninja=1.10.2=h06a4308_5
66 | - ninja-base=1.10.2=hd09550d_5
67 | - numpy=1.21.5=py37h6c91a56_3
68 | - numpy-base=1.21.5=py37ha15fc14_3
69 | - openh264=2.1.1=h4ff587b_0
70 | - openssl=1.1.1u=h7f8727e_0
71 | - pillow=9.4.0=py37h6a678d5_0
72 | - pip=22.3.1=py37h06a4308_0
73 | - pycparser=2.21=pyhd3eb1b0_0
74 | - pyopenssl=23.0.0=py37h06a4308_0
75 | - pysocks=1.7.1=py37_1
76 | - python=3.7.16=h7a1cb2a_0
77 | - pytorch=1.13.1=py3.7_cuda11.7_cudnn8.5.0_0
78 | - pytorch-cuda=11.7=h778d358_5
79 | - pytorch-mutex=1.0=cuda
80 | - readline=8.2=h5eee18b_0
81 | - setuptools=65.6.3=py37h06a4308_0
82 | - six=1.16.0=pyhd3eb1b0_1
83 | - sqlite=3.41.2=h5eee18b_0
84 | - tk=8.6.12=h1ccaba5_0
85 | - torchaudio=0.13.1=py37_cu117
86 | - torchvision=0.14.1=py37_cu117
87 | - tqdm=4.64.1=py37h06a4308_0
88 | - typing_extensions=4.3.0=py37h06a4308_0
89 | - wheel=0.38.4=py37h06a4308_0
90 | - xz=5.4.2=h5eee18b_0
91 | - zlib=1.2.13=h5eee18b_0
92 | - zstd=1.5.5=hc292b87_0
93 | - pip:
94 | - absl-py==1.4.0
95 | - appdirs==1.4.4
96 | - attributee==0.1.8
97 | - attrs==23.1.0
98 | - bidict==0.22.1
99 | - cachetools==5.3.1
100 | - charset-normalizer==3.2.0
101 | - click==8.1.7
102 | - colorama==0.4.6
103 | - cycler==0.11.0
104 | - cython==3.0.0
105 | - dataclasses==0.6
106 | - docker-pycreds==0.4.0
107 | - dominate==2.8.0
108 | - easydict==1.10
109 | - fonttools==4.38.0
110 | - future==0.18.3
111 | - gitdb==4.0.10
112 | - gitpython==3.1.32
113 | - google-auth==2.22.0
114 | - google-auth-oauthlib==0.4.6
115 | - grpcio==1.56.2
116 | - importlib-metadata==6.7.0
117 | - importlib-resources==5.12.0
118 | - info-nce-pytorch==0.1.4
119 | - install==1.3.5
120 | - jpeg4py==0.1.4
121 | - jsonpatch==1.33
122 | - jsonpointer==2.4
123 | - jsonschema==4.17.3
124 | - kiwisolver==1.4.4
125 | - lazy-object-proxy==1.9.0
126 | - llvmlite==0.39.1
127 | - lmdb==1.4.1
128 | - markdown==3.4.3
129 | - markupsafe==2.1.3
130 | - matplotlib==3.5.3
131 | - networkx==2.6.3
132 | - numba==0.56.4
133 | - oauthlib==3.2.2
134 | - opencv-python==4.8.0.74
135 | - ordered-set==4.1.0
136 | - packaging==23.1
137 | - pandas==1.3.5
138 | - pathtools==0.1.2
139 | - phx-class-registry==4.0.6
140 | - pkgutil-resolve-name==1.3.10
141 | - protobuf==3.20.3
142 | - psutil==5.9.5
143 | - pyasn1==0.5.0
144 | - pyasn1-modules==0.3.0
145 | - pycocotools==2.0.6
146 | - pylatex==1.4.1
147 | - pyparsing==3.1.0
148 | - pyrsistent==0.19.3
149 | - python-dateutil==2.8.2
150 | - pytz==2023.3
151 | - pyyaml==6.0.1
152 | - requests==2.31.0
153 | - requests-oauthlib==1.3.1
154 | - rsa==4.9
155 | - scipy==1.7.3
156 | - sentry-sdk==1.30.0
157 | - setproctitle==1.3.2
158 | - smmap==5.0.0
159 | - tb-nightly==2.12.0a20230113
160 | - tensorboard-data-server==0.6.1
161 | - tensorboard-plugin-wit==1.8.1
162 | - tensorly==0.8.1
163 | - timm==0.5.4
164 | - tornado==6.2
165 | - urllib3==1.26.16
166 | - visdom==0.2.4
167 | - vot-toolkit==0.5.3
168 | - vot-trax==3.0.2
169 | - wandb==0.15.9
170 | - websocket-client==1.6.1
171 | - werkzeug==2.2.3
172 | - zipp==3.15.0
173 | prefix: /home/zwu/anaconda3/envs/untrack
174 |
--------------------------------------------------------------------------------
/eval_all.sh:
--------------------------------------------------------------------------------
1 | # test lasher
2 |
3 | sh eval_rgbd.sh
4 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name LasHeR --yaml_name deep_rgbt
5 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name LasHeR --yaml_name deep_rgbt
6 |
7 | # test rgbt234
8 |
9 | CUDA_VISIBLE_DEVICES=0 python ./RGBE_workspace/test_rgbe_mgpus.py --script_name untrack --yaml_name deep_rgbe
10 | CUDA_VISIBLE_DEVICES=0 python ./RGBE_workspace/test_rgbe_mgpus.py --script_name untrack --yaml_name deep_rgbe
11 |
12 |
13 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name RGBT234 --yaml_name deep_rgbt
14 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name RGBT234 --yaml_name deep_rgbt
15 |
16 |
--------------------------------------------------------------------------------
/eval_rgbd.sh:
--------------------------------------------------------------------------------
1 | # eval depthtrack
2 | cd Depthtrack_workspace
3 | vot evaluate --workspace ./ untrack_deep
4 | vot analysis --nocache --name untrack_deep
5 | cd ..
6 |
--------------------------------------------------------------------------------
/eval_rgbe.sh:
--------------------------------------------------------------------------------
1 | # test visevent
2 | CUDA_VISIBLE_DEVICES=0 python ./RGBE_workspace/test_rgbe_mgpus.py --script_name untrack --yaml_name deep_rgbe
3 |
--------------------------------------------------------------------------------
/eval_rgbt.sh:
--------------------------------------------------------------------------------
1 | # test lasher
2 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name LasHeR --yaml_name deep_rgbt
3 |
4 | # test rgbt234
5 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name RGBT234 --yaml_name deep_rgbt
6 |
--------------------------------------------------------------------------------
/eval_rgbtlasher.sh:
--------------------------------------------------------------------------------
1 | # test lasher
2 | CUDA_VISIBLE_DEVICES=0 python ./RGBT_workspace/test_rgbt_mgpus.py --script_name untrack --dataset_name LasHeR --yaml_name deep_rgbt
3 |
--------------------------------------------------------------------------------
/eval_rgbvotd.sh:
--------------------------------------------------------------------------------
1 | # eval depthtrack
2 | #cd Depthtrack_workspace
3 | #vot evaluate --workspace ./ untrack_deep
4 | #vot analysis --nocache --name untrack_deep
5 | #cd ..
6 |
7 | ## eval vot22-rgbd
8 | cd VOT22RGBD_workspace
9 | vot evaluate --workspace ./ untrack_deep
10 | vot analysis --nocache --name untrack_deep
11 | cd ..
12 |
13 |
--------------------------------------------------------------------------------
/experiments/untrack/deep_rgbd.yaml:
--------------------------------------------------------------------------------
1 | DATA:
2 | MAX_SAMPLE_INTERVAL: 200
3 | MEAN:
4 | - 0.485
5 | - 0.456
6 | - 0.406
7 | SEARCH:
8 | CENTER_JITTER: 3
9 | FACTOR: 4.0
10 | SCALE_JITTER: 0.25
11 | SIZE: 256
12 | NUMBER: 1
13 | STD:
14 | - 0.229
15 | - 0.224
16 | - 0.225
17 | TEMPLATE:
18 | CENTER_JITTER: 0
19 | FACTOR: 2.0
20 | SCALE_JITTER: 0
21 | SIZE: 128
22 | TRAIN:
23 | DATASETS_NAME:
24 | - DepthTrack_train
25 | DATASETS_RATIO:
26 | - 1
27 | SAMPLE_PER_EPOCH: 60000
28 | VAL:
29 | DATASETS_NAME:
30 | - DepthTrack_val
31 | DATASETS_RATIO:
32 | - 1
33 | SAMPLE_PER_EPOCH: 10000
34 | MODEL:
35 | PRETRAIN_FILE: "./pretrained/OSTrack_ep0300.pth.tar"
36 | EXTRA_MERGER: False
37 | RETURN_INTER: False
38 | BACKBONE:
39 | TYPE: vit_base_patch16_224_ce_prompt
40 | STRIDE: 16
41 | CE_LOC: [3, 6, 9]
42 | CE_KEEP_RATIO: [0.7, 0.7, 0.7]
43 | CE_TEMPLATE_RANGE: 'CTR_POINT' # choose between ALL, CTR_POINT, CTR_REC, GT_BOX
44 | HEAD:
45 | TYPE: CENTER
46 | NUM_CHANNELS: 256
47 | TRAIN:
48 | BACKBONE_MULTIPLIER: 0.1
49 | DROP_PATH_RATE: 0.1
50 | CE_START_EPOCH: 4 # candidate elimination start epoch 1/15
51 | CE_WARM_EPOCH: 16 # candidate elimination warm up epoch 4/15
52 | BATCH_SIZE: 32
53 | EPOCH: 60
54 | GIOU_WEIGHT: 2.0
55 | L1_WEIGHT: 5.0
56 | GRAD_CLIP_NORM: 0.1
57 | LR: 0.0004
58 | LR_DROP_EPOCH: 48 # 4/5
59 | NUM_WORKER: 10
60 | OPTIMIZER: ADAMW
61 | PRINT_INTERVAL: 50
62 | SCHEDULER:
63 | TYPE: step
64 | DECAY_RATE: 0.1
65 | VAL_EPOCH_INTERVAL: 5
66 | WEIGHT_DECAY: 0.0001
67 | AMP: False
68 | PROMPT:
69 | TYPE: deep
70 | FIX_BN: true
71 | SAVE_EPOCH_INTERVAL: 5
72 | SAVE_LAST_N_EPOCH: 1
73 | TEST:
74 | EPOCH: 60
75 | SEARCH_FACTOR: 4.0
76 | SEARCH_SIZE: 256
77 | TEMPLATE_FACTOR: 2.0
78 | TEMPLATE_SIZE: 128
79 |
--------------------------------------------------------------------------------
/experiments/untrack/deep_rgbe.yaml:
--------------------------------------------------------------------------------
1 | DATA:
2 | MAX_SAMPLE_INTERVAL: 200
3 | MEAN:
4 | - 0.485
5 | - 0.456
6 | - 0.406
7 | SEARCH:
8 | CENTER_JITTER: 3
9 | FACTOR: 4.0
10 | SCALE_JITTER: 0.25
11 | SIZE: 256
12 | NUMBER: 1
13 | STD:
14 | - 0.229
15 | - 0.224
16 | - 0.225
17 | TEMPLATE:
18 | CENTER_JITTER: 0
19 | FACTOR: 2.0
20 | SCALE_JITTER: 0
21 | SIZE: 128
22 | TRAIN:
23 | DATASETS_NAME:
24 | - VisEvent
25 | DATASETS_RATIO:
26 | - 1
27 | SAMPLE_PER_EPOCH: 60000
28 | VAL:
29 | DATASETS_NAME:
30 | -
31 | DATASETS_RATIO:
32 | - 1
33 | SAMPLE_PER_EPOCH: 10000
34 | MODEL:
35 | PRETRAIN_FILE: "./pretrained/OSTrack_ep0300.pth.tar"
36 | EXTRA_MERGER: False
37 | RETURN_INTER: False
38 | BACKBONE:
39 | TYPE: vit_base_patch16_224_ce_prompt
40 | STRIDE: 16
41 | CE_LOC: [3, 6, 9]
42 | CE_KEEP_RATIO: [0.7, 0.7, 0.7]
43 | CE_TEMPLATE_RANGE: 'CTR_POINT' # choose between ALL, CTR_POINT, CTR_REC, GT_BOX
44 | HEAD:
45 | TYPE: CENTER
46 | NUM_CHANNELS: 256
47 | TRAIN:
48 | BACKBONE_MULTIPLIER: 0.1
49 | DROP_PATH_RATE: 0.1
50 | CE_START_EPOCH: 4 # candidate elimination start epoch 1/15
51 | CE_WARM_EPOCH: 16 # candidate elimination warm up epoch 4/15
52 | BATCH_SIZE: 32
53 | EPOCH: 60
54 | GIOU_WEIGHT: 2.0
55 | L1_WEIGHT: 5.0
56 | GRAD_CLIP_NORM: 0.1
57 | LR: 0.0004
58 | LR_DROP_EPOCH: 48 # 4/5
59 | NUM_WORKER: 10
60 | OPTIMIZER: ADAMW
61 | PRINT_INTERVAL: 50
62 | SCHEDULER:
63 | TYPE: step
64 | DECAY_RATE: 0.1
65 | VAL_EPOCH_INTERVAL: 5
66 | WEIGHT_DECAY: 0.0001
67 | AMP: False
68 | PROMPT:
69 | TYPE: deep
70 | FIX_BN: true
71 | SAVE_EPOCH_INTERVAL: 5
72 | SAVE_LAST_N_EPOCH: 1
73 | TEST:
74 | EPOCH: 60
75 | SEARCH_FACTOR: 4.0
76 | SEARCH_SIZE: 256
77 | TEMPLATE_FACTOR: 2.0
78 | TEMPLATE_SIZE: 128
79 |
--------------------------------------------------------------------------------
/experiments/untrack/deep_rgbt.yaml:
--------------------------------------------------------------------------------
1 | DATA:
2 | MAX_SAMPLE_INTERVAL: 200
3 | MEAN:
4 | - 0.485
5 | - 0.456
6 | - 0.406
7 | SEARCH:
8 | CENTER_JITTER: 3
9 | FACTOR: 4.0
10 | SCALE_JITTER: 0.25
11 | SIZE: 256
12 | NUMBER: 1
13 | STD:
14 | - 0.229
15 | - 0.224
16 | - 0.225
17 | TEMPLATE:
18 | CENTER_JITTER: 0
19 | FACTOR: 2.0
20 | SCALE_JITTER: 0
21 | SIZE: 128
22 | TRAIN:
23 | DATASETS_NAME:
24 | - LasHeR_train
25 | DATASETS_RATIO:
26 | - 1
27 | SAMPLE_PER_EPOCH: 60000
28 | VAL:
29 | DATASETS_NAME:
30 | - LasHeR_val
31 | DATASETS_RATIO:
32 | - 1
33 | SAMPLE_PER_EPOCH: 10000
34 | MODEL:
35 | PRETRAIN_FILE: "./pretrained/OSTrack_ep0300.pth.tar"
36 | EXTRA_MERGER: False
37 | RETURN_INTER: False
38 | BACKBONE:
39 | TYPE: vit_base_patch16_224_ce_prompt
40 | STRIDE: 16
41 | CE_LOC: [3, 6, 9]
42 | CE_KEEP_RATIO: [0.7, 0.7, 0.7]
43 | CE_TEMPLATE_RANGE: 'CTR_POINT' # choose between ALL, CTR_POINT, CTR_REC, GT_BOX
44 | HEAD:
45 | TYPE: CENTER
46 | NUM_CHANNELS: 256
47 | TRAIN:
48 | BACKBONE_MULTIPLIER: 0.1
49 | DROP_PATH_RATE: 0.1
50 | CE_START_EPOCH: 4 # candidate elimination start epoch 1/15
51 | CE_WARM_EPOCH: 16 # candidate elimination warm up epoch 4/15
52 | BATCH_SIZE: 64
53 | EPOCH: 60
54 | GIOU_WEIGHT: 2.0
55 | L1_WEIGHT: 5.0
56 | GRAD_CLIP_NORM: 0.1
57 | LR: 0.0004
58 | LR_DROP_EPOCH: 48 # 4/5
59 | NUM_WORKER: 10
60 | OPTIMIZER: ADAMW
61 | PRINT_INTERVAL: 50
62 | SCHEDULER:
63 | TYPE: step
64 | DECAY_RATE: 0.1
65 | VAL_EPOCH_INTERVAL: 5
66 | WEIGHT_DECAY: 0.0001
67 | AMP: False
68 | PROMPT:
69 | TYPE: deep
70 | FIX_BN: true
71 | SAVE_EPOCH_INTERVAL: 5
72 | SAVE_LAST_N_EPOCH: 1
73 | TEST:
74 | EPOCH: 60
75 | SEARCH_FACTOR: 4.0
76 | SEARCH_SIZE: 256
77 | TEMPLATE_FACTOR: 2.0
78 | TEMPLATE_SIZE: 128
79 |
--------------------------------------------------------------------------------
/experiments/untrack/deep_rgbx.yaml:
--------------------------------------------------------------------------------
1 | DATA:
2 | MAX_SAMPLE_INTERVAL: 200
3 | MEAN:
4 | - 0.485
5 | - 0.456
6 | - 0.406
7 | SEARCH:
8 | CENTER_JITTER: 3
9 | FACTOR: 4.0
10 | SCALE_JITTER: 0.25
11 | SIZE: 256
12 | NUMBER: 1
13 | STD:
14 | - 0.229
15 | - 0.224
16 | - 0.225
17 | TEMPLATE:
18 | CENTER_JITTER: 0
19 | FACTOR: 2.0
20 | SCALE_JITTER: 0
21 | SIZE: 128
22 | TRAIN:
23 | DATASETS_NAME:
24 | - DepthTrack_LasHeR_VisEvent
25 | DATASETS_RATIO:
26 | - 1
27 | - 1
28 | - 1
29 | SAMPLE_PER_EPOCH: 60000 # 60000
30 | VAL:
31 | DATASETS_NAME:
32 | - DepthTrack_LasHeR_val
33 | DATASETS_RATIO:
34 | - 1
35 | - 1
36 | SAMPLE_PER_EPOCH: 10000 # 10000
37 | MODEL:
38 | PRETRAIN_FILE: "./pretrained/OSTrack_ep0300.pth.tar"
39 | EXTRA_MERGER: False
40 | RETURN_INTER: False
41 | BACKBONE:
42 | TYPE: vit_base_patch16_224_ce_prompt
43 | STRIDE: 16
44 | CE_LOC: [3, 6, 9]
45 | CE_KEEP_RATIO: [0.7, 0.7, 0.7]
46 | CE_TEMPLATE_RANGE: 'CTR_POINT' # choose between ALL, CTR_POINT, CTR_REC, GT_BOX
47 | HEAD:
48 | TYPE: CENTER
49 | NUM_CHANNELS: 256
50 | TRAIN:
51 | BACKBONE_MULTIPLIER: 0.1
52 | DROP_PATH_RATE: 0.1
53 | CE_START_EPOCH: 4 # candidate elimination start epoch 1/15
54 | CE_WARM_EPOCH: 16 # candidate elimination warm up epoch 4/15
55 | BATCH_SIZE: 48 #32
56 | EPOCH: 80
57 | GIOU_WEIGHT: 2.0
58 | L1_WEIGHT: 5.0
59 | GRAD_CLIP_NORM: 0.1
60 | LR: 0.0004
61 | LR_DROP_EPOCH: 48
62 | NUM_WORKER: 10
63 | OPTIMIZER: ADAMW
64 | PRINT_INTERVAL: 50
65 | SCHEDULER:
66 | TYPE: step
67 | DECAY_RATE: 0.1
68 | VAL_EPOCH_INTERVAL: 5
69 | WEIGHT_DECAY: 0.0001
70 | AMP: False
71 | PROMPT:
72 | TYPE: deep
73 | FIX_BN: true
74 | SAVE_EPOCH_INTERVAL: 5
75 | SAVE_LAST_N_EPOCH: 1
76 | TEST:
77 | EPOCH: 60
78 | SEARCH_FACTOR: 4.0
79 | SEARCH_SIZE: 256
80 | TEMPLATE_FACTOR: 2.0
81 | TEMPLATE_SIZE: 128
82 |
--------------------------------------------------------------------------------
/install.sh:
--------------------------------------------------------------------------------
1 | echo "****************** Installing pytorch ******************"
2 | conda install -y pytorch==1.7.0 torchvision==0.8.1 cudatoolkit=10.2 -c pytorch
3 |
4 | echo ""
5 | echo ""
6 | echo "****************** Installing yaml ******************"
7 | pip install PyYAML
8 |
9 | echo ""
10 | echo ""
11 | echo "****************** Installing easydict ******************"
12 | pip install easydict
13 |
14 | echo ""
15 | echo ""
16 | echo "****************** Installing cython ******************"
17 | pip install cython
18 |
19 | echo ""
20 | echo ""
21 | echo "****************** Installing opencv-python ******************"
22 | pip install opencv-python
23 |
24 | echo ""
25 | echo ""
26 | echo "****************** Installing pandas ******************"
27 | pip install pandas
28 |
29 | echo ""
30 | echo ""
31 | echo "****************** Installing tqdm ******************"
32 | conda install -y tqdm
33 |
34 | echo ""
35 | echo ""
36 | echo "****************** Installing coco toolkit ******************"
37 | pip install pycocotools
38 |
39 | echo ""
40 | echo ""
41 | echo "****************** Installing jpeg4py python wrapper ******************"
42 | apt-get install libturbojpeg
43 | pip install jpeg4py
44 |
45 | echo ""
46 | echo ""
47 | echo "****************** Installing scipy ******************"
48 | pip install scipy
49 |
50 | echo ""
51 | echo ""
52 | echo "****************** Installing timm ******************"
53 | pip install timm==0.5.4
54 |
55 | echo ""
56 | echo ""
57 | echo "****************** Installing tensorboard ******************"
58 | pip install tb-nightly
59 |
60 | echo ""
61 | echo ""
62 | echo "****************** Installing lmdb ******************"
63 | pip install lmdb
64 |
65 | echo ""
66 | echo ""
67 | echo "****************** Installing visdom ******************"
68 | pip install visdom
69 |
70 | echo ""
71 | echo ""
72 | echo "****************** Installing vot-toolkit python ******************"
73 | pip install git+https://github.com/votchallenge/vot-toolkit-python
74 |
75 | echo "****************** Installation complete! ******************"
--------------------------------------------------------------------------------
/lib/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/__init__.py
--------------------------------------------------------------------------------
/lib/__pycache__/__init__.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/__pycache__/__init__.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/config/untrack/__pycache__/config.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/config/untrack/__pycache__/config.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/config/untrack/config.py:
--------------------------------------------------------------------------------
1 | from easydict import EasyDict as edict
2 | import yaml
3 |
4 | """
5 | Add default config for UnTrack.
6 | """
7 | cfg = edict()
8 |
9 | # MODEL
10 | cfg.MODEL = edict()
11 | cfg.MODEL.PRETRAIN_FILE = ""
12 | cfg.MODEL.EXTRA_MERGER = False
13 | cfg.MODEL.RETURN_INTER = False
14 | cfg.MODEL.RETURN_STAGES = []
15 |
16 | # MODEL.BACKBONE
17 | cfg.MODEL.BACKBONE = edict()
18 | cfg.MODEL.BACKBONE.TYPE = "vit_base_patch16_224"
19 | cfg.MODEL.BACKBONE.STRIDE = 16
20 | cfg.MODEL.BACKBONE.MID_PE = False
21 | cfg.MODEL.BACKBONE.SEP_SEG = False
22 | cfg.MODEL.BACKBONE.CAT_MODE = 'direct'
23 | cfg.MODEL.BACKBONE.MERGE_LAYER = 0
24 | cfg.MODEL.BACKBONE.ADD_CLS_TOKEN = False
25 | cfg.MODEL.BACKBONE.CLS_TOKEN_USE_MODE = 'ignore'
26 |
27 | cfg.MODEL.BACKBONE.CE_LOC = []
28 | cfg.MODEL.BACKBONE.CE_KEEP_RATIO = []
29 | cfg.MODEL.BACKBONE.CE_TEMPLATE_RANGE = 'ALL' # choose between ALL, CTR_POINT, CTR_REC, GT_BOX
30 |
31 | # MODEL.HEAD
32 | cfg.MODEL.HEAD = edict()
33 | cfg.MODEL.HEAD.TYPE = "CENTER"
34 | cfg.MODEL.HEAD.NUM_CHANNELS = 256
35 |
36 | # TRAIN
37 | cfg.TRAIN = edict()
38 | cfg.TRAIN.PROMPT = edict()
39 | cfg.TRAIN.PROMPT.TYPE = 'deep'
40 | cfg.TRAIN.LR = 0.0001
41 | cfg.TRAIN.WEIGHT_DECAY = 0.0001
42 | cfg.TRAIN.EPOCH = 500
43 | cfg.TRAIN.LR_DROP_EPOCH = 400
44 | cfg.TRAIN.BATCH_SIZE = 16
45 | cfg.TRAIN.NUM_WORKER = 8
46 | cfg.TRAIN.OPTIMIZER = "ADAMW"
47 | cfg.TRAIN.BACKBONE_MULTIPLIER = 0.1
48 | cfg.TRAIN.GIOU_WEIGHT = 2.0
49 | cfg.TRAIN.L1_WEIGHT = 5.0
50 | cfg.TRAIN.FREEZE_LAYERS = [0, ]
51 | cfg.TRAIN.PRINT_INTERVAL = 50
52 | cfg.TRAIN.VAL_EPOCH_INTERVAL = 20
53 | cfg.TRAIN.GRAD_CLIP_NORM = 0.1
54 | cfg.TRAIN.AMP = False
55 | ## TRAIN save cfgs
56 | cfg.TRAIN.FIX_BN = True
57 | cfg.TRAIN.SAVE_EPOCH_INTERVAL = 1 # 1 means save model each epoch
58 | cfg.TRAIN.SAVE_LAST_N_EPOCH = 1 # besides, last n epoch model will be saved
59 |
60 | cfg.TRAIN.CE_START_EPOCH = 20 # candidate elimination start epoch
61 | cfg.TRAIN.CE_WARM_EPOCH = 80 # candidate elimination warm up epoch
62 | cfg.TRAIN.DROP_PATH_RATE = 0.1 # drop path rate for ViT backbone
63 |
64 | # TRAIN.SCHEDULER
65 | cfg.TRAIN.SCHEDULER = edict()
66 | cfg.TRAIN.SCHEDULER.TYPE = "step"
67 | cfg.TRAIN.SCHEDULER.DECAY_RATE = 0.1
68 |
69 | # DATA
70 | cfg.DATA = edict()
71 | cfg.DATA.SAMPLER_MODE = "causal" # sampling methods
72 | cfg.DATA.MEAN = [0.485, 0.456, 0.406]
73 | cfg.DATA.STD = [0.229, 0.224, 0.225]
74 | cfg.DATA.MAX_SAMPLE_INTERVAL = 200
75 | # DATA.TRAIN
76 | cfg.DATA.TRAIN = edict()
77 | cfg.DATA.TRAIN.DATASETS_NAME = ["LASOT", "GOT10K_vottrain"]
78 | cfg.DATA.TRAIN.DATASETS_RATIO = [1, 1]
79 | cfg.DATA.TRAIN.SAMPLE_PER_EPOCH = 60000
80 | # DATA.VAL
81 | cfg.DATA.VAL = edict()
82 | cfg.DATA.VAL.DATASETS_NAME = []
83 | cfg.DATA.VAL.DATASETS_RATIO = [1]
84 | cfg.DATA.VAL.SAMPLE_PER_EPOCH = 10000
85 | # DATA.SEARCH
86 | cfg.DATA.SEARCH = edict()
87 | cfg.DATA.SEARCH.SIZE = 320
88 | cfg.DATA.SEARCH.FACTOR = 5.0
89 | cfg.DATA.SEARCH.CENTER_JITTER = 4.5
90 | cfg.DATA.SEARCH.SCALE_JITTER = 0.5
91 | cfg.DATA.SEARCH.NUMBER = 1
92 | # DATA.TEMPLATE
93 | cfg.DATA.TEMPLATE = edict()
94 | cfg.DATA.TEMPLATE.NUMBER = 1
95 | cfg.DATA.TEMPLATE.SIZE = 128
96 | cfg.DATA.TEMPLATE.FACTOR = 2.0
97 | cfg.DATA.TEMPLATE.CENTER_JITTER = 0
98 | cfg.DATA.TEMPLATE.SCALE_JITTER = 0
99 |
100 | # TEST
101 | cfg.TEST = edict()
102 | cfg.TEST.TEMPLATE_FACTOR = 2.0
103 | cfg.TEST.TEMPLATE_SIZE = 128
104 | cfg.TEST.SEARCH_FACTOR = 5.0
105 | cfg.TEST.SEARCH_SIZE = 320
106 | cfg.TEST.EPOCH = 500
107 |
108 |
109 | def _edict2dict(dest_dict, src_edict):
110 | if isinstance(dest_dict, dict) and isinstance(src_edict, dict):
111 | for k, v in src_edict.items():
112 | if not isinstance(v, edict):
113 | dest_dict[k] = v
114 | else:
115 | dest_dict[k] = {}
116 | _edict2dict(dest_dict[k], v)
117 | else:
118 | return
119 |
120 |
121 | def gen_config(config_file):
122 | cfg_dict = {}
123 | _edict2dict(cfg_dict, cfg)
124 | with open(config_file, 'w') as f:
125 | yaml.dump(cfg_dict, f, default_flow_style=False)
126 |
127 |
128 | def _update_config(base_cfg, exp_cfg):
129 | if isinstance(base_cfg, dict) and isinstance(exp_cfg, edict):
130 | for k, v in exp_cfg.items():
131 | if k in base_cfg:
132 | if not isinstance(v, dict):
133 | base_cfg[k] = v
134 | else:
135 | _update_config(base_cfg[k], v)
136 | else:
137 | raise ValueError("{} not exist in config.py".format(k))
138 | else:
139 | return
140 |
141 |
142 | def update_config_from_file(filename, base_cfg=None):
143 | exp_config = None
144 | with open(filename) as f:
145 | exp_config = edict(yaml.safe_load(f))
146 | if base_cfg is not None:
147 | _update_config(base_cfg, exp_config)
148 | else:
149 | _update_config(cfg, exp_config)
150 |
--------------------------------------------------------------------------------
/lib/models/__init__.py:
--------------------------------------------------------------------------------
1 | from .untrack.ostrack_prompt import build_untrack
2 |
--------------------------------------------------------------------------------
/lib/models/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/MoE_prompt.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import torch.nn as nn
3 | import torch.nn.functional as F
4 |
5 | # class Expert(nn.Module):
6 | # def __init__(self, in_features, out_features):
7 | # super(Expert, self).__init__()
8 | # self.layer = nn.Linear(in_features, out_features)
9 | #
10 | # def forward(self, x):
11 | # return F.relu(self.layer(x))
12 | #
13 | #
14 | # class Router(nn.Module):
15 | # def __init__(self, in_features, num_experts):
16 | # super(Router, self).__init__()
17 | # self.network = nn.Sequential(
18 | # nn.Linear(in_features, 128),
19 | # nn.ReLU(),
20 | # nn.Linear(128, num_experts)
21 | # )
22 | #
23 | # def forward(self, x):
24 | # return F.softmax(self.network(x), dim=1)
25 | #
26 | #
27 | # # class MoE(nn.Module):
28 | # # def __init(self, in_features, out_features, num_experts):
29 | # # super(MoE, self).__init__()
30 | # # self.gate = nn.Linear(in_features, num_experts)
31 | # # self.experts = nn.ModuleList([Expert(in_features, out_features) for i in range(num_experts)])
32 | # #
33 | # # def foward(self, x):
34 | # # gate_output = F.softmax(self.gate(x), dim=1)
35 | # # expert_outputs = [expert(x) for expert in self.experts]
36 | # # final_output = 0
37 | # # for i, expert_output in enumerate(expert_outputs):
38 | # # final_output += gate_output[:, i].unsqueeze(1) * expert_output
39 | # # return final_output
40 | #
41 | #
42 | # class MoE(nn.Module):
43 | # def __init(self, in_features, out_features, num_experts):
44 | # super(MoE, self).__init__()
45 | # self.gate = Router(in_features, num_experts)
46 | # self.experts = nn.ModuleList([Expert(in_features, out_features) for i in range(num_experts)])
47 | #
48 | # def foward(self, x):
49 | # gate_output = self.gate(x)
50 | # scores, indices = torch.sort(gate_output, dim=1, descending=True)
51 | # final_output = 0
52 | # for i in range(6):
53 | # expert_output = self.experts[indices[:, i]](x)
54 | # final_output += scores[:, i].unsqueeze(1) * expert_output
55 | # return final_output
56 | class Expert(nn.Module):
57 | def __init__(self):
58 | super(Expert, self).__init__()
59 | self.layer = nn.Sequential(
60 | nn.Linear(768,1024),
61 | nn.ReLU(),
62 | nn.Linear(1024,1024),
63 | nn.ReLU(),
64 | nn.Linear(1024,768),
65 | )
66 |
67 | def forward(self, x):
68 | p_task = F.softmax(self.layer(x), dim=-1)
69 | return self.layer(x), p_task
70 |
71 |
72 | class Router(nn.Module):
73 | def __init__(self, num_experts):
74 | super(Router, self).__init__()
75 | self.pool = nn.AdaptiveAvgPool1d(1)
76 | self.network = nn.Sequential(
77 | nn.Linear(768, 128),
78 | nn.ReLU(),
79 | nn.Linear(128, num_experts)
80 | )
81 |
82 | def forward(self, x):
83 | x = x.permute(0,2,1)
84 | x = self.pool(x)
85 | #print('x.pool',x.shape)
86 | x = x.squeeze(-1)
87 | #print('squeeze',x.shape)
88 | return F.softmax(self.network(x), dim=1)
89 |
90 |
91 | class MoE(nn.Module):
92 | def __init__(self, num_experts=2):
93 | super(MoE, self).__init__()
94 | self.gate = Router(num_experts)
95 | self.experts = nn.ModuleList([Expert() for _ in range(num_experts)])
96 |
97 | def forward(self, x):
98 | #print('inputshape',x.shape) (32,64,768)
99 | gate_output = self.gate(x) #(32,64,10)
100 | #print('gateoutput',gate_output.shape) (32,10)
101 | topk_values, topk_indices = torch.topk(gate_output, 2, dim=1)
102 | #print('topk_indices',topk_indices.shape)(32,6)
103 | #print('ttttttt', topk_indices.t().shape)# (6,32)
104 | #print('topk_value',topk_values.shape)(32,6)
105 | #x_reshape = x.reshape(-1, x.shape[-1])
106 | #print('x_reshape', x_reshape.shape)(2048,768)
107 | #topk_indices - topk_indices.permute(1,0)
108 | expert_output = torch.stack([expert(x)[-1] for expert in self.experts])
109 | #print('expert_output', expert_output.shape)#(10,32,64,768)
110 | #print('unsqueeze', topk_indices.unsqueeze(2).expand(-1, -1, expert_output.shape[-1]).shape) #(32,6,768)
111 | topk_indices = topk_indices.t().unsqueeze(2)
112 | topk_indices =topk_indices.unsqueeze(3)
113 | #print('unsqueeze2',topk_indices.shape)
114 | expert_output_topk = expert_output.gather(0, topk_indices.expand(-1, -1, expert_output.shape[-2],expert_output.shape[-1]))
115 | #print('expertoutputtopk',expert_output_topk.shape)#6,32,64,768
116 | # expert_outputs = [self.experts[idx](x) for idx in topk_indices]
117 | final_output = 0
118 | for i, expert_output in enumerate(expert_output_topk):
119 | weight = topk_values[:, i].unsqueeze(1).unsqueeze(1).unsqueeze(0)
120 | #print(weight.shape)
121 | final_output += weight*expert_output
122 | #print(final_output.shape)
123 | #print('use MoE')
124 | final_output = final_output.squeeze(0)
125 | return final_output
126 |
127 | def mutual_info_loss(self, p_z, p_t_given_z):
128 | H_z = -torch.sum(p_z * torch.log(p_z), dim=1)
129 | H_t_given_z = -torch.sum(p_t_given_z * torch.log(p_t_given_z), dim=1)
130 | L_mi = H_z - torch.sum(p_z * H_t_given_z, dim=1)
131 |
132 | return L_mi
133 |
134 |
135 | if __name__ == "__main__":
136 | model = MoE().cuda()
137 | inp = torch.randn(32, 64, 768).cuda()
138 | out = model(inp)
139 |
--------------------------------------------------------------------------------
/lib/models/layers/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__init__.py
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/MoE_prompt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/MoE_prompt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/attn.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/attn.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/attn_blocks.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/attn_blocks.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/frozen_bn.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/frozen_bn.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/head.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/head.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/patch_embed.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/patch_embed.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/__pycache__/rpe.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/layers/__pycache__/rpe.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/layers/attn.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import torch.nn as nn
3 | import torch.nn.functional as F
4 | from timm.models.layers import trunc_normal_
5 |
6 | from lib.models.layers.rpe import generate_2d_concatenated_self_attention_relative_positional_encoding_index
7 |
8 |
9 | class Attention(nn.Module):
10 | def __init__(self, dim, num_heads=8, qkv_bias=False, attn_drop=0., proj_drop=0.,
11 | rpe=False, z_size=7, x_size=14):
12 | super().__init__()
13 | self.num_heads = num_heads
14 | head_dim = dim // num_heads
15 | self.scale = head_dim ** -0.5
16 |
17 | self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
18 | self.attn_drop = nn.Dropout(attn_drop)
19 | self.proj = nn.Linear(dim, dim)
20 | self.proj_drop = nn.Dropout(proj_drop)
21 |
22 | self.rpe =rpe
23 | if self.rpe:
24 | relative_position_index = \
25 | generate_2d_concatenated_self_attention_relative_positional_encoding_index([z_size, z_size],
26 | [x_size, x_size])
27 | self.register_buffer("relative_position_index", relative_position_index)
28 | # define a parameter table of relative position bias
29 | self.relative_position_bias_table = nn.Parameter(torch.empty((num_heads,
30 | relative_position_index.max() + 1)))
31 | trunc_normal_(self.relative_position_bias_table, std=0.02)
32 |
33 | def forward(self, x, mask=None, return_attention=False):
34 | # x: B, N, C
35 | # mask: [B, N, ] torch.bool
36 | B, N, C = x.shape
37 | qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
38 | q, k, v = qkv.unbind(0) # make torchscript happy (cannot use tensor as tuple)
39 |
40 | attn = (q @ k.transpose(-2, -1)) * self.scale
41 |
42 | if self.rpe:
43 | relative_position_bias = self.relative_position_bias_table[:, self.relative_position_index].unsqueeze(0)
44 | attn += relative_position_bias
45 |
46 | if mask is not None:
47 | attn = attn.masked_fill(mask.unsqueeze(1).unsqueeze(2), float('-inf'),)
48 |
49 | attn = attn.softmax(dim=-1)
50 | attn = self.attn_drop(attn)
51 |
52 | x = (attn @ v).transpose(1, 2).reshape(B, N, C)
53 | x = self.proj(x)
54 | x = self.proj_drop(x)
55 |
56 | if return_attention:
57 | return x, attn
58 | else:
59 | return x
60 |
61 |
62 | class Attention_talking_head(nn.Module):
63 | # taken from https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
64 | # with slight modifications to add Talking Heads Attention (https://arxiv.org/pdf/2003.02436v1.pdf)
65 | def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.,
66 | rpe=True, z_size=7, x_size=14):
67 | super().__init__()
68 |
69 | self.num_heads = num_heads
70 |
71 | head_dim = dim // num_heads
72 |
73 | self.scale = qk_scale or head_dim ** -0.5
74 |
75 | self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
76 | self.attn_drop = nn.Dropout(attn_drop)
77 |
78 | self.proj = nn.Linear(dim, dim)
79 |
80 | self.proj_l = nn.Linear(num_heads, num_heads)
81 | self.proj_w = nn.Linear(num_heads, num_heads)
82 |
83 | self.proj_drop = nn.Dropout(proj_drop)
84 |
85 | self.rpe = rpe
86 | if self.rpe:
87 | relative_position_index = \
88 | generate_2d_concatenated_self_attention_relative_positional_encoding_index([z_size, z_size],
89 | [x_size, x_size])
90 | self.register_buffer("relative_position_index", relative_position_index)
91 | # define a parameter table of relative position bias
92 | self.relative_position_bias_table = nn.Parameter(torch.empty((num_heads,
93 | relative_position_index.max() + 1)))
94 | trunc_normal_(self.relative_position_bias_table, std=0.02)
95 |
96 | def forward(self, x, mask=None):
97 | B, N, C = x.shape
98 | qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
99 | q, k, v = qkv[0] * self.scale, qkv[1], qkv[2]
100 |
101 | attn = (q @ k.transpose(-2, -1))
102 |
103 | if self.rpe:
104 | relative_position_bias = self.relative_position_bias_table[:, self.relative_position_index].unsqueeze(0)
105 | attn += relative_position_bias
106 |
107 | if mask is not None:
108 | attn = attn.masked_fill(mask.unsqueeze(1).unsqueeze(2),
109 | float('-inf'),)
110 |
111 | attn = self.proj_l(attn.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)
112 |
113 | attn = attn.softmax(dim=-1)
114 |
115 | attn = self.proj_w(attn.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)
116 | attn = self.attn_drop(attn)
117 |
118 | x = (attn @ v).transpose(1, 2).reshape(B, N, C)
119 | x = self.proj(x)
120 | x = self.proj_drop(x)
121 | return x
--------------------------------------------------------------------------------
/lib/models/layers/frozen_bn.py:
--------------------------------------------------------------------------------
1 | import torch
2 |
3 |
4 | class FrozenBatchNorm2d(torch.nn.Module):
5 | """
6 | BatchNorm2d where the batch statistics and the affine parameters are fixed.
7 |
8 | Copy-paste from torchvision.misc.ops with added eps before rqsrt,
9 | without which any other models than torchvision.models.resnet[18,34,50,101]
10 | produce nans.
11 | """
12 |
13 | def __init__(self, n):
14 | super(FrozenBatchNorm2d, self).__init__()
15 | self.register_buffer("weight", torch.ones(n))
16 | self.register_buffer("bias", torch.zeros(n))
17 | self.register_buffer("running_mean", torch.zeros(n))
18 | self.register_buffer("running_var", torch.ones(n))
19 |
20 | def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
21 | missing_keys, unexpected_keys, error_msgs):
22 | num_batches_tracked_key = prefix + 'num_batches_tracked'
23 | if num_batches_tracked_key in state_dict:
24 | del state_dict[num_batches_tracked_key]
25 |
26 | super(FrozenBatchNorm2d, self)._load_from_state_dict(
27 | state_dict, prefix, local_metadata, strict,
28 | missing_keys, unexpected_keys, error_msgs)
29 |
30 | def forward(self, x):
31 | # move reshapes to the beginning
32 | # to make it fuser-friendly
33 | w = self.weight.reshape(1, -1, 1, 1)
34 | b = self.bias.reshape(1, -1, 1, 1)
35 | rv = self.running_var.reshape(1, -1, 1, 1)
36 | rm = self.running_mean.reshape(1, -1, 1, 1)
37 | eps = 1e-5
38 | scale = w * (rv + eps).rsqrt() # rsqrt(x): 1/sqrt(x), r: reciprocal
39 | bias = b - rm * scale
40 | return x * scale + bias
41 |
--------------------------------------------------------------------------------
/lib/models/layers/patch_embed.py:
--------------------------------------------------------------------------------
1 | import torch.nn as nn
2 | import torch.nn.functional as F
3 | from timm.models.layers import to_2tuple
4 | import torch
5 |
6 | class PatchEmbed(nn.Module):
7 | """ 2D Image to Patch Embedding
8 | """
9 |
10 | def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, norm_layer=None, flatten=True):
11 | super().__init__()
12 | img_size = to_2tuple(img_size) #(224,224)
13 | patch_size = to_2tuple(patch_size)
14 | self.img_size = img_size
15 | self.patch_size = patch_size
16 | self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
17 | self.num_patches = self.grid_size[0] * self.grid_size[1]
18 | self.flatten = flatten
19 |
20 | self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
21 | self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
22 |
23 | def forward(self, x):
24 | x = self.proj(x) #([32, 768, 16/8, 16/8])/
25 | if self.flatten:
26 | x = x.flatten(2).transpose(1, 2) # BCHW -> BNC
27 | x = self.norm(x)
28 | return x
29 |
--------------------------------------------------------------------------------
/lib/models/layers/rpe.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import torch.nn as nn
3 | from timm.models.layers import trunc_normal_
4 |
5 |
6 | def generate_2d_relative_positional_encoding_index(z_shape, x_shape):
7 | '''
8 | z_shape: (z_h, z_w)
9 | x_shape: (x_h, x_w)
10 | '''
11 | z_2d_index_h, z_2d_index_w = torch.meshgrid(torch.arange(z_shape[0]), torch.arange(z_shape[1]))
12 | x_2d_index_h, x_2d_index_w = torch.meshgrid(torch.arange(x_shape[0]), torch.arange(x_shape[1]))
13 |
14 | z_2d_index_h = z_2d_index_h.flatten(0)
15 | z_2d_index_w = z_2d_index_w.flatten(0)
16 | x_2d_index_h = x_2d_index_h.flatten(0)
17 | x_2d_index_w = x_2d_index_w.flatten(0)
18 |
19 | diff_h = z_2d_index_h[:, None] - x_2d_index_h[None, :]
20 | diff_w = z_2d_index_w[:, None] - x_2d_index_w[None, :]
21 |
22 | diff = torch.stack((diff_h, diff_w), dim=-1)
23 | _, indices = torch.unique(diff.view(-1, 2), return_inverse=True, dim=0)
24 | return indices.view(z_shape[0] * z_shape[1], x_shape[0] * x_shape[1])
25 |
26 |
27 | def generate_2d_concatenated_self_attention_relative_positional_encoding_index(z_shape, x_shape):
28 | '''
29 | z_shape: (z_h, z_w)
30 | x_shape: (x_h, x_w)
31 | '''
32 | z_2d_index_h, z_2d_index_w = torch.meshgrid(torch.arange(z_shape[0]), torch.arange(z_shape[1]))
33 | x_2d_index_h, x_2d_index_w = torch.meshgrid(torch.arange(x_shape[0]), torch.arange(x_shape[1]))
34 |
35 | z_2d_index_h = z_2d_index_h.flatten(0)
36 | z_2d_index_w = z_2d_index_w.flatten(0)
37 | x_2d_index_h = x_2d_index_h.flatten(0)
38 | x_2d_index_w = x_2d_index_w.flatten(0)
39 |
40 | concatenated_2d_index_h = torch.cat((z_2d_index_h, x_2d_index_h))
41 | concatenated_2d_index_w = torch.cat((z_2d_index_w, x_2d_index_w))
42 |
43 | diff_h = concatenated_2d_index_h[:, None] - concatenated_2d_index_h[None, :]
44 | diff_w = concatenated_2d_index_w[:, None] - concatenated_2d_index_w[None, :]
45 |
46 | z_len = z_shape[0] * z_shape[1]
47 | x_len = x_shape[0] * x_shape[1]
48 | a = torch.empty((z_len + x_len), dtype=torch.int64)
49 | a[:z_len] = 0
50 | a[z_len:] = 1
51 | b=a[:, None].repeat(1, z_len + x_len)
52 | c=a[None, :].repeat(z_len + x_len, 1)
53 |
54 | diff = torch.stack((diff_h, diff_w, b, c), dim=-1)
55 | _, indices = torch.unique(diff.view((z_len + x_len) * (z_len + x_len), 4), return_inverse=True, dim=0)
56 | return indices.view((z_len + x_len), (z_len + x_len))
57 |
58 |
59 | def generate_2d_concatenated_cross_attention_relative_positional_encoding_index(z_shape, x_shape):
60 | '''
61 | z_shape: (z_h, z_w)
62 | x_shape: (x_h, x_w)
63 | '''
64 | z_2d_index_h, z_2d_index_w = torch.meshgrid(torch.arange(z_shape[0]), torch.arange(z_shape[1]))
65 | x_2d_index_h, x_2d_index_w = torch.meshgrid(torch.arange(x_shape[0]), torch.arange(x_shape[1]))
66 |
67 | z_2d_index_h = z_2d_index_h.flatten(0)
68 | z_2d_index_w = z_2d_index_w.flatten(0)
69 | x_2d_index_h = x_2d_index_h.flatten(0)
70 | x_2d_index_w = x_2d_index_w.flatten(0)
71 |
72 | concatenated_2d_index_h = torch.cat((z_2d_index_h, x_2d_index_h))
73 | concatenated_2d_index_w = torch.cat((z_2d_index_w, x_2d_index_w))
74 |
75 | diff_h = x_2d_index_h[:, None] - concatenated_2d_index_h[None, :]
76 | diff_w = x_2d_index_w[:, None] - concatenated_2d_index_w[None, :]
77 |
78 | z_len = z_shape[0] * z_shape[1]
79 | x_len = x_shape[0] * x_shape[1]
80 |
81 | a = torch.empty(z_len + x_len, dtype=torch.int64)
82 | a[: z_len] = 0
83 | a[z_len:] = 1
84 | c = a[None, :].repeat(x_len, 1)
85 |
86 | diff = torch.stack((diff_h, diff_w, c), dim=-1)
87 | _, indices = torch.unique(diff.view(x_len * (z_len + x_len), 3), return_inverse=True, dim=0)
88 | return indices.view(x_len, (z_len + x_len))
89 |
90 |
91 | class RelativePosition2DEncoder(nn.Module):
92 | def __init__(self, num_heads, embed_size):
93 | super(RelativePosition2DEncoder, self).__init__()
94 | self.relative_position_bias_table = nn.Parameter(torch.empty((num_heads, embed_size)))
95 | trunc_normal_(self.relative_position_bias_table, std=0.02)
96 |
97 | def forward(self, attn_rpe_index):
98 | '''
99 | Args:
100 | attn_rpe_index (torch.Tensor): (*), any shape containing indices, max(attn_rpe_index) < embed_size
101 | Returns:
102 | torch.Tensor: (1, num_heads, *)
103 | '''
104 | return self.relative_position_bias_table[:, attn_rpe_index].unsqueeze(0)
105 |
--------------------------------------------------------------------------------
/lib/models/untrack/__init__.py:
--------------------------------------------------------------------------------
1 | from .ostrack import build_ostrack
2 | from .ostrack_prompt import build_untrack
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/attention.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/attention.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/base_backbone.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/base_backbone.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/ostrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/ostrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/ostrack_prompt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/ostrack_prompt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/vit.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/vit.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/vit_ce.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/vit_ce.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/vit_ce_prompt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/vit_ce_prompt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/__pycache__/vit_prompt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/models/untrack/__pycache__/vit_prompt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/models/untrack/test_gradient.py:
--------------------------------------------------------------------------------
1 | import math
2 | import logging
3 | import pdb
4 | from functools import partial
5 | from collections import OrderedDict
6 | from copy import deepcopy
7 |
8 | import matplotlib.pyplot as plt
9 | import torch
10 | import torch.nn as nn
11 | import torch.nn.functional as F
12 |
13 | from timm.models.layers import to_2tuple
14 |
15 | import functools
16 | from torch import nn, Tensor
17 | from info_nce import InfoNCE
18 |
19 | def gradient(depth_tmp):
20 | step = 7
21 |
22 | B, C, H, W = depth_tmp.size()
23 | pad = (step - 1) // 2
24 | depth_tmp = F.pad(depth_tmp, [pad, pad, pad, pad], mode='constant', value=0)
25 | patches = depth_tmp.unfold(dimension=2, size=step, step=1)
26 | patches = patches.unfold(dimension=3, size=step, step=1)
27 | max_depth, _ = patches.reshape(B, C, H, W, -1).max(dim=-1)
28 |
29 | # 求解max_depth四个方向梯度, 随后concat depth, 以缓解深度跳变对深度预测模块的影响
30 | step = float(step)
31 | shift_list = [[step / H, 0.0 / W], [-step / H, 0.0 / W], [0.0 / H, step / W], [0.0 / H, -step / W]]
32 | output_list = []
33 | for shift in shift_list:
34 | transform_matrix = torch.tensor([[1, 0, shift[0]], [0, 1, shift[1]]]).unsqueeze(0).repeat(B, 1, 1).cuda()
35 | grid = F.affine_grid(transform_matrix, max_depth.shape).float()
36 | output = F.grid_sample(max_depth, grid, mode='nearest') # 平移后图像
37 | output = max_depth - output
38 | output_mask = ((output == max_depth) == False)
39 | output = output * output_mask
40 | output_list.append(output)
41 | grad = torch.cat(output_list, dim=1)
42 | max_grad = torch.abs(grad).max(dim=1)[0].unsqueeze(1)
43 |
44 | return grad, max_grad
45 |
46 | if __name__ == "__main__":
47 | path = '/home/zwu/Tracking/data/depthtrack/train/ball02_indoor/color/00001464.jpg'
48 | im = plt.imread(path)
49 | rgb = torch.from_numpy(im).unsqueeze(0).permute(0,3,1,2).cuda()
50 | rgb = F.interpolate(rgb, (256,256)).float()
51 | grad = gradient(rgb)
52 | max_grad = torch.abs(grad).max(dim=1)[0].unsqueeze(1)
53 | a=1
--------------------------------------------------------------------------------
/lib/models/untrack/utils.py:
--------------------------------------------------------------------------------
1 | import math
2 |
3 | import torch
4 | import torch.nn.functional as F
5 |
6 |
7 | def combine_tokens(template_tokens, search_tokens, mode='direct', return_res=False):
8 | # [B, HW, C]
9 | len_t = template_tokens.shape[1]
10 | len_s = search_tokens.shape[1]
11 |
12 | if mode == 'direct':
13 | merged_feature = torch.cat((template_tokens, search_tokens), dim=1)
14 | elif mode == 'template_central':
15 | central_pivot = len_s // 2
16 | first_half = search_tokens[:, :central_pivot, :]
17 | second_half = search_tokens[:, central_pivot:, :]
18 | merged_feature = torch.cat((first_half, template_tokens, second_half), dim=1)
19 | elif mode == 'partition':
20 | feat_size_s = int(math.sqrt(len_s))
21 | feat_size_t = int(math.sqrt(len_t))
22 | window_size = math.ceil(feat_size_t / 2.)
23 | # pad feature maps to multiples of window size
24 | B, _, C = template_tokens.shape
25 | H = W = feat_size_t
26 | template_tokens = template_tokens.view(B, H, W, C)
27 | pad_l = pad_b = pad_r = 0
28 | # pad_r = (window_size - W % window_size) % window_size
29 | pad_t = (window_size - H % window_size) % window_size
30 | template_tokens = F.pad(template_tokens, (0, 0, pad_l, pad_r, pad_t, pad_b))
31 | _, Hp, Wp, _ = template_tokens.shape
32 | template_tokens = template_tokens.view(B, Hp // window_size, window_size, W, C)
33 | template_tokens = torch.cat([template_tokens[:, 0, ...], template_tokens[:, 1, ...]], dim=2)
34 | _, Hc, Wc, _ = template_tokens.shape
35 | template_tokens = template_tokens.view(B, -1, C)
36 | merged_feature = torch.cat([template_tokens, search_tokens], dim=1)
37 |
38 | # calculate new h and w, which may be useful for SwinT or others
39 | merged_h, merged_w = feat_size_s + Hc, feat_size_s
40 | if return_res:
41 | return merged_feature, merged_h, merged_w
42 |
43 | else:
44 | raise NotImplementedError
45 |
46 | return merged_feature
47 |
48 |
49 | def recover_tokens(merged_tokens, len_template_token, len_search_token, mode='direct'):
50 | if mode == 'direct':
51 | recovered_tokens = merged_tokens
52 | elif mode == 'template_central':
53 | central_pivot = len_search_token // 2
54 | len_remain = len_search_token - central_pivot
55 | len_half_and_t = central_pivot + len_template_token
56 |
57 | first_half = merged_tokens[:, :central_pivot, :]
58 | second_half = merged_tokens[:, -len_remain:, :]
59 | template_tokens = merged_tokens[:, central_pivot:len_half_and_t, :]
60 |
61 | recovered_tokens = torch.cat((template_tokens, first_half, second_half), dim=1)
62 | elif mode == 'partition':
63 | recovered_tokens = merged_tokens
64 | else:
65 | raise NotImplementedError
66 |
67 | return recovered_tokens
68 |
69 |
70 | def window_partition(x, window_size: int):
71 | """
72 | Args:
73 | x: (B, H, W, C)
74 | window_size (int): window size
75 |
76 | Returns:
77 | windows: (num_windows*B, window_size, window_size, C)
78 | """
79 | B, H, W, C = x.shape
80 | x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
81 | windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
82 | return windows
83 |
84 |
85 | def window_reverse(windows, window_size: int, H: int, W: int):
86 | """
87 | Args:
88 | windows: (num_windows*B, window_size, window_size, C)
89 | window_size (int): Window size
90 | H (int): Height of image
91 | W (int): Width of image
92 |
93 | Returns:
94 | x: (B, H, W, C)
95 | """
96 | B = int(windows.shape[0] / (H * W / window_size / window_size))
97 | x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
98 | x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
99 | return x
100 |
101 |
102 | '''
103 | add token transfer to feature
104 | '''
105 | def token2feature(tokens):
106 | B,L,D=tokens.shape
107 | H=W=int(L**0.5)
108 | x = tokens.permute(0, 2, 1).view(B, D, W, H).contiguous()
109 | return x
110 |
111 |
112 | '''
113 | feature2token
114 | '''
115 | def feature2token(x):
116 | B,C,W,H = x.shape
117 | L = W*H
118 | tokens = x.view(B, C, L).permute(0, 2, 1).contiguous()
119 | return tokens
--------------------------------------------------------------------------------
/lib/test/evaluation/__init__.py:
--------------------------------------------------------------------------------
1 | from .data import Sequence
2 | from .tracker import Tracker, trackerlist
3 | from .datasets import get_dataset
4 | from .environment import create_default_local_file_test
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/data.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/data.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/datasets.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/datasets.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/environment.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/environment.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/local.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/local.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/running.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/running.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/tracker.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/tracker.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/__pycache__/votdataset.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/evaluation/__pycache__/votdataset.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/evaluation/datasets.py:
--------------------------------------------------------------------------------
1 | from collections import namedtuple
2 | import importlib
3 | from lib.test.evaluation.data import SequenceList
4 |
5 | DatasetInfo = namedtuple('DatasetInfo', ['module', 'class_name', 'kwargs'])
6 |
7 | pt = "lib.test.evaluation.%sdataset" # Useful abbreviations to reduce the clutter
8 |
9 | dataset_dict = dict(
10 | otb=DatasetInfo(module=pt % "otb", class_name="OTBDataset", kwargs=dict()),
11 | nfs=DatasetInfo(module=pt % "nfs", class_name="NFSDataset", kwargs=dict()),
12 | uav=DatasetInfo(module=pt % "uav", class_name="UAVDataset", kwargs=dict()),
13 | tc128=DatasetInfo(module=pt % "tc128", class_name="TC128Dataset", kwargs=dict()),
14 | tc128ce=DatasetInfo(module=pt % "tc128ce", class_name="TC128CEDataset", kwargs=dict()),
15 | trackingnet=DatasetInfo(module=pt % "trackingnet", class_name="TrackingNetDataset", kwargs=dict()),
16 | got10k_test=DatasetInfo(module=pt % "got10k", class_name="GOT10KDataset", kwargs=dict(split='test')),
17 | got10k_val=DatasetInfo(module=pt % "got10k", class_name="GOT10KDataset", kwargs=dict(split='val')),
18 | got10k_ltrval=DatasetInfo(module=pt % "got10k", class_name="GOT10KDataset", kwargs=dict(split='ltrval')),
19 | lasot=DatasetInfo(module=pt % "lasot", class_name="LaSOTDataset", kwargs=dict()),
20 | lasot_lmdb=DatasetInfo(module=pt % "lasot_lmdb", class_name="LaSOTlmdbDataset", kwargs=dict()),
21 |
22 | vot18=DatasetInfo(module=pt % "vot", class_name="VOTDataset", kwargs=dict()),
23 | vot22=DatasetInfo(module=pt % "vot", class_name="VOTDataset", kwargs=dict(year=22)),
24 | itb=DatasetInfo(module=pt % "itb", class_name="ITBDataset", kwargs=dict()),
25 | tnl2k=DatasetInfo(module=pt % "tnl2k", class_name="TNL2kDataset", kwargs=dict()),
26 | lasot_extension_subset=DatasetInfo(module=pt % "lasotextensionsubset", class_name="LaSOTExtensionSubsetDataset",
27 | kwargs=dict()),
28 | vtuav_st=DatasetInfo(module=pt % "vtuav", class_name="VTUAVDataset", kwargs=dict(subset='st')),
29 | vtuav_lt=DatasetInfo(module=pt % "vtuav", class_name="VTUAVDataset", kwargs=dict(subset='lt')),
30 | lasher=DatasetInfo(module=pt % "lasher", class_name="LasHeRDataset", kwargs=dict()),
31 | depthtrack=DatasetInfo(module=pt % "depthtrack", class_name="DepthTrackDataset", kwargs=dict()),
32 |
33 | )
34 |
35 |
36 | def load_dataset(name: str):
37 | """ Import and load a single dataset."""
38 | name = name.lower()
39 | dset_info = dataset_dict.get(name)
40 | if dset_info is None:
41 | raise ValueError('Unknown dataset \'%s\'' % name)
42 |
43 | m = importlib.import_module(dset_info.module)
44 | dataset = getattr(m, dset_info.class_name)(**dset_info.kwargs) # Call the constructor
45 | return dataset.get_sequence_list()
46 |
47 |
48 | def get_dataset(*args):
49 | """ Get a single or set of datasets."""
50 | dset = SequenceList()
51 | for name in args:
52 | dset.extend(load_dataset(name))
53 | return dset
--------------------------------------------------------------------------------
/lib/test/evaluation/environment.py:
--------------------------------------------------------------------------------
1 | import importlib
2 | import os
3 |
4 |
5 | class EnvSettings:
6 | def __init__(self):
7 | test_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
8 |
9 | self.results_path = '{}/tracking_results/'.format(test_path)
10 | self.segmentation_path = '{}/segmentation_results/'.format(test_path)
11 | self.network_path = '{}/networks/'.format(test_path)
12 | self.result_plot_path = '{}/result_plots/'.format(test_path)
13 | self.otb_path = ''
14 | self.nfs_path = ''
15 | self.uav_path = ''
16 | self.tpl_path = ''
17 | self.vot_path = ''
18 | self.got10k_path = ''
19 | self.lasot_path = ''
20 | self.trackingnet_path = ''
21 | self.davis_dir = ''
22 | self.youtubevos_dir = ''
23 |
24 | self.got_packed_results_path = ''
25 | self.got_reports_path = ''
26 | self.tn_packed_results_path = ''
27 |
28 |
29 | def create_default_local_file():
30 | comment = {'results_path': 'Where to store tracking results',
31 | 'network_path': 'Where tracking networks are stored.'}
32 |
33 | path = os.path.join(os.path.dirname(__file__), 'local.py')
34 | with open(path, 'w') as f:
35 | settings = EnvSettings()
36 |
37 | f.write('from test.evaluation.environment import EnvSettings\n\n')
38 | f.write('def local_env_settings():\n')
39 | f.write(' settings = EnvSettings()\n\n')
40 | f.write(' # Set your local paths here.\n\n')
41 |
42 | for attr in dir(settings):
43 | comment_str = None
44 | if attr in comment:
45 | comment_str = comment[attr]
46 | attr_val = getattr(settings, attr)
47 | if not attr.startswith('__') and not callable(attr_val):
48 | if comment_str is None:
49 | f.write(' settings.{} = \'{}\'\n'.format(attr, attr_val))
50 | else:
51 | f.write(' settings.{} = \'{}\' # {}\n'.format(attr, attr_val, comment_str))
52 | f.write('\n return settings\n\n')
53 |
54 |
55 | class EnvSettings_ITP:
56 | def __init__(self, workspace_dir, data_dir, save_dir):
57 | self.prj_dir = workspace_dir
58 | self.save_dir = save_dir
59 | self.results_path = os.path.join(save_dir, 'test/tracking_results')
60 | self.segmentation_path = os.path.join(save_dir, 'test/segmentation_results')
61 | self.network_path = os.path.join(save_dir, 'test/networks')
62 | self.result_plot_path = os.path.join(save_dir, 'test/result_plots')
63 | self.otb_path = os.path.join(data_dir, 'otb')
64 | self.nfs_path = os.path.join(data_dir, 'nfs')
65 | self.uav_path = os.path.join(data_dir, 'uav')
66 | self.tc128_path = os.path.join(data_dir, 'TC128')
67 | self.tpl_path = ''
68 | self.vot_path = os.path.join(data_dir, 'VOT2019')
69 | self.got10k_path = os.path.join(data_dir, 'got10k')
70 | self.got10k_lmdb_path = os.path.join(data_dir, 'got10k_lmdb')
71 | self.lasot_path = os.path.join(data_dir, 'lasot')
72 | self.lasot_lmdb_path = os.path.join(data_dir, 'lasot_lmdb')
73 | self.trackingnet_path = os.path.join(data_dir, 'trackingnet')
74 | self.vot18_path = os.path.join(data_dir, 'vot2018')
75 | self.vot22_path = os.path.join(data_dir, 'vot2022')
76 | self.itb_path = os.path.join(data_dir, 'itb')
77 | self.tnl2k_path = os.path.join(data_dir, 'tnl2k')
78 | self.lasot_extension_subset_path_path = os.path.join(data_dir, 'lasot_extension_subset')
79 | self.davis_dir = ''
80 | self.youtubevos_dir = ''
81 |
82 | self.got_packed_results_path = ''
83 | self.got_reports_path = ''
84 | self.tn_packed_results_path = ''
85 |
86 |
87 | def create_default_local_file_test(workspace_dir, data_dir, save_dir):
88 | comment = {'results_path': 'Where to store tracking results',
89 | 'network_path': 'Where tracking networks are stored.'}
90 |
91 | path = os.path.join(os.path.dirname(__file__), 'local.py')
92 | with open(path, 'w') as f:
93 | settings = EnvSettings_ITP(workspace_dir, data_dir, save_dir)
94 |
95 | f.write('from lib.test.evaluation.environment import EnvSettings\n\n')
96 | f.write('def local_env_settings():\n')
97 | f.write(' settings = EnvSettings()\n\n')
98 | f.write(' # Set your local paths here.\n\n')
99 |
100 | for attr in dir(settings):
101 | comment_str = None
102 | if attr in comment:
103 | comment_str = comment[attr]
104 | attr_val = getattr(settings, attr)
105 | if not attr.startswith('__') and not callable(attr_val):
106 | if comment_str is None:
107 | f.write(' settings.{} = \'{}\'\n'.format(attr, attr_val))
108 | else:
109 | f.write(' settings.{} = \'{}\' # {}\n'.format(attr, attr_val, comment_str))
110 | f.write('\n return settings\n\n')
111 |
112 |
113 | def env_settings():
114 | env_module_name = 'lib.test.evaluation.local'
115 | try:
116 | env_module = importlib.import_module(env_module_name)
117 | return env_module.local_env_settings()
118 | except:
119 | env_file = os.path.join(os.path.dirname(__file__), 'local.py')
120 |
121 | # Create a default file
122 | create_default_local_file()
123 | raise RuntimeError('YOU HAVE NOT SETUP YOUR local.py!!!\n Go to "{}" and set all the paths you need. '
124 | 'Then try to run again.'.format(env_file))
--------------------------------------------------------------------------------
/lib/test/evaluation/local.py:
--------------------------------------------------------------------------------
1 | from lib.test.evaluation.environment import EnvSettings
2 |
3 | def local_env_settings():
4 | settings = EnvSettings()
5 |
6 | # Set your local paths here.
7 |
8 | settings.davis_dir = ''
9 | settings.got10k_lmdb_path = '/home/zwu/Tracking/data/got10k_lmdb'
10 | settings.got10k_path = '/home/zwu/Tracking/data/got10k'
11 | settings.got_packed_results_path = ''
12 | settings.got_reports_path = ''
13 | settings.itb_path = '/home/zwu/Tracking/data/itb'
14 | settings.lasot_extension_subset_path_path = '/home/zwu/Tracking/data/lasot_extension_subset'
15 | settings.lasot_lmdb_path = '/home/zwu/Tracking/data/lasot_lmdb'
16 | settings.lasot_path = '/home/zwu/Tracking/data/lasot'
17 | settings.network_path = '/home/zwu/Tracking/output/test/networks' # Where tracking networks are stored.
18 | settings.nfs_path = '/home/zwu/Tracking/data/nfs'
19 | settings.otb_path = '/home/zwu/Tracking/data/otb'
20 | settings.prj_dir = '/home/zwu/Tracking'
21 | settings.result_plot_path = '/home/zwu/Tracking/output/test/result_plots'
22 | settings.results_path = '/home/zwu/Tracking/output/test/tracking_results' # Where to store tracking results
23 | settings.save_dir = '/home/zwu/Tracking/output'
24 | settings.segmentation_path = '/home/zwu/Tracking/output/test/segmentation_results'
25 | settings.tc128_path = '/home/zwu/Tracking/data/TC128'
26 | settings.tn_packed_results_path = ''
27 | settings.tnl2k_path = '/home/zwu/Tracking/data/tnl2k'
28 | settings.tpl_path = ''
29 | settings.trackingnet_path = '/home/zwu/Tracking/data/trackingnet'
30 | settings.uav_path = '/home/zwu/Tracking/data/uav'
31 | settings.vot18_path = '/home/zwu/Tracking/data/vot2018'
32 | settings.vot22_path = '/home/zwu/Tracking/data/vot2022'
33 | settings.vot_path = '/home/zwu/Tracking/data/VOT2019'
34 | settings.youtubevos_dir = ''
35 |
36 | return settings
37 |
38 |
--------------------------------------------------------------------------------
/lib/test/parameter/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/parameter/__init__.py
--------------------------------------------------------------------------------
/lib/test/parameter/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/parameter/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/parameter/__pycache__/untrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/parameter/__pycache__/untrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/parameter/__pycache__/vipt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/parameter/__pycache__/vipt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/parameter/untrack.py:
--------------------------------------------------------------------------------
1 | from lib.test.utils import TrackerParams
2 | import os
3 | from lib.test.evaluation.environment import env_settings
4 | from lib.config.untrack.config import cfg, update_config_from_file
5 |
6 |
7 | def parameters(yaml_name: str, epoch=None):
8 | params = TrackerParams()
9 | prj_dir = env_settings().prj_dir
10 | save_dir = env_settings().save_dir
11 | # update default config from yaml file
12 | yaml_file = os.path.join(prj_dir, 'experiments/untrack/%s.yaml' % yaml_name)
13 | update_config_from_file(yaml_file)
14 | params.cfg = cfg
15 | print("test config: ", cfg)
16 |
17 | # template and search region
18 | params.template_factor = cfg.TEST.TEMPLATE_FACTOR
19 | params.template_size = cfg.TEST.TEMPLATE_SIZE
20 | params.search_factor = cfg.TEST.SEARCH_FACTOR
21 | params.search_size = cfg.TEST.SEARCH_SIZE
22 |
23 | # Network checkpoint path
24 | params.checkpoint = os.path.join(prj_dir, "./models/UnTrack.pth.tar")
25 |
26 | # whether to save boxes from all queries
27 | params.save_all_boxes = False
28 |
29 | return params
30 |
--------------------------------------------------------------------------------
/lib/test/tracker/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__init__.py
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/basetracker.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/basetracker.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/data_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/data_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/ostrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/ostrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/untrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/untrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/vipt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/vipt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/__pycache__/vis_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/tracker/__pycache__/vis_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/tracker/basetracker.py:
--------------------------------------------------------------------------------
1 | import time
2 |
3 | import torch
4 | from _collections import OrderedDict
5 |
6 | from lib.train.data.processing_utils import transform_image_to_crop
7 | from lib.vis.visdom_cus import Visdom
8 |
9 |
10 | class BaseTracker:
11 | """Base class for all trackers."""
12 |
13 | def __init__(self, params):
14 | self.params = params
15 | self.visdom = None
16 |
17 | def predicts_segmentation_mask(self):
18 | return False
19 |
20 | def initialize(self, image, info: dict) -> dict:
21 | """Overload this function in your tracker. This should initialize the model."""
22 | raise NotImplementedError
23 |
24 | def track(self, image, info: dict = None) -> dict:
25 | """Overload this function in your tracker. This should track in the frame and update the model."""
26 | raise NotImplementedError
27 |
28 | def visdom_draw_tracking(self, image, box, segmentation=None):
29 | if isinstance(box, OrderedDict):
30 | box = [v for k, v in box.items()]
31 | else:
32 | box = (box,)
33 | if segmentation is None:
34 | self.visdom.register((image, *box), 'Tracking', 1, 'Tracking')
35 | else:
36 | self.visdom.register((image, *box, segmentation), 'Tracking', 1, 'Tracking')
37 |
38 | def transform_bbox_to_crop(self, box_in, resize_factor, device, box_extract=None, crop_type='template'):
39 | # box_in: list [x1, y1, w, h], not normalized
40 | # box_extract: same as box_in
41 | # out bbox: Torch.tensor [1, 1, 4], x1y1wh, normalized
42 | if crop_type == 'template':
43 | crop_sz = torch.Tensor([self.params.template_size, self.params.template_size])
44 | elif crop_type == 'search':
45 | crop_sz = torch.Tensor([self.params.search_size, self.params.search_size])
46 | else:
47 | raise NotImplementedError
48 |
49 | box_in = torch.tensor(box_in)
50 | if box_extract is None:
51 | box_extract = box_in
52 | else:
53 | box_extract = torch.tensor(box_extract)
54 | template_bbox = transform_image_to_crop(box_in, box_extract, resize_factor, crop_sz, normalize=True)
55 | template_bbox = template_bbox.view(1, 1, 4).to(device)
56 |
57 | return template_bbox
58 |
59 | def _init_visdom(self, visdom_info, debug):
60 | visdom_info = {} if visdom_info is None else visdom_info
61 | self.pause_mode = False
62 | self.step = False
63 | self.next_seq = False
64 | if debug > 0 and visdom_info.get('use_visdom', True):
65 | try:
66 | self.visdom = Visdom(debug, {'handler': self._visdom_ui_handler, 'win_id': 'Tracking'},
67 | visdom_info=visdom_info)
68 | except:
69 | time.sleep(0.5)
70 | print('!!! WARNING: Visdom could not start, so using matplotlib visualization instead !!!\n'
71 | '!!! Start Visdom in a separate terminal window by typing \'visdom\' !!!')
72 |
73 | def _visdom_ui_handler(self, data):
74 | if data['event_type'] == 'KeyPress':
75 | if data['key'] == ' ':
76 | self.pause_mode = not self.pause_mode
77 |
78 | elif data['key'] == 'ArrowRight' and self.pause_mode:
79 | self.step = True
80 |
81 | elif data['key'] == 'n':
82 | self.next_seq = True
83 |
--------------------------------------------------------------------------------
/lib/test/tracker/data_utils.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import numpy as np
3 |
4 | class Preprocessor(object):
5 | def __init__(self):
6 | self.mean = torch.tensor([0.485, 0.456, 0.406]).view((1, 3, 1, 1)).cuda()
7 | self.std = torch.tensor([0.229, 0.224, 0.225]).view((1, 3, 1, 1)).cuda()
8 |
9 | def process(self, img_arr: np.ndarray):
10 | # Deal with the image patch
11 | img_tensor = torch.tensor(img_arr).cuda().float().permute((2,0,1)).unsqueeze(dim=0)
12 | img_tensor_norm = ((img_tensor / 255.0) - self.mean) / self.std # (1,3,H,W)
13 | return img_tensor_norm
14 |
15 | class PreprocessorMM(object):
16 | def __init__(self):
17 | self.mean = torch.tensor([0.485, 0.456, 0.406, 0.485, 0.456, 0.406]).view((1, 6, 1, 1)).cuda()
18 | self.std = torch.tensor([0.229, 0.224, 0.225, 0.229, 0.224, 0.225]).view((1, 6, 1, 1)).cuda()
19 |
20 |
21 |
22 | #self.mean = torch.tensor([0.485, 0.456, 0.406, 0.485, 0.456, 0.406, 0.485, 0.456, 0.406]).view((1, 9, 1, 1)).cuda()
23 | #self.std = torch.tensor([0.229, 0.224, 0.225, 0.229, 0.224, 0.225, 0.229, 0.224, 0.225]).view((1, 9, 1, 1)).cuda()
24 |
25 |
26 | def process(self, img_arr: np.ndarray):
27 | # Deal with the image patch
28 |
29 | img_tensor = torch.tensor(img_arr).cuda().float().permute((2,0,1)).unsqueeze(dim=0)
30 | temp = img_tensor[:, :-1, ...]
31 | sem = img_tensor[:, -1:, ...]
32 | temp_norm = ((temp / 255.0) - self.mean) / self.std # (1,6,H,W)
33 | img_tensor_norm = torch.cat((temp_norm, sem), dim=1)
34 | #img_tensor_norm = ((img_tensor / 255.0) - self.mean) / self.std # (1,6,H,W)
35 |
36 | return img_tensor_norm
37 |
38 |
39 | class PreprocessorX(object):
40 | def __init__(self):
41 | self.mean = torch.tensor([0.485, 0.456, 0.406]).view((1, 3, 1, 1)).cuda()
42 | self.std = torch.tensor([0.229, 0.224, 0.225]).view((1, 3, 1, 1)).cuda()
43 |
44 | def process(self, img_arr: np.ndarray, amask_arr: np.ndarray):
45 | # Deal with the image patch
46 | img_tensor = torch.tensor(img_arr).cuda().float().permute((2,0,1)).unsqueeze(dim=0)
47 | img_tensor_norm = ((img_tensor / 255.0) - self.mean) / self.std # (1,3,H,W)
48 | # Deal with the attention mask
49 | amask_tensor = torch.from_numpy(amask_arr).to(torch.bool).cuda().unsqueeze(dim=0) # (1,H,W)
50 | return img_tensor_norm, amask_tensor
51 |
52 |
53 | class PreprocessorX_onnx(object):
54 | def __init__(self):
55 | self.mean = np.array([0.485, 0.456, 0.406]).reshape((1, 3, 1, 1))
56 | self.std = np.array([0.229, 0.224, 0.225]).reshape((1, 3, 1, 1))
57 |
58 | def process(self, img_arr: np.ndarray, amask_arr: np.ndarray):
59 | """img_arr: (H,W,3), amask_arr: (H,W)"""
60 | # Deal with the image patch
61 | img_arr_4d = img_arr[np.newaxis, :, :, :].transpose(0, 3, 1, 2)
62 | img_arr_4d = (img_arr_4d / 255.0 - self.mean) / self.std # (1, 3, H, W)
63 | # Deal with the attention mask
64 | amask_arr_3d = amask_arr[np.newaxis, :, :] # (1,H,W)
65 | return img_arr_4d.astype(np.float32), amask_arr_3d.astype(np.bool)
66 |
--------------------------------------------------------------------------------
/lib/test/tracker/vis_utils.py:
--------------------------------------------------------------------------------
1 | import numpy as np
2 |
3 |
4 | ############## used for visulize eliminated tokens #################
5 | def get_keep_indices(decisions):
6 | keep_indices = []
7 | for i in range(3):
8 | if i == 0:
9 | keep_indices.append(decisions[i])
10 | else:
11 | keep_indices.append(keep_indices[-1][decisions[i]])
12 | return keep_indices
13 |
14 |
15 | def gen_masked_tokens(tokens, indices, alpha=0.2):
16 | # indices = [i for i in range(196) if i not in indices]
17 | indices = indices[0].astype(int)
18 | tokens = tokens.copy()
19 | tokens[indices] = alpha * tokens[indices] + (1 - alpha) * 255
20 | return tokens
21 |
22 |
23 | def recover_image(tokens, H, W, Hp, Wp, patch_size):
24 | # image: (C, 196, 16, 16)
25 | image = tokens.reshape(Hp, Wp, patch_size, patch_size, 3).swapaxes(1, 2).reshape(H, W, 3)
26 | return image
27 |
28 |
29 | def pad_img(img):
30 | height, width, channels = img.shape
31 | im_bg = np.ones((height, width + 8, channels)) * 255
32 | im_bg[0:height, 0:width, :] = img
33 | return im_bg
34 |
35 |
36 | def gen_visualization(image, mask_indices, patch_size=16):
37 | # image [224, 224, 3]
38 | # mask_indices, list of masked token indices
39 |
40 | # mask mask_indices need to cat
41 | # mask_indices = mask_indices[::-1]
42 | num_stages = len(mask_indices)
43 | for i in range(1, num_stages):
44 | mask_indices[i] = np.concatenate([mask_indices[i-1], mask_indices[i]], axis=1)
45 |
46 | # keep_indices = get_keep_indices(decisions)
47 | image = np.asarray(image)
48 | H, W, C = image.shape
49 | Hp, Wp = H // patch_size, W // patch_size
50 | image_tokens = image.reshape(Hp, patch_size, Wp, patch_size, 3).swapaxes(1, 2).reshape(Hp * Wp, patch_size, patch_size, 3)
51 |
52 | stages = [
53 | recover_image(gen_masked_tokens(image_tokens, mask_indices[i]), H, W, Hp, Wp, patch_size)
54 | for i in range(num_stages)
55 | ]
56 | imgs = [image] + stages
57 | imgs = [pad_img(img) for img in imgs]
58 | viz = np.concatenate(imgs, axis=1)
59 | return viz
60 |
--------------------------------------------------------------------------------
/lib/test/utils/__init__.py:
--------------------------------------------------------------------------------
1 | from .params import TrackerParams, FeatureParams, Choice
--------------------------------------------------------------------------------
/lib/test/utils/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/utils/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/utils/__pycache__/hann.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/utils/__pycache__/hann.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/utils/__pycache__/params.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/utils/__pycache__/params.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/utils/_init_paths.py:
--------------------------------------------------------------------------------
1 | from __future__ import absolute_import
2 | from __future__ import division
3 | from __future__ import print_function
4 |
5 | import os.path as osp
6 | import sys
7 |
8 |
9 | def add_path(path):
10 | if path not in sys.path:
11 | sys.path.insert(0, path)
12 |
13 |
14 | this_dir = osp.dirname(__file__)
15 |
16 | prj_path = osp.join(this_dir, '..', '..', '..')
17 | add_path(prj_path)
18 |
--------------------------------------------------------------------------------
/lib/test/utils/hann.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import math
3 | import torch.nn.functional as F
4 |
5 |
6 | def hann1d(sz: int, centered = True) -> torch.Tensor:
7 | """1D cosine window."""
8 | if centered:
9 | return 0.5 * (1 - torch.cos((2 * math.pi / (sz + 1)) * torch.arange(1, sz + 1).float()))
10 | w = 0.5 * (1 + torch.cos((2 * math.pi / (sz + 2)) * torch.arange(0, sz//2 + 1).float()))
11 | return torch.cat([w, w[1:sz-sz//2].flip((0,))])
12 |
13 |
14 | def hann2d(sz: torch.Tensor, centered = True) -> torch.Tensor:
15 | """2D cosine window."""
16 | return hann1d(sz[0].item(), centered).reshape(1, 1, -1, 1) * hann1d(sz[1].item(), centered).reshape(1, 1, 1, -1)
17 |
18 |
19 | def hann2d_bias(sz: torch.Tensor, ctr_point: torch.Tensor, centered = True) -> torch.Tensor:
20 | """2D cosine window."""
21 | distance = torch.stack([ctr_point, sz-ctr_point], dim=0)
22 | max_distance, _ = distance.max(dim=0)
23 |
24 | hann1d_x = hann1d(max_distance[0].item() * 2, centered)
25 | hann1d_x = hann1d_x[max_distance[0] - distance[0, 0]: max_distance[0] + distance[1, 0]]
26 | hann1d_y = hann1d(max_distance[1].item() * 2, centered)
27 | hann1d_y = hann1d_y[max_distance[1] - distance[0, 1]: max_distance[1] + distance[1, 1]]
28 |
29 | return hann1d_y.reshape(1, 1, -1, 1) * hann1d_x.reshape(1, 1, 1, -1)
30 |
31 |
32 |
33 | def hann2d_clipped(sz: torch.Tensor, effective_sz: torch.Tensor, centered = True) -> torch.Tensor:
34 | """1D clipped cosine window."""
35 |
36 | # Ensure that the difference is even
37 | effective_sz += (effective_sz - sz) % 2
38 | effective_window = hann1d(effective_sz[0].item(), True).reshape(1, 1, -1, 1) * hann1d(effective_sz[1].item(), True).reshape(1, 1, 1, -1)
39 |
40 | pad = (sz - effective_sz) // 2
41 |
42 | window = F.pad(effective_window, (pad[1].item(), pad[1].item(), pad[0].item(), pad[0].item()), 'replicate')
43 |
44 | if centered:
45 | return window
46 | else:
47 | mid = (sz / 2).int()
48 | window_shift_lr = torch.cat((window[:, :, :, mid[1]:], window[:, :, :, :mid[1]]), 3)
49 | return torch.cat((window_shift_lr[:, :, mid[0]:, :], window_shift_lr[:, :, :mid[0], :]), 2)
50 |
51 |
52 | def gauss_fourier(sz: int, sigma: float, half: bool = False) -> torch.Tensor:
53 | if half:
54 | k = torch.arange(0, int(sz/2+1))
55 | else:
56 | k = torch.arange(-int((sz-1)/2), int(sz/2+1))
57 | return (math.sqrt(2*math.pi) * sigma / sz) * torch.exp(-2 * (math.pi * sigma * k.float() / sz)**2)
58 |
59 |
60 | def gauss_spatial(sz, sigma, center=0, end_pad=0):
61 | k = torch.arange(-(sz-1)/2, (sz+1)/2+end_pad)
62 | return torch.exp(-1.0/(2*sigma**2) * (k - center)**2)
63 |
64 |
65 | def label_function(sz: torch.Tensor, sigma: torch.Tensor):
66 | return gauss_fourier(sz[0].item(), sigma[0].item()).reshape(1, 1, -1, 1) * gauss_fourier(sz[1].item(), sigma[1].item(), True).reshape(1, 1, 1, -1)
67 |
68 | def label_function_spatial(sz: torch.Tensor, sigma: torch.Tensor, center: torch.Tensor = torch.zeros(2), end_pad: torch.Tensor = torch.zeros(2)):
69 | """The origin is in the middle of the image."""
70 | return gauss_spatial(sz[0].item(), sigma[0].item(), center[0], end_pad[0].item()).reshape(1, 1, -1, 1) * \
71 | gauss_spatial(sz[1].item(), sigma[1].item(), center[1], end_pad[1].item()).reshape(1, 1, 1, -1)
72 |
73 |
74 | def cubic_spline_fourier(f, a):
75 | """The continuous Fourier transform of a cubic spline kernel."""
76 |
77 | bf = (6*(1 - torch.cos(2 * math.pi * f)) + 3*a*(1 - torch.cos(4 * math.pi * f))
78 | - (6 + 8*a)*math.pi*f*torch.sin(2 * math.pi * f) - 2*a*math.pi*f*torch.sin(4 * math.pi * f)) \
79 | / (4 * math.pi**4 * f**4)
80 |
81 | bf[f == 0] = 1
82 |
83 | return bf
84 |
85 | def max2d(a: torch.Tensor) -> (torch.Tensor, torch.Tensor):
86 | """Computes maximum and argmax in the last two dimensions."""
87 |
88 | max_val_row, argmax_row = torch.max(a, dim=-2)
89 | max_val, argmax_col = torch.max(max_val_row, dim=-1)
90 | argmax_row = argmax_row.view(argmax_col.numel(),-1)[torch.arange(argmax_col.numel()), argmax_col.view(-1)]
91 | argmax_row = argmax_row.reshape(argmax_col.shape)
92 | argmax = torch.cat((argmax_row.unsqueeze(-1), argmax_col.unsqueeze(-1)), -1)
93 | return max_val, argmax
94 |
--------------------------------------------------------------------------------
/lib/test/utils/load_text.py:
--------------------------------------------------------------------------------
1 | import numpy as np
2 | import pandas as pd
3 |
4 |
5 | def load_text_numpy(path, delimiter, dtype):
6 | if isinstance(delimiter, (tuple, list)):
7 | for d in delimiter:
8 | try:
9 | ground_truth_rect = np.loadtxt(path, delimiter=d, dtype=dtype)
10 | return ground_truth_rect
11 | except:
12 | pass
13 |
14 | raise Exception('Could not read file {}'.format(path))
15 | else:
16 | ground_truth_rect = np.loadtxt(path, delimiter=delimiter, dtype=dtype)
17 | return ground_truth_rect
18 |
19 |
20 | def load_text_pandas(path, delimiter, dtype):
21 | if isinstance(delimiter, (tuple, list)):
22 | for d in delimiter:
23 | try:
24 | ground_truth_rect = pd.read_csv(path, delimiter=d, header=None, dtype=dtype, na_filter=False,
25 | low_memory=False).values
26 | return ground_truth_rect
27 | except Exception as e:
28 | pass
29 |
30 | raise Exception('Could not read file {}'.format(path))
31 | else:
32 | ground_truth_rect = pd.read_csv(path, delimiter=delimiter, header=None, dtype=dtype, na_filter=False,
33 | low_memory=False).values
34 | return ground_truth_rect
35 |
36 |
37 | def load_text(path, delimiter=' ', dtype=np.float32, backend='numpy'):
38 | if backend == 'numpy':
39 | return load_text_numpy(path, delimiter, dtype)
40 | elif backend == 'pandas':
41 | return load_text_pandas(path, delimiter, dtype)
42 |
43 |
44 | def load_str(path):
45 | with open(path, "r") as f:
46 | text_str = f.readline().strip().lower()
47 | return text_str
48 |
--------------------------------------------------------------------------------
/lib/test/utils/params.py:
--------------------------------------------------------------------------------
1 | from lib.utils import TensorList
2 | import random
3 |
4 |
5 | class TrackerParams:
6 | """Class for tracker parameters."""
7 | def set_default_values(self, default_vals: dict):
8 | for name, val in default_vals.items():
9 | if not hasattr(self, name):
10 | setattr(self, name, val)
11 |
12 | def get(self, name: str, *default):
13 | """Get a parameter value with the given name. If it does not exists, it return the default value given as a
14 | second argument or returns an error if no default value is given."""
15 | if len(default) > 1:
16 | raise ValueError('Can only give one default value.')
17 |
18 | if not default:
19 | return getattr(self, name)
20 |
21 | return getattr(self, name, default[0])
22 |
23 | def has(self, name: str):
24 | """Check if there exist a parameter with the given name."""
25 | return hasattr(self, name)
26 |
27 |
28 | class FeatureParams:
29 | """Class for feature specific parameters"""
30 | def __init__(self, *args, **kwargs):
31 | if len(args) > 0:
32 | raise ValueError
33 |
34 | for name, val in kwargs.items():
35 | if isinstance(val, list):
36 | setattr(self, name, TensorList(val))
37 | else:
38 | setattr(self, name, val)
39 |
40 |
41 | def Choice(*args):
42 | """Can be used to sample random parameter values."""
43 | return random.choice(args)
44 |
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/untrack_baseline.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/untrack_baseline.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/untrack_class.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/untrack_class.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/vipt_baseline.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/vipt_baseline.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/vipt_class.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/vipt_class.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/vot.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/vot.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/__pycache__/vot22_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/test/vot/__pycache__/vot22_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/test/vot/untrack_baseline.py:
--------------------------------------------------------------------------------
1 | import os
2 | import sys
3 | print('************************************')
4 | env_path = os.path.join(os.path.dirname(__file__), '../../..')
5 | print('*********************************', env_path)
6 | if env_path not in sys.path:
7 | sys.path.append(env_path)
8 |
9 | from lib.test.vot.untrack_class import run_vot_exp
10 | os.environ['CUDA_VISIBLE_DEVICES'] = '0'
11 |
12 |
13 | run_vot_exp('untrack', 'deep_rgbd', vis=False, out_conf=True, channel_type='rgbd')
14 |
--------------------------------------------------------------------------------
/lib/test/vot/untrack_class.py:
--------------------------------------------------------------------------------
1 | from __future__ import absolute_import
2 | from __future__ import division
3 | from __future__ import print_function
4 | from __future__ import unicode_literals
5 |
6 | import pdb
7 | import cv2
8 | import torch
9 | # import vot
10 | import sys
11 | import time
12 | import os
13 | from lib.test.evaluation import Tracker
14 | import lib.test.vot.vot as vot
15 | from lib.test.vot.vot22_utils import *
16 | from lib.train.dataset.depth_utils import get_rgbd_frame
17 |
18 |
19 | class untrack(object):
20 | def __init__(self, tracker_name='', para_name=''):
21 | # create tracker
22 | tracker_info = Tracker(tracker_name, para_name, "vot22", None)
23 | params = tracker_info.get_parameters()
24 | params.visualization = False
25 | params.debug = False
26 | self.tracker = tracker_info.create_tracker(params)
27 |
28 | def write(self, str):
29 | txt_path = ""
30 | file = open(txt_path, 'a')
31 | file.write(str)
32 |
33 | def initialize(self, img_rgb, selection):
34 | # init on the 1st frame
35 | # region = rect_from_mask(mask)
36 | x, y, w, h = selection
37 | bbox = [x,y,w,h]
38 | self.H, self.W, _ = img_rgb.shape
39 | init_info = {'init_bbox': bbox}
40 | _ = self.tracker.initialize(img_rgb, init_info)
41 |
42 | def track(self, img_rgb):
43 | # track
44 | outputs = self.tracker.track(img_rgb)
45 | pred_bbox = outputs['target_bbox']
46 | max_score = outputs['best_score'] #.max().cpu().numpy()
47 | return pred_bbox, max_score
48 |
49 |
50 | def run_vot_exp(tracker_name, para_name, vis=False, out_conf=False, channel_type='color'):
51 |
52 | torch.set_num_threads(1)
53 | save_root = os.path.join('', para_name)
54 | if vis and (not os.path.exists(save_root)):
55 | os.mkdir(save_root)
56 |
57 |
58 | print(tracker_name)
59 | print("######")
60 | print(para_name)
61 | tracker = untrack(tracker_name=tracker_name, para_name=para_name)
62 | print('No prob after tracker init')
63 |
64 | if channel_type=='rgb':
65 | channel_type=None
66 | handle = vot.VOT("rectangle", channels=channel_type)
67 |
68 | selection = handle.region()
69 | imagefile = handle.frame()
70 |
71 | if not imagefile:
72 | sys.exit(0)
73 | if vis:
74 | '''for vis'''
75 | seq_name = imagefile.split('/')[-3]
76 | save_v_dir = os.path.join(save_root,seq_name)
77 | if not os.path.exists(save_v_dir):
78 | os.mkdir(save_v_dir)
79 | cur_time = int(time.time() % 10000)
80 | save_dir = os.path.join(save_v_dir, str(cur_time))
81 | if not os.path.exists(save_dir):
82 | os.makedirs(save_dir)
83 |
84 |
85 | # read rgbd data
86 | if isinstance(imagefile, list) and len(imagefile)==2:
87 | image = get_rgbd_frame(imagefile[0], imagefile[1], dtype='rgbcolormap', depth_clip=True)
88 |
89 | modality = image[:, :, 3:]
90 | if '/depth/' in imagefile[1]:
91 | dummy = modality[:, :, 0:1].copy() * 0 + 1
92 | image = cv2.merge((image[:, :, :3], modality, dummy))
93 | else:
94 | dummy = modality[:, :, 0:1].copy() * 0 + 1
95 | image = cv2.merge((image[:, :, :3], modality, dummy))
96 | else:
97 | image = cv2.cvtColor(cv2.imread(imagefile), cv2.COLOR_BGR2RGB) # Right
98 |
99 | tracker.initialize(image, selection)
100 |
101 | while True:
102 | imagefile = handle.frame()
103 | if not imagefile:
104 | break
105 |
106 | # read rgbd data
107 | if isinstance(imagefile, list) and len(imagefile) == 2:
108 | image = get_rgbd_frame(imagefile[0], imagefile[1], dtype='rgbcolormap', depth_clip=True)
109 |
110 |
111 | modality = image[:, :, 3:]
112 | if '/depth/' in imagefile[1]:
113 | dummy = modality[:, :, 0:1].copy() * 0 + 1 # +1 for depth
114 | image = cv2.merge((image[:, :, :3], modality, dummy))
115 | else:
116 | dummy = modality[:, :, 0:1].copy() * 0 + 1
117 | image = cv2.merge((image[:, :, :3], modality, dummy))
118 |
119 |
120 | else:
121 | image = cv2.cvtColor(cv2.imread(imagefile), cv2.COLOR_BGR2RGB) # Right
122 |
123 | b1, max_score = tracker.track(image)
124 |
125 | if out_conf:
126 | handle.report(vot.Rectangle(*b1), max_score)
127 | else:
128 | handle.report(vot.Rectangle(*b1))
129 | if vis:
130 | '''Visualization'''
131 | # original image
132 | image_ori = image[:,:,::-1].copy() # RGB --> BGR
133 | image_name = imagefile.split('/')[-1]
134 | save_path = os.path.join(save_dir, image_name)
135 | image_b = image_ori.copy()
136 | cv2.rectangle(image_b, (int(b1[0]), int(b1[1])),
137 | (int(b1[0] + b1[2]), int(b1[1] + b1[3])), (0, 0, 255), 2)
138 | image_b_name = image_name.replace('.jpg','_bbox.jpg')
139 | save_path = os.path.join(save_dir, image_b_name)
140 | cv2.imwrite(save_path, image_b)
141 |
142 |
--------------------------------------------------------------------------------
/lib/test/vot/vot.py:
--------------------------------------------------------------------------------
1 | """
2 | \file vot.py
3 | @brief Python utility functions for VOT integration
4 | @author Luka Cehovin, Alessio Dore
5 | @date 2016
6 | """
7 |
8 | import sys
9 | import copy
10 | import collections
11 | import numpy as np
12 |
13 | try:
14 | import trax
15 | except ImportError:
16 | raise Exception('TraX support not found. Please add trax module to Python path.')
17 |
18 | Rectangle = collections.namedtuple('Rectangle', ['x', 'y', 'width', 'height'])
19 | Point = collections.namedtuple('Point', ['x', 'y'])
20 | Polygon = collections.namedtuple('Polygon', ['points'])
21 |
22 | class VOT(object):
23 | """ Base class for Python VOT integration """
24 | def __init__(self, region_format, channels=None):
25 | """ Constructor
26 | Args:
27 | region_format: Region format options
28 | """
29 | assert(region_format in [trax.Region.RECTANGLE, trax.Region.POLYGON, trax.Region.MASK])
30 |
31 | if channels is None:
32 | channels = ['color']
33 | elif channels == 'rgbd':
34 | channels = ['color', 'depth']
35 | elif channels == 'rgbt':
36 | channels = ['color', 'ir']
37 | elif channels == 'ir':
38 | channels = ['ir']
39 | else:
40 | raise Exception('Illegal configuration {}.'.format(channels))
41 |
42 | # self._trax = trax.Server([region_format], [trax.Image.PATH], channels, customMetadata=dict(vot="python"))
43 | self._trax = trax.Server([region_format], [trax.Image.PATH], channels, customMetadata=dict(vot="python"))
44 |
45 | request = self._trax.wait()
46 | assert(request.type == 'initialize')
47 | if isinstance(request.region, trax.Polygon):
48 | self._region = Polygon([Point(x[0], x[1]) for x in request.region])
49 | elif isinstance(request.region, trax.Mask):
50 | self._region = request.region.array(True)
51 | else:
52 | self._region = Rectangle(*request.region.bounds())
53 | self._image = [x.path() for k, x in request.image.items()]
54 | if len(self._image) == 1:
55 | self._image = self._image[0]
56 |
57 | self._trax.status(request.region)
58 |
59 | def region(self):
60 | """
61 | Send configuration message to the client and receive the initialization
62 | region and the path of the first image
63 | Returns:
64 | initialization region
65 | """
66 |
67 | return self._region
68 |
69 | def report(self, region, confidence = None):
70 | """
71 | Report the tracking results to the client
72 | Arguments:
73 | region: region for the frame
74 | """
75 | assert(isinstance(region, (Rectangle, Polygon, np.ndarray)))
76 | if isinstance(region, Polygon):
77 | tregion = trax.Polygon.create([(x.x, x.y) for x in region.points])
78 | elif isinstance(region, np.ndarray):
79 | tregion = trax.Mask.create(region)
80 | else:
81 | tregion = trax.Rectangle.create(region.x, region.y, region.width, region.height)
82 | properties = {}
83 | if not confidence is None:
84 | properties['confidence'] = confidence
85 | self._trax.status(tregion, properties)
86 |
87 | def frame(self):
88 | """
89 | Get a frame (image path) from client
90 | Returns:
91 | absolute path of the image
92 | """
93 | if hasattr(self, "_image"):
94 | image = self._image
95 | del self._image
96 | return image
97 |
98 | request = self._trax.wait()
99 |
100 | if request.type == 'frame':
101 | image = [x.path() for k, x in request.image.items()]
102 | if len(image) == 1:
103 | return image[0]
104 | return image
105 | else:
106 | return None
107 |
108 |
109 | def quit(self):
110 | if hasattr(self, '_trax'):
111 | self._trax.quit()
112 |
113 | def __del__(self):
114 | self.quit()
115 |
--------------------------------------------------------------------------------
/lib/test/vot/vot22_utils.py:
--------------------------------------------------------------------------------
1 | import numpy as np
2 |
3 |
4 | def make_full_size(x, output_sz):
5 | """
6 | zero-pad input x (right and down) to match output_sz
7 | x: numpy array e.g., binary mask
8 | output_sz: size of the output [width, height]
9 | """
10 | if x.shape[0] == output_sz[1] and x.shape[1] == output_sz[0]:
11 | return x
12 | pad_x = output_sz[0] - x.shape[1]
13 | if pad_x < 0:
14 | x = x[:, :x.shape[1] + pad_x]
15 | # padding has to be set to zero, otherwise pad function fails
16 | pad_x = 0
17 | pad_y = output_sz[1] - x.shape[0]
18 | if pad_y < 0:
19 | x = x[:x.shape[0] + pad_y, :]
20 | # padding has to be set to zero, otherwise pad function fails
21 | pad_y = 0
22 | return np.pad(x, ((0, pad_y), (0, pad_x)), 'constant', constant_values=0)
23 |
24 |
25 | def rect_from_mask(mask):
26 | """
27 | create an axis-aligned rectangle from a given binary mask
28 | mask in created as a minimal rectangle containing all non-zero pixels
29 | """
30 | x_ = np.sum(mask, axis=0)
31 | y_ = np.sum(mask, axis=1)
32 | x0 = np.min(np.nonzero(x_))
33 | x1 = np.max(np.nonzero(x_))
34 | y0 = np.min(np.nonzero(y_))
35 | y1 = np.max(np.nonzero(y_))
36 | return [x0, y0, x1 - x0 + 1, y1 - y0 + 1]
37 |
38 |
39 | def mask_from_rect(rect, output_sz):
40 | """
41 | create a binary mask from a given rectangle
42 | rect: axis-aligned rectangle [x0, y0, width, height]
43 | output_sz: size of the output [width, height]
44 | """
45 | mask = np.zeros((output_sz[1], output_sz[0]), dtype=np.uint8)
46 | x0 = max(int(round(rect[0])), 0)
47 | y0 = max(int(round(rect[1])), 0)
48 | x1 = min(int(round(rect[0] + rect[2])), output_sz[0])
49 | y1 = min(int(round(rect[1] + rect[3])), output_sz[1])
50 | mask[y0:y1, x0:x1] = 1
51 | return mask
52 |
53 |
54 | def bbox_clip(x1, y1, x2, y2, boundary, min_sz=10):
55 | """boundary (H,W)"""
56 | x1_new = max(0, min(x1, boundary[1] - min_sz))
57 | y1_new = max(0, min(y1, boundary[0] - min_sz))
58 | x2_new = max(min_sz, min(x2, boundary[1]))
59 | y2_new = max(min_sz, min(y2, boundary[0]))
60 | return x1_new, y1_new, x2_new, y2_new
--------------------------------------------------------------------------------
/lib/train/__init__.py:
--------------------------------------------------------------------------------
1 | from .admin.multigpu import MultiGPU
2 |
--------------------------------------------------------------------------------
/lib/train/__pycache__/__init__.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/__init__.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/__pycache__/_init_paths.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/_init_paths.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/__pycache__/_init_paths.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/_init_paths.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/__pycache__/base_functions.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/base_functions.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/__pycache__/train_script.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/__pycache__/train_script.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/_init_paths.py:
--------------------------------------------------------------------------------
1 | from __future__ import absolute_import
2 | from __future__ import division
3 | from __future__ import print_function
4 |
5 | import os.path as osp
6 | import sys
7 |
8 |
9 | def add_path(path):
10 | if path not in sys.path:
11 | sys.path.insert(0, path)
12 |
13 |
14 | this_dir = osp.dirname(__file__)
15 |
16 | prj_path = osp.join(this_dir, '../..')
17 | add_path(prj_path)
18 |
--------------------------------------------------------------------------------
/lib/train/actors/__init__.py:
--------------------------------------------------------------------------------
1 | from .base_actor import BaseActor
2 | from .untrack import UntrackActor
3 |
--------------------------------------------------------------------------------
/lib/train/actors/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/actors/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/actors/__pycache__/base_actor.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/actors/__pycache__/base_actor.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/actors/__pycache__/untrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/actors/__pycache__/untrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/actors/__pycache__/vipt.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/actors/__pycache__/vipt.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/actors/base_actor.py:
--------------------------------------------------------------------------------
1 | from lib.utils import TensorDict
2 |
3 |
4 | class BaseActor:
5 | """ Base class for actor. The actor class handles the passing of the data through the network
6 | and calculation the loss"""
7 | def __init__(self, net, objective):
8 | """
9 | args:
10 | net - The network to train
11 | objective - The loss function
12 | """
13 | self.net = net
14 | self.objective = objective
15 |
16 | def __call__(self, data: TensorDict):
17 | """ Called in each training iteration. Should pass in input data through the network, calculate the loss, and
18 | return the training stats for the input data
19 | args:
20 | data - A TensorDict containing all the necessary data blocks.
21 |
22 | returns:
23 | loss - loss for the input data
24 | stats - a dict containing detailed losses
25 | """
26 | raise NotImplementedError
27 |
28 | def to(self, device):
29 | """ Move the network to device
30 | args:
31 | device - device to use. 'cpu' or 'cuda'
32 | """
33 | self.net.to(device)
34 |
35 | def train(self, mode=True):
36 | """ Set whether the network is in train mode.
37 | args:
38 | mode (True) - Bool specifying whether in training mode.
39 | """
40 | self.net.train(mode)
41 |
42 | def eval(self):
43 | """ Set network to eval mode"""
44 | self.train(False)
--------------------------------------------------------------------------------
/lib/train/actors/untrack.py:
--------------------------------------------------------------------------------
1 | import pdb
2 |
3 | from . import BaseActor
4 | from lib.utils.box_ops import box_cxcywh_to_xyxy, box_xywh_to_xyxy
5 | import torch
6 | from ...utils.heapmap_utils import generate_heatmap
7 | from ...utils.ce_utils import generate_mask_cond, adjust_keep_rate
8 | from lib.train.admin import multigpu
9 |
10 |
11 | class UntrackActor(BaseActor):
12 | """ Actor for training UnTrack models """
13 |
14 | def __init__(self, net, objective, loss_weight, settings, cfg=None):
15 | super().__init__(net, objective)
16 | self.loss_weight = loss_weight
17 | self.settings = settings
18 | self.bs = self.settings.batchsize # batch size
19 | self.cfg = cfg
20 |
21 | def fix_bns(self):
22 | net = self.net.module if multigpu.is_multi_gpu(self.net) else self.net
23 | net.box_head.apply(self.fix_bn)
24 |
25 | def fix_bn(self, m):
26 | classname = m.__class__.__name__
27 | if classname.find('BatchNorm') != -1:
28 | m.eval()
29 |
30 | def __call__(self, data):
31 | """
32 | args:
33 | data - The input data, should contain the fields 'template', 'search', 'gt_bbox'.
34 | template_images: (N_t, batch, 3, H, W)
35 | search_images: (N_s, batch, 3, H, W)
36 | returns:
37 | loss - the training loss
38 | status - dict containing detailed losses
39 | """
40 | # forward pass
41 | out_dict = self.forward_pass(data)
42 | # compute losses
43 | loss, status = self.compute_losses(out_dict, data)
44 |
45 | return loss, status
46 |
47 | def forward_pass(self, data):
48 | # currently only support 1 template and 1 search region
49 | assert len(data['template_images']) == 1
50 | assert len(data['search_images']) == 1
51 |
52 | template_list = []
53 | for i in range(self.settings.num_template):
54 | template_img_i = data['template_images'][i].view(-1,
55 | *data['template_images'].shape[2:]) # (batch, 6, 128, 128)
56 | template_list.append(template_img_i)
57 |
58 | search_img = data['search_images'][0].view(-1, *data['search_images'].shape[2:]) # (batch, 6, 320, 320)
59 |
60 | box_mask_z = None
61 | ce_keep_rate = None
62 | if self.cfg.MODEL.BACKBONE.CE_LOC:
63 | box_mask_z = generate_mask_cond(self.cfg, template_list[0].shape[0], template_list[0].device,
64 | data['template_anno'][0])
65 |
66 | ce_start_epoch = self.cfg.TRAIN.CE_START_EPOCH
67 | ce_warm_epoch = self.cfg.TRAIN.CE_WARM_EPOCH
68 | ce_keep_rate = adjust_keep_rate(data['epoch'], warmup_epochs=ce_start_epoch,
69 | total_epochs=ce_start_epoch + ce_warm_epoch,
70 | ITERS_PER_EPOCH=1,
71 | base_keep_rate=self.cfg.MODEL.BACKBONE.CE_KEEP_RATIO[0])
72 | # ce_keep_rate = 0.7
73 |
74 | if len(template_list) == 1:
75 | template_list = template_list[0]
76 |
77 | out_dict = self.net(template=template_list,
78 | search=search_img,
79 | ce_template_mask=box_mask_z,
80 | ce_keep_rate=ce_keep_rate,
81 | return_last_attn=False)
82 |
83 | return out_dict
84 |
85 | def compute_losses(self, pred_dict, gt_dict, return_status=True):
86 | #infonce = pred_dict['infonce']
87 |
88 | # gt gaussian map
89 | gt_bbox = gt_dict['search_anno'][-1] # (Ns, batch, 4) (x1,y1,w,h) -> (batch, 4)
90 | gt_gaussian_maps = generate_heatmap(gt_dict['search_anno'], self.cfg.DATA.SEARCH.SIZE, self.cfg.MODEL.BACKBONE.STRIDE)
91 | gt_gaussian_maps = gt_gaussian_maps[-1].unsqueeze(1) # (B,1,H,W)
92 |
93 | # Get boxes
94 | pred_boxes = pred_dict['pred_boxes']
95 | if torch.isnan(pred_boxes).any():
96 | raise ValueError("Network outputs is NAN! Stop Training")
97 | num_queries = pred_boxes.size(1)
98 | pred_boxes_vec = box_cxcywh_to_xyxy(pred_boxes).view(-1, 4) # (B,N,4) --> (BN,4) (x1,y1,x2,y2)
99 | gt_boxes_vec = box_xywh_to_xyxy(gt_bbox)[:, None, :].repeat((1, num_queries, 1)).view(-1, 4).clamp(min=0.0,
100 | max=1.0) # (B,4) --> (B,1,4) --> (B,N,4)
101 | # compute giou and iou
102 | try:
103 | giou_loss, iou = self.objective['giou'](pred_boxes_vec, gt_boxes_vec) # (BN,4) (BN,4)
104 | except:
105 | giou_loss, iou = torch.tensor(0.0).cuda(), torch.tensor(0.0).cuda()
106 | # compute l1 loss
107 | l1_loss = self.objective['l1'](pred_boxes_vec, gt_boxes_vec) # (BN,4) (BN,4)
108 | # compute location loss
109 | if 'score_map' in pred_dict:
110 | location_loss = self.objective['focal'](pred_dict['score_map'], gt_gaussian_maps)
111 | else:
112 | location_loss = torch.tensor(0.0, device=l1_loss.device)
113 | # weighted sum
114 | loss = self.loss_weight['giou'] * giou_loss + self.loss_weight['l1'] * l1_loss + self.loss_weight['focal'] * location_loss
115 | if return_status:
116 | # status for log
117 | mean_iou = iou.detach().mean()
118 | status = {"Loss/total": loss.item(),
119 | "Loss/giou": giou_loss.item(),
120 | "Loss/l1": l1_loss.item(),
121 | "Loss/location": location_loss.item(),
122 | "IoU": mean_iou.item(),
123 | }
124 | return loss, status
125 | else:
126 | return loss
--------------------------------------------------------------------------------
/lib/train/admin/__init__.py:
--------------------------------------------------------------------------------
1 | from .environment import env_settings, create_default_local_file_train
2 | from .tensorboard import TensorboardWriter
3 | from .stats import AverageMeter, StatValue
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/__init__.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/__init__.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/environment.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/environment.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/environment.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/environment.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/local.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/local.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/multigpu.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/multigpu.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/multigpu.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/multigpu.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/settings.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/settings.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/settings.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/settings.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/stats.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/stats.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/stats.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/stats.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/tensorboard.cpython-310.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/tensorboard.cpython-310.pyc
--------------------------------------------------------------------------------
/lib/train/admin/__pycache__/tensorboard.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/admin/__pycache__/tensorboard.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/admin/environment.py:
--------------------------------------------------------------------------------
1 | import importlib
2 | import os
3 | from collections import OrderedDict
4 |
5 |
6 | def create_default_local_file():
7 | path = os.path.join(os.path.dirname(__file__), 'local.py')
8 |
9 | empty_str = '\'\''
10 | default_settings = OrderedDict({
11 | 'workspace_dir': empty_str,
12 | 'tensorboard_dir': 'self.workspace_dir + \'/tensorboard/\'',
13 | 'pretrained_networks': 'self.workspace_dir + \'/pretrained_networks/\'',
14 | 'lasot_dir': empty_str,
15 | 'got10k_dir': empty_str,
16 | 'trackingnet_dir': empty_str,
17 | 'coco_dir': empty_str,
18 | 'lvis_dir': empty_str,
19 | 'sbd_dir': empty_str,
20 | 'imagenet_dir': empty_str,
21 | 'imagenetdet_dir': empty_str,
22 | 'ecssd_dir': empty_str,
23 | 'hkuis_dir': empty_str,
24 | 'msra10k_dir': empty_str,
25 | 'davis_dir': empty_str,
26 | 'youtubevos_dir': empty_str})
27 |
28 | comment = {'workspace_dir': 'Base directory for saving network checkpoints.',
29 | 'tensorboard_dir': 'Directory for tensorboard files.'}
30 |
31 | with open(path, 'w') as f:
32 | f.write('class EnvironmentSettings:\n')
33 | f.write(' def __init__(self):\n')
34 |
35 | for attr, attr_val in default_settings.items():
36 | comment_str = None
37 | if attr in comment:
38 | comment_str = comment[attr]
39 | if comment_str is None:
40 | f.write(' self.{} = {}\n'.format(attr, attr_val))
41 | else:
42 | f.write(' self.{} = {} # {}\n'.format(attr, attr_val, comment_str))
43 |
44 |
45 | def create_default_local_file_train(workspace_dir, data_dir):
46 | path = os.path.join(os.path.dirname(__file__), 'local.py')
47 |
48 | empty_str = '\'\''
49 | default_settings = OrderedDict({
50 | 'workspace_dir': workspace_dir,
51 | 'tensorboard_dir': os.path.join(workspace_dir, 'tensorboard'), # Directory for tensorboard files.
52 | 'pretrained_networks': os.path.join(workspace_dir, 'pretrained_networks'),
53 | 'got10k_val_dir': os.path.join(data_dir, 'got10k/val'),
54 | 'lasot_lmdb_dir': os.path.join(data_dir, 'lasot_lmdb'),
55 | 'got10k_lmdb_dir': os.path.join(data_dir, 'got10k_lmdb'),
56 | 'trackingnet_lmdb_dir': os.path.join(data_dir, 'trackingnet_lmdb'),
57 | 'coco_lmdb_dir': os.path.join(data_dir, 'coco_lmdb'),
58 | 'coco_dir': os.path.join(data_dir, 'coco'),
59 | 'lasot_dir': os.path.join(data_dir, 'lasot'),
60 | 'got10k_dir': os.path.join(data_dir, 'got10k/train'),
61 | 'trackingnet_dir': os.path.join(data_dir, 'trackingnet'),
62 | 'depthtrack_dir': os.path.join(data_dir, 'depthtrack/train'),
63 | 'lasher_dir': os.path.join(data_dir, 'lasher/trainingset'),
64 | 'visevent_dir': os.path.join(data_dir, 'visevent/train'),
65 | })
66 |
67 | comment = {'workspace_dir': 'Base directory for saving network checkpoints.',
68 | 'tensorboard_dir': 'Directory for tensorboard files.'}
69 |
70 | with open(path, 'w') as f:
71 | f.write('class EnvironmentSettings:\n')
72 | f.write(' def __init__(self):\n')
73 |
74 | for attr, attr_val in default_settings.items():
75 | comment_str = None
76 | if attr in comment:
77 | comment_str = comment[attr]
78 | if comment_str is None:
79 | if attr_val == empty_str:
80 | f.write(' self.{} = {}\n'.format(attr, attr_val))
81 | else:
82 | f.write(' self.{} = \'{}\'\n'.format(attr, attr_val))
83 | else:
84 | f.write(' self.{} = \'{}\' # {}\n'.format(attr, attr_val, comment_str))
85 |
86 |
87 | def env_settings():
88 | env_module_name = 'lib.train.admin.local'
89 | try:
90 | env_module = importlib.import_module(env_module_name)
91 | return env_module.EnvironmentSettings()
92 | except:
93 | env_file = os.path.join(os.path.dirname(__file__), 'local.py')
94 |
95 | create_default_local_file()
96 | raise RuntimeError('YOU HAVE NOT SETUP YOUR local.py!!!\n Go to "{}" and set all the paths you need. Then try to run again.'.format(env_file))
97 |
--------------------------------------------------------------------------------
/lib/train/admin/local.py:
--------------------------------------------------------------------------------
1 | class EnvironmentSettings:
2 | def __init__(self):
3 | self.workspace_dir = '/home/zwu/Tracking' # Base directory for saving network checkpoints.
4 | self.tensorboard_dir = '/home/zwu/Tracking/tensorboard' # Directory for tensorboard files.
5 | self.pretrained_networks = '/home/zwu/Tracking/pretrained_networks'
6 | self.got10k_val_dir = '/home/zwu/Tracking/data/got10k/val'
7 | self.lasot_lmdb_dir = '/home/zwu/Tracking/data/lasot_lmdb'
8 | self.got10k_lmdb_dir = '/home/zwu/Tracking/data/got10k_lmdb'
9 | self.trackingnet_lmdb_dir = '/home/zwu/Tracking/data/trackingnet_lmdb'
10 | self.coco_lmdb_dir = '/home/zwu/Tracking/data/coco_lmdb'
11 | self.coco_dir = '/home/zwu/Tracking/data/coco'
12 | self.lasot_dir = '/home/zwu/Tracking/data/lasot'
13 | self.got10k_dir = '/home/zwu/Tracking/data/got10k/train'
14 | self.trackingnet_dir = '/home/zwu/Tracking/data/trackingnet'
15 | self.depthtrack_dir = '/home/zwu/Tracking/data/depthtrack/train'
16 | self.lasher_dir = '/home/zwu/Tracking/data/lasher/trainingset'
17 | self.visevent_dir = '/home/zwu/Tracking/data/visevent/train'
18 |
--------------------------------------------------------------------------------
/lib/train/admin/multigpu.py:
--------------------------------------------------------------------------------
1 | import torch.nn as nn
2 | # Here we use DistributedDataParallel(DDP) rather than DataParallel(DP) for multiple GPUs training
3 |
4 |
5 | def is_multi_gpu(net):
6 | return isinstance(net, (MultiGPU, nn.parallel.distributed.DistributedDataParallel))
7 |
8 |
9 | class MultiGPU(nn.parallel.distributed.DistributedDataParallel):
10 | def __getattr__(self, item):
11 | try:
12 | return super().__getattr__(item)
13 | except:
14 | pass
15 | return getattr(self.module, item)
16 |
--------------------------------------------------------------------------------
/lib/train/admin/settings.py:
--------------------------------------------------------------------------------
1 | from lib.train.admin.environment import env_settings
2 |
3 |
4 | class Settings:
5 | """ Training settings, e.g. the paths to datasets and networks."""
6 | def __init__(self):
7 | self.set_default()
8 |
9 | def set_default(self):
10 | self.env = env_settings()
11 | self.use_gpu = True
12 |
13 |
14 |
--------------------------------------------------------------------------------
/lib/train/admin/stats.py:
--------------------------------------------------------------------------------
1 |
2 |
3 | class StatValue:
4 | def __init__(self):
5 | self.clear()
6 |
7 | def reset(self):
8 | self.val = 0
9 |
10 | def clear(self):
11 | self.reset()
12 | self.history = []
13 |
14 | def update(self, val):
15 | self.val = val
16 | self.history.append(self.val)
17 |
18 |
19 | class AverageMeter(object):
20 | """Computes and stores the average and current value"""
21 | def __init__(self):
22 | self.clear()
23 | self.has_new_data = False
24 |
25 | def reset(self):
26 | self.avg = 0
27 | self.val = 0
28 | self.sum = 0
29 | self.count = 0
30 |
31 | def clear(self):
32 | self.reset()
33 | self.history = []
34 |
35 | def update(self, val, n=1):
36 | self.val = val
37 | self.sum += val * n
38 | self.count += n
39 | self.avg = self.sum / self.count
40 |
41 | def new_epoch(self):
42 | if self.count > 0:
43 | self.history.append(self.avg)
44 | self.reset()
45 | self.has_new_data = True
46 | else:
47 | self.has_new_data = False
48 |
49 |
50 | def topk_accuracy(output, target, topk=(1,)):
51 | """Computes the precision@k for the specified values of k"""
52 | single_input = not isinstance(topk, (tuple, list))
53 | if single_input:
54 | topk = (topk,)
55 |
56 | maxk = max(topk)
57 | batch_size = target.size(0)
58 |
59 | _, pred = output.topk(maxk, 1, True, True)
60 | pred = pred.t()
61 | correct = pred.eq(target.view(1, -1).expand_as(pred))
62 |
63 | res = []
64 | for k in topk:
65 | correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)[0]
66 | res.append(correct_k * 100.0 / batch_size)
67 |
68 | if single_input:
69 | return res[0]
70 |
71 | return res
72 |
--------------------------------------------------------------------------------
/lib/train/admin/tensorboard.py:
--------------------------------------------------------------------------------
1 | import os
2 | from collections import OrderedDict
3 |
4 | try:
5 | from torch.utils.tensorboard import SummaryWriter
6 | except:
7 | print('WARNING: You are using tensorboardX instead sis you have a too old pytorch version.')
8 | from tensorboardX import SummaryWriter
9 |
10 |
11 | class TensorboardWriter:
12 | def __init__(self, directory, loader_names):
13 | self.directory = directory
14 | self.writer = OrderedDict({name: SummaryWriter(os.path.join(self.directory, name)) for name in loader_names})
15 |
16 | def write_info(self, script_name, description):
17 | tb_info_writer = SummaryWriter(os.path.join(self.directory, 'info'))
18 | tb_info_writer.add_text('Script_name', script_name)
19 | tb_info_writer.add_text('Description', description)
20 | tb_info_writer.close()
21 |
22 | def write_epoch(self, stats: OrderedDict, epoch: int, ind=-1):
23 | for loader_name, loader_stats in stats.items():
24 | if loader_stats is None:
25 | continue
26 | for var_name, val in loader_stats.items():
27 | if hasattr(val, 'history') and getattr(val, 'has_new_data', True):
28 | self.writer[loader_name].add_scalar(var_name, val.history[ind], epoch)
--------------------------------------------------------------------------------
/lib/train/data/__init__.py:
--------------------------------------------------------------------------------
1 | from .loader import LTRLoader
2 | from .image_loader import jpeg4py_loader, opencv_loader, jpeg4py_loader_w_failsafe, default_image_loader
3 |
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/image_loader.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/image_loader.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/loader.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/loader.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/processing.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/processing.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/processing_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/processing_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/sampler.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/sampler.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/transforms.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/transforms.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/__pycache__/wandb_logger.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/data/__pycache__/wandb_logger.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/data/bounding_box_utils.py:
--------------------------------------------------------------------------------
1 | import torch
2 |
3 |
4 | def rect_to_rel(bb, sz_norm=None):
5 | """Convert standard rectangular parametrization of the bounding box [x, y, w, h]
6 | to relative parametrization [cx/sw, cy/sh, log(w), log(h)], where [cx, cy] is the center coordinate.
7 | args:
8 | bb - N x 4 tensor of boxes.
9 | sz_norm - [N] x 2 tensor of value of [sw, sh] (optional). sw=w and sh=h if not given.
10 | """
11 |
12 | c = bb[...,:2] + 0.5 * bb[...,2:]
13 | if sz_norm is None:
14 | c_rel = c / bb[...,2:]
15 | else:
16 | c_rel = c / sz_norm
17 | sz_rel = torch.log(bb[...,2:])
18 | return torch.cat((c_rel, sz_rel), dim=-1)
19 |
20 |
21 | def rel_to_rect(bb, sz_norm=None):
22 | """Inverts the effect of rect_to_rel. See above."""
23 |
24 | sz = torch.exp(bb[...,2:])
25 | if sz_norm is None:
26 | c = bb[...,:2] * sz
27 | else:
28 | c = bb[...,:2] * sz_norm
29 | tl = c - 0.5 * sz
30 | return torch.cat((tl, sz), dim=-1)
31 |
32 |
33 | def masks_to_bboxes(mask, fmt='c'):
34 |
35 | """ Convert a mask tensor to one or more bounding boxes.
36 | Note: This function is a bit new, make sure it does what it says. /Andreas
37 | :param mask: Tensor of masks, shape = (..., H, W)
38 | :param fmt: bbox layout. 'c' => "center + size" or (x_center, y_center, width, height)
39 | 't' => "top left + size" or (x_left, y_top, width, height)
40 | 'v' => "vertices" or (x_left, y_top, x_right, y_bottom)
41 | :return: tensor containing a batch of bounding boxes, shape = (..., 4)
42 | """
43 | batch_shape = mask.shape[:-2]
44 | mask = mask.reshape((-1, *mask.shape[-2:]))
45 | bboxes = []
46 |
47 | for m in mask:
48 | mx = m.sum(dim=-2).nonzero()
49 | my = m.sum(dim=-1).nonzero()
50 | bb = [mx.min(), my.min(), mx.max(), my.max()] if (len(mx) > 0 and len(my) > 0) else [0, 0, 0, 0]
51 | bboxes.append(bb)
52 |
53 | bboxes = torch.tensor(bboxes, dtype=torch.float32, device=mask.device)
54 | bboxes = bboxes.reshape(batch_shape + (4,))
55 |
56 | if fmt == 'v':
57 | return bboxes
58 |
59 | x1 = bboxes[..., :2]
60 | s = bboxes[..., 2:] - x1 + 1
61 |
62 | if fmt == 'c':
63 | return torch.cat((x1 + 0.5 * s, s), dim=-1)
64 | elif fmt == 't':
65 | return torch.cat((x1, s), dim=-1)
66 |
67 | raise ValueError("Undefined bounding box layout '%s'" % fmt)
68 |
69 |
70 | def masks_to_bboxes_multi(mask, ids, fmt='c'):
71 | assert mask.dim() == 2
72 | bboxes = []
73 |
74 | for id in ids:
75 | mx = (mask == id).sum(dim=-2).nonzero()
76 | my = (mask == id).float().sum(dim=-1).nonzero()
77 | bb = [mx.min(), my.min(), mx.max(), my.max()] if (len(mx) > 0 and len(my) > 0) else [0, 0, 0, 0]
78 |
79 | bb = torch.tensor(bb, dtype=torch.float32, device=mask.device)
80 |
81 | x1 = bb[:2]
82 | s = bb[2:] - x1 + 1
83 |
84 | if fmt == 'v':
85 | pass
86 | elif fmt == 'c':
87 | bb = torch.cat((x1 + 0.5 * s, s), dim=-1)
88 | elif fmt == 't':
89 | bb = torch.cat((x1, s), dim=-1)
90 | else:
91 | raise ValueError("Undefined bounding box layout '%s'" % fmt)
92 | bboxes.append(bb)
93 |
94 | return bboxes
95 |
--------------------------------------------------------------------------------
/lib/train/data/image_loader.py:
--------------------------------------------------------------------------------
1 | import jpeg4py
2 | import cv2 as cv
3 | from PIL import Image
4 | import numpy as np
5 |
6 | davis_palette = np.repeat(np.expand_dims(np.arange(0,256), 1), 3, 1).astype(np.uint8)
7 | davis_palette[:22, :] = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
8 | [0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
9 | [64, 0, 0], [191, 0, 0], [64, 128, 0], [191, 128, 0],
10 | [64, 0, 128], [191, 0, 128], [64, 128, 128], [191, 128, 128],
11 | [0, 64, 0], [128, 64, 0], [0, 191, 0], [128, 191, 0],
12 | [0, 64, 128], [128, 64, 128]]
13 |
14 |
15 | def default_image_loader(path):
16 | """The default image loader, reads the image from the given path. It first tries to use the jpeg4py_loader,
17 | but reverts to the opencv_loader if the former is not available."""
18 | if default_image_loader.use_jpeg4py is None:
19 | # Try using jpeg4py
20 | im = jpeg4py_loader(path)
21 | if im is None:
22 | default_image_loader.use_jpeg4py = False
23 | print('Using opencv_loader instead.')
24 | else:
25 | default_image_loader.use_jpeg4py = True
26 | return im
27 | if default_image_loader.use_jpeg4py:
28 | return jpeg4py_loader(path)
29 | return opencv_loader(path)
30 |
31 | default_image_loader.use_jpeg4py = None
32 |
33 |
34 | def jpeg4py_loader(path):
35 | """ Image reading using jpeg4py https://github.com/ajkxyz/jpeg4py"""
36 | try:
37 | return jpeg4py.JPEG(path).decode()
38 | except Exception as e:
39 | print('ERROR: Could not read image "{}"'.format(path))
40 | print(e)
41 | return None
42 |
43 |
44 | def opencv_loader(path):
45 | """ Read image using opencv's imread function and returns it in rgb format"""
46 | try:
47 | im = cv.imread(path, cv.IMREAD_COLOR)
48 |
49 | # convert to rgb and return
50 | return cv.cvtColor(im, cv.COLOR_BGR2RGB)
51 | except Exception as e:
52 | print('ERROR: Could not read image "{}"'.format(path))
53 | print(e)
54 | return None
55 |
56 |
57 | def jpeg4py_loader_w_failsafe(path):
58 | """ Image reading using jpeg4py https://github.com/ajkxyz/jpeg4py"""
59 | try:
60 | return jpeg4py.JPEG(path).decode()
61 | except:
62 | try:
63 | im = cv.imread(path, cv.IMREAD_COLOR)
64 |
65 | # convert to rgb and return
66 | return cv.cvtColor(im, cv.COLOR_BGR2RGB)
67 | except Exception as e:
68 | print('ERROR: Could not read image "{}"'.format(path))
69 | print(e)
70 | return None
71 |
72 |
73 | def opencv_seg_loader(path):
74 | """ Read segmentation annotation using opencv's imread function"""
75 | try:
76 | return cv.imread(path)
77 | except Exception as e:
78 | print('ERROR: Could not read image "{}"'.format(path))
79 | print(e)
80 | return None
81 |
82 |
83 | def imread_indexed(filename):
84 | """ Load indexed image with given filename. Used to read segmentation annotations."""
85 |
86 | im = Image.open(filename)
87 |
88 | annotation = np.atleast_3d(im)[...,0]
89 | return annotation
90 |
91 |
92 | def imwrite_indexed(filename, array, color_palette=None):
93 | """ Save indexed image as png. Used to save segmentation annotation."""
94 |
95 | if color_palette is None:
96 | color_palette = davis_palette
97 |
98 | if np.atleast_3d(array).shape[2] != 1:
99 | raise Exception("Saving indexed PNGs requires 2D array.")
100 |
101 | im = Image.fromarray(array)
102 | im.putpalette(color_palette.ravel())
103 | im.save(filename, format='PNG')
--------------------------------------------------------------------------------
/lib/train/data/wandb_logger.py:
--------------------------------------------------------------------------------
1 | from collections import OrderedDict
2 |
3 | try:
4 | import wandb
5 | except ImportError:
6 | raise ImportError(
7 | 'Please run "pip install wandb" to install wandb')
8 |
9 |
10 | class WandbWriter:
11 | def __init__(self, exp_name, cfg, output_dir, cur_step=0, step_interval=0):
12 | self.wandb = wandb
13 | self.step = cur_step
14 | self.interval = step_interval
15 | wandb.init(project="tracking", name=exp_name, config=cfg, dir=output_dir)
16 |
17 | def write_log(self, stats: OrderedDict, epoch=-1):
18 | self.step += 1
19 | for loader_name, loader_stats in stats.items():
20 | if loader_stats is None:
21 | continue
22 |
23 | log_dict = {}
24 | for var_name, val in loader_stats.items():
25 | if hasattr(val, 'avg'):
26 | log_dict.update({loader_name + '/' + var_name: val.avg})
27 | else:
28 | log_dict.update({loader_name + '/' + var_name: val.val})
29 |
30 | if epoch >= 0:
31 | log_dict.update({loader_name + '/epoch': epoch})
32 |
33 | self.wandb.log(log_dict, step=self.step*self.interval)
--------------------------------------------------------------------------------
/lib/train/data_specs/README.md:
--------------------------------------------------------------------------------
1 | # README
2 |
3 | ## Description for different text files
4 | GOT10K
5 | - got10k_train_full_split.txt: the complete GOT-10K training set. (9335 videos)
6 | - got10k_train_split.txt: part of videos from the GOT-10K training set
7 | - got10k_val_split.txt: another part of videos from the GOT-10K training set
8 | - got10k_vot_exclude.txt: 1k videos that are forbidden from "using to train models then testing on VOT" (as required by [VOT Challenge](https://www.votchallenge.net/vot2020/participation.html))
9 | - got10k_vot_train_split.txt: part of videos from the "VOT-permitted" GOT-10K training set
10 | - got10k_vot_val_split.txt: another part of videos from the "VOT-permitted" GOT-10K training set
11 |
12 | LaSOT
13 | - lasot_train_split.txt: the complete LaSOT training set
14 |
15 | TrackingNnet
16 | - trackingnet_classmap.txt: The map from the sequence name to the target class for the TrackingNet
--------------------------------------------------------------------------------
/lib/train/data_specs/depthtrack_train.txt:
--------------------------------------------------------------------------------
1 | adapter02_indoor
2 | bag03_indoor
3 | bag05_indoor
4 | ball02_indoor
5 | ball03_indoor
6 | ball04_indoor
7 | ball05_indoor
8 | ball07_indoor
9 | ball08_wild
10 | ball09_wild
11 | ball12_wild
12 | ball13_indoor
13 | ball14_wild
14 | ball17_wild
15 | ball19_indoor
16 | ball21_indoor
17 | basket_indoor
18 | beautifullight01_indoor
19 | bike01_wild
20 | bike02_wild
21 | bike03_wild
22 | book01_indoor
23 | book02_indoor
24 | book04_indoor
25 | book05_indoor
26 | book06_indoor
27 | bottle01_indoor
28 | bottle02_indoor
29 | bottle05_indoor
30 | bottle06_indoor
31 | box_indoor
32 | candlecup_indoor
33 | car01_indoor
34 | car02_indoor
35 | cart_indoor
36 | cat02_indoor
37 | cat03_indoor
38 | cat04_indoor
39 | cat05_indoor
40 | chair01_indoor
41 | chair02_indoor
42 | clothes_indoor
43 | colacan01_indoor
44 | colacan02_indoor
45 | colacan04_indoor
46 | container01_indoor
47 | container02_indoor
48 | cube01_indoor
49 | cube04_indoor
50 | cube06_indoor
51 | cup03_indoor
52 | cup05_indoor
53 | cup06_indoor
54 | cup07_indoor
55 | cup08_indoor
56 | cup09_indoor
57 | cup10_indoor
58 | cup11_indoor
59 | cup13_indoor
60 | cup14_indoor
61 | duck01_wild
62 | duck02_wild
63 | duck04_wild
64 | duck05_wild
65 | duck06_wild
66 | dumbbells02_indoor
67 | earphone02_indoor
68 | egg_indoor
69 | file02_indoor
70 | flower01_indoor
71 | flower02_wild
72 | flowerbasket_indoor
73 | ghostmask_indoor
74 | glass02_indoor
75 | glass03_indoor
76 | glass04_indoor
77 | glass05_indoor
78 | guitarbag_indoor
79 | gymring_wild
80 | hand02_indoor
81 | hat01_indoor
82 | hat02_indoor_320
83 | hat03_indoor
84 | hat04_indoor
85 | human01_indoor
86 | human03_wild
87 | human04_wild
88 | human05_wild
89 | human06_indoor
90 | leaves01_wild
91 | leaves02_indoor
92 | leaves03_wild
93 | leaves04_indoor
94 | leaves05_indoor
95 | leaves06_wild
96 | lock01_wild
97 | mac_indoor
98 | milkbottle_indoor
99 | mirror_indoor
100 | mobilephone01_indoor
101 | mobilephone02_indoor
102 | mobilephone04_indoor
103 | mobilephone05_indoor
104 | mobilephone06_indoor
105 | mushroom01_indoor
106 | mushroom02_wild
107 | mushroom03_wild
108 | mushroom04_indoor
109 | mushroom05_indoor
110 | notebook02_indoor
111 | notebook03_indoor
112 | paintbottle_indoor
113 | painting_indoor_320
114 | parkingsign_wild
115 | pigeon03_wild
116 | pigeon06_wild
117 | pigeon07_wild
118 | pine01_indoor
119 | pine02_wild_320
120 | shoes01_indoor
121 | shoes03_indoor
122 | skateboard01_indoor
123 | skateboard02_indoor
124 | speaker_indoor
125 | stand_indoor
126 | suitcase_indoor
127 | swing01_wild
128 | swing02_wild
129 | teacup_indoor
130 | thermos01_indoor
131 | thermos02_indoor
132 | toiletpaper02_indoor
133 | toiletpaper03_indoor
134 | toiletpaper04_indoor
135 | toy01_indoor
136 | toy04_indoor
137 | toy05_indoor
138 | toy06_indoor
139 | toy07_indoor_320
140 | toy08_indoor
141 | toy10_indoor
142 | toydog_indoor
143 | trashbin_indoor
144 | tree_wild
145 | trophy_indoor
146 | ukulele02_indoor
147 |
--------------------------------------------------------------------------------
/lib/train/data_specs/depthtrack_val.txt:
--------------------------------------------------------------------------------
1 | toy03_indoor
2 | pigeon05_wild
3 | bottle03_indoor
4 | ball16_indoor
5 | bag04_indoor
6 | flower03_indoor
--------------------------------------------------------------------------------
/lib/train/data_specs/lasher_val.txt:
--------------------------------------------------------------------------------
1 | boywalkinginsnow3
2 | leftdrillmasterstanding
3 | leftgirlunderthelamp
4 | girlridesbike
5 | midboyplayingphone
6 | boywithumbrella
7 | manrun
8 | ab_pingpongball
9 | whitecarturnl
10 | girltakemoto
11 | rightgirlatbike
12 | easy_blackboy
13 | man_with_black_clothes2
14 | 7runone
15 | turnblkbike
16 | motobesidescar
17 | bikeafterwhitecar
18 | 2runsix
19 | rightboy_1227
20 | whitesuvcome
21 | AQrightofcomingmotos
22 | 7one
23 | blackman_0115
24 | rightmirrornotshining
25 | AQmanfromdarktrees
26 | bikeboy128
27 | orangegirl
28 | girlturnbike
29 | blackman2
30 | blackcarback
31 | rightof2cupsattached
32 | whitecar2west
33 | hatboy`shead
34 | whitebetweenblackandblue
35 | 2rdcarcome
36 | whitemancome
37 | nearmangotoD
38 | farmanrightwhitesmallhouse
39 | lightmotocoming
40 | boymototakesgirl
41 | leftblackboy
42 | righttallholdball
43 | blackcarcome
44 | twolinefirstone-gai
45 | lowerfoam2throw
46 | Awhitecargo
47 | car2north3
48 | rightfirstboy-ly
49 | girltakingplate
50 | left2ndgreenboy
51 | ab_bolster
52 | 9hatboy
53 | whitecarturn2
54 | midboyblue
55 | basketboywhite
56 | nightmototurn
57 | girlbike
58 | mantoground
59 | pickuptheyellowbook
60 | 8lastone
61 | AQbikeback
62 | girlsquattingbesidesleftbar
63 | blkbikefromnorth
64 | whitecar
65 | Amidredgirl
66 | blackbag
67 | AQblkgirlbike
68 | manwithyellowumbrella
69 | browncar2north
70 | carstop
71 | whiteboywithbag
72 | theleftestrunningboy
73 | girlafterglassdoor2
74 | rightmirrorlikesky
75 | redgirl1497
76 | midboy
77 | folderatlefthand
78 | bikecome
79 | leftfallenchair_inf_white
80 | Agirlrideback
81 | rightgirl
82 | belowrightwhiteboy
83 | moto2north1
84 | truckk
85 | highright2ndboy
86 | girl`sheadoncall
87 | whiteboy
88 | truckwhite
89 | AQgirlbiketurns
90 | left2ndboy
91 | whitegirl2right
92 | rightboywithwhite
93 | girlplayingphone
94 | girlumbrella
95 | truck
96 | manfarbesidespool
97 | dotat43
--------------------------------------------------------------------------------
/lib/train/dataset/__init__.py:
--------------------------------------------------------------------------------
1 | from .lasot import Lasot
2 | from .got10k import Got10k
3 | from .tracking_net import TrackingNet
4 | from .imagenetvid import ImagenetVID
5 | from .coco import MSCOCO
6 | from .coco_seq import MSCOCOSeq
7 | from .got10k_lmdb import Got10k_lmdb
8 | from .lasot_lmdb import Lasot_lmdb
9 | from .imagenetvid_lmdb import ImagenetVID_lmdb
10 | from .coco_seq_lmdb import MSCOCOSeq_lmdb
11 | from .tracking_net_lmdb import TrackingNet_lmdb
12 | # RGBT dataloader
13 | from .lasher import LasHeR
14 | # RGBD dataloader
15 | from .depthtrack import DepthTrack
16 | # Event dataloader
17 | from .visevent import VisEvent
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/COCO_tool.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/COCO_tool.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/base_image_dataset.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/base_image_dataset.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/base_video_dataset.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/base_video_dataset.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/coco.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/coco.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/coco_seq.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/coco_seq.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/coco_seq_lmdb.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/coco_seq_lmdb.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/depth_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/depth_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/depthtrack.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/depthtrack.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/got10k.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/got10k.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/got10k_lmdb.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/got10k_lmdb.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/imagenetvid.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/imagenetvid.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/imagenetvid_lmdb.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/imagenetvid_lmdb.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/lasher.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/lasher.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/lasot.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/lasot.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/lasot_lmdb.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/lasot_lmdb.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/tracking_net.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/tracking_net.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/tracking_net_lmdb.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/tracking_net_lmdb.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/__pycache__/visevent.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/__pycache__/visevent.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/dataset/base_image_dataset.py:
--------------------------------------------------------------------------------
1 | import torch.utils.data
2 | from lib.train.data.image_loader import jpeg4py_loader
3 |
4 |
5 | class BaseImageDataset(torch.utils.data.Dataset):
6 | """ Base class for image datasets """
7 |
8 | def __init__(self, name, root, image_loader=jpeg4py_loader):
9 | """
10 | args:
11 | root - The root path to the dataset
12 | image_loader (jpeg4py_loader) - The function to read the images. jpeg4py (https://github.com/ajkxyz/jpeg4py)
13 | is used by default.
14 | """
15 | self.name = name
16 | self.root = root
17 | self.image_loader = image_loader
18 |
19 | self.image_list = [] # Contains the list of sequences.
20 | self.class_list = []
21 |
22 | def __len__(self):
23 | """ Returns size of the dataset
24 | returns:
25 | int - number of samples in the dataset
26 | """
27 | return self.get_num_images()
28 |
29 | def __getitem__(self, index):
30 | """ Not to be used! Check get_frames() instead.
31 | """
32 | return None
33 |
34 | def get_name(self):
35 | """ Name of the dataset
36 |
37 | returns:
38 | string - Name of the dataset
39 | """
40 | raise NotImplementedError
41 |
42 | def get_num_images(self):
43 | """ Number of sequences in a dataset
44 |
45 | returns:
46 | int - number of sequences in the dataset."""
47 | return len(self.image_list)
48 |
49 | def has_class_info(self):
50 | return False
51 |
52 | def get_class_name(self, image_id):
53 | return None
54 |
55 | def get_num_classes(self):
56 | return len(self.class_list)
57 |
58 | def get_class_list(self):
59 | return self.class_list
60 |
61 | def get_images_in_class(self, class_name):
62 | raise NotImplementedError
63 |
64 | def has_segmentation_info(self):
65 | return False
66 |
67 | def get_image_info(self, seq_id: object) -> object:
68 | """ Returns information about a particular image,
69 |
70 | args:
71 | seq_id - index of the image
72 |
73 | returns:
74 | Dict
75 | """
76 | raise NotImplementedError
77 |
78 | def get_image(self, image_id, anno=None):
79 | """ Get a image
80 |
81 | args:
82 | image_id - index of image
83 | anno(None) - The annotation for the sequence (see get_sequence_info). If None, they will be loaded.
84 |
85 | returns:
86 | image -
87 | anno -
88 | dict - A dict containing meta information about the sequence, e.g. class of the target object.
89 |
90 | """
91 | raise NotImplementedError
92 |
93 |
--------------------------------------------------------------------------------
/lib/train/dataset/base_video_dataset.py:
--------------------------------------------------------------------------------
1 | import torch.utils.data
2 | # 2021.1.5 use jpeg4py_loader_w_failsafe as default
3 | from lib.train.data.image_loader import jpeg4py_loader_w_failsafe
4 |
5 |
6 | class BaseVideoDataset(torch.utils.data.Dataset):
7 | """ Base class for video datasets """
8 |
9 | def __init__(self, name, root, image_loader=jpeg4py_loader_w_failsafe):
10 | """
11 | args:
12 | root - The root path to the dataset
13 | image_loader (jpeg4py_loader) - The function to read the images. jpeg4py (https://github.com/ajkxyz/jpeg4py)
14 | is used by default.
15 | """
16 | self.name = name
17 | self.root = root
18 | self.image_loader = image_loader
19 |
20 | self.sequence_list = [] # Contains the list of sequences.
21 | self.class_list = []
22 |
23 | def __len__(self):
24 | """ Returns size of the dataset
25 | returns:
26 | int - number of samples in the dataset
27 | """
28 | return self.get_num_sequences()
29 |
30 | def __getitem__(self, index):
31 | """ Not to be used! Check get_frames() instead.
32 | """
33 | return None
34 |
35 | def is_video_sequence(self):
36 | """ Returns whether the dataset is a video dataset or an image dataset
37 |
38 | returns:
39 | bool - True if a video dataset
40 | """
41 | return True
42 |
43 | def is_synthetic_video_dataset(self):
44 | """ Returns whether the dataset contains real videos or synthetic
45 |
46 | returns:
47 | bool - True if a video dataset
48 | """
49 | return False
50 |
51 | def get_name(self):
52 | """ Name of the dataset
53 |
54 | returns:
55 | string - Name of the dataset
56 | """
57 | raise NotImplementedError
58 |
59 | def get_num_sequences(self):
60 | """ Number of sequences in a dataset
61 |
62 | returns:
63 | int - number of sequences in the dataset."""
64 | return len(self.sequence_list)
65 |
66 | def has_class_info(self):
67 | return False
68 |
69 | def has_occlusion_info(self):
70 | return False
71 |
72 | def get_num_classes(self):
73 | return len(self.class_list)
74 |
75 | def get_class_list(self):
76 | return self.class_list
77 |
78 | def get_sequences_in_class(self, class_name):
79 | raise NotImplementedError
80 |
81 | def has_segmentation_info(self):
82 | return False
83 |
84 | def get_sequence_info(self, seq_id):
85 | """ Returns information about a particular sequences,
86 |
87 | args:
88 | seq_id - index of the sequence
89 |
90 | returns:
91 | Dict
92 | """
93 | raise NotImplementedError
94 |
95 | def get_frames(self, seq_id, frame_ids, anno=None):
96 | """ Get a set of frames from a particular sequence
97 |
98 | args:
99 | seq_id - index of sequence
100 | frame_ids - a list of frame numbers
101 | anno(None) - The annotation for the sequence (see get_sequence_info). If None, they will be loaded.
102 |
103 | returns:
104 | list - List of frames corresponding to frame_ids
105 | list - List of dicts for each frame
106 | dict - A dict containing meta information about the sequence, e.g. class of the target object.
107 |
108 | """
109 | raise NotImplementedError
110 |
111 |
--------------------------------------------------------------------------------
/lib/train/dataset/imagenetvid_lmdb.py:
--------------------------------------------------------------------------------
1 | import os
2 | from .base_video_dataset import BaseVideoDataset
3 | from lib.train.data import jpeg4py_loader
4 | import torch
5 | from collections import OrderedDict
6 | from lib.train.admin import env_settings
7 | from lib.utils.lmdb_utils import decode_img, decode_json
8 |
9 |
10 | def get_target_to_image_ratio(seq):
11 | anno = torch.Tensor(seq['anno'])
12 | img_sz = torch.Tensor(seq['image_size'])
13 | return (anno[0, 2:4].prod() / (img_sz.prod())).sqrt()
14 |
15 |
16 | class ImagenetVID_lmdb(BaseVideoDataset):
17 | """ Imagenet VID dataset.
18 |
19 | Publication:
20 | ImageNet Large Scale Visual Recognition Challenge
21 | Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy,
22 | Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei
23 | IJCV, 2015
24 | https://arxiv.org/pdf/1409.0575.pdf
25 |
26 | Download the dataset from http://image-net.org/
27 | """
28 | def __init__(self, root=None, image_loader=jpeg4py_loader, min_length=0, max_target_area=1):
29 | """
30 | args:
31 | root - path to the imagenet vid dataset.
32 | image_loader (default_image_loader) - The function to read the images. If installed,
33 | jpeg4py (https://github.com/ajkxyz/jpeg4py) is used by default. Else,
34 | opencv's imread is used.
35 | min_length - Minimum allowed sequence length.
36 | max_target_area - max allowed ratio between target area and image area. Can be used to filter out targets
37 | which cover complete image.
38 | """
39 | root = env_settings().imagenet_dir if root is None else root
40 | super().__init__("imagenetvid_lmdb", root, image_loader)
41 |
42 | sequence_list_dict = decode_json(root, "cache.json")
43 | self.sequence_list = sequence_list_dict
44 |
45 | # Filter the sequences based on min_length and max_target_area in the first frame
46 | self.sequence_list = [x for x in self.sequence_list if len(x['anno']) >= min_length and
47 | get_target_to_image_ratio(x) < max_target_area]
48 |
49 | def get_name(self):
50 | return 'imagenetvid_lmdb'
51 |
52 | def get_num_sequences(self):
53 | return len(self.sequence_list)
54 |
55 | def get_sequence_info(self, seq_id):
56 | bb_anno = torch.Tensor(self.sequence_list[seq_id]['anno'])
57 | valid = (bb_anno[:, 2] > 0) & (bb_anno[:, 3] > 0)
58 | visible = torch.ByteTensor(self.sequence_list[seq_id]['target_visible']) & valid.byte()
59 | return {'bbox': bb_anno, 'valid': valid, 'visible': visible}
60 |
61 | def _get_frame(self, sequence, frame_id):
62 | set_name = 'ILSVRC2015_VID_train_{:04d}'.format(sequence['set_id'])
63 | vid_name = 'ILSVRC2015_train_{:08d}'.format(sequence['vid_id'])
64 | frame_number = frame_id + sequence['start_frame']
65 | frame_path = os.path.join('Data', 'VID', 'train', set_name, vid_name,
66 | '{:06d}.JPEG'.format(frame_number))
67 | return decode_img(self.root, frame_path)
68 |
69 | def get_frames(self, seq_id, frame_ids, anno=None):
70 | sequence = self.sequence_list[seq_id]
71 |
72 | frame_list = [self._get_frame(sequence, f) for f in frame_ids]
73 |
74 | if anno is None:
75 | anno = self.get_sequence_info(seq_id)
76 |
77 | # Create anno dict
78 | anno_frames = {}
79 | for key, value in anno.items():
80 | anno_frames[key] = [value[f_id, ...].clone() for f_id in frame_ids]
81 |
82 | # added the class info to the meta info
83 | object_meta = OrderedDict({'object_class': sequence['class_name'],
84 | 'motion_class': None,
85 | 'major_class': None,
86 | 'root_class': None,
87 | 'motion_adverb': None})
88 |
89 | return frame_list, anno_frames, object_meta
90 |
91 |
--------------------------------------------------------------------------------
/lib/train/dataset/open_set.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/dataset/open_set.py
--------------------------------------------------------------------------------
/lib/train/run_training.py:
--------------------------------------------------------------------------------
1 | import os
2 | os.chdir('/home/zwu/Tracking')
3 | import sys
4 | import argparse
5 | import importlib
6 | import cv2 as cv
7 | import torch.backends.cudnn
8 | import torch.distributed as dist
9 |
10 | import random
11 | import numpy as np
12 | torch.backends.cudnn.benchmark = False
13 |
14 | import _init_paths
15 | import lib.train.admin.settings as ws_settings
16 | import warnings
17 | warnings.filterwarnings("ignore")
18 |
19 | def init_seeds(seed):
20 | random.seed(seed)
21 | np.random.seed(seed)
22 | torch.manual_seed(seed)
23 | torch.cuda.manual_seed(seed)
24 | torch.backends.cudnn.deterministic = True
25 | torch.backends.cudnn.benchmark = False
26 |
27 |
28 | def run_training(script_name, config_name, cudnn_benchmark=True, local_rank=-1, save_dir=None, base_seed=None,
29 | use_lmdb=False, script_name_prv=None, config_name_prv=None, use_wandb=False,
30 | distill=None, script_teacher=None, config_teacher=None):
31 | """Run the train script.
32 | args:
33 | script_name: Name of emperiment in the "experiments/" folder.
34 | config_name: Name of the yaml file in the "experiments/".
35 | cudnn_benchmark: Use cudnn benchmark or not (default is True).
36 | """
37 | if save_dir is None:
38 | print("save_dir dir is not given. Use the default dir instead.")
39 | # This is needed to avoid strange crashes related to opencv
40 | cv.setNumThreads(0)
41 |
42 | torch.backends.cudnn.benchmark = cudnn_benchmark
43 |
44 | print('script_name: {}.py config_name: {}.yaml'.format(script_name, config_name))
45 |
46 | '''2021.1.5 set seed for different process'''
47 | if base_seed is not None:
48 | if local_rank != -1:
49 | init_seeds(base_seed + local_rank)
50 | else:
51 | init_seeds(base_seed)
52 |
53 | settings = ws_settings.Settings()
54 | settings.script_name = script_name
55 | settings.config_name = config_name
56 | settings.project_path = 'train/{}/{}'.format(script_name, config_name) #train/untrack/deep_rgbx
57 | if script_name_prv is not None and config_name_prv is not None:
58 | settings.project_path_prv = 'train/{}/{}'.format(script_name_prv, config_name_prv)
59 | settings.local_rank = local_rank
60 | settings.save_dir = os.path.abspath(save_dir)
61 | settings.use_lmdb = use_lmdb
62 | prj_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))
63 | settings.cfg_file = os.path.join(prj_dir, 'experiments/%s/%s.yaml' % (script_name, config_name))
64 | settings.use_wandb = use_wandb
65 | print('project_path:', settings.project_path)
66 | if distill:
67 | settings.distill = distill
68 | settings.script_teacher = script_teacher
69 | settings.config_teacher = config_teacher
70 | if script_teacher is not None and config_teacher is not None:
71 | settings.project_path_teacher = 'train/{}/{}'.format(script_teacher, config_teacher)
72 | settings.cfg_file_teacher = os.path.join(prj_dir, 'experiments/%s/%s.yaml' % (script_teacher, config_teacher))
73 | expr_module = importlib.import_module('lib.train.train_script_distill')
74 | print('dis')
75 | else:
76 | expr_module = importlib.import_module('lib.train.train_script')
77 | print('undistill')
78 | expr_func = getattr(expr_module, 'run')
79 |
80 | expr_func(settings)
81 |
82 |
83 | def main():
84 | parser = argparse.ArgumentParser(description='Run a train scripts in train_settings.')
85 | parser.add_argument('--script', type=str, required=True, help='Name of the train script.')
86 | parser.add_argument('--config', type=str, required=True, help="Name of the config file.")
87 | parser.add_argument('--cudnn_benchmark', type=bool, default=True, help='Set cudnn benchmark on (1) or off (0) (default is on).')
88 | parser.add_argument('--local_rank', default=-1, type=int, help='node rank for distributed training')
89 | parser.add_argument('--save_dir', type=str, help='the directory to save checkpoints and logs') # ./output
90 | parser.add_argument('--seed', type=int, default=0, help='seed for random numbers')
91 | parser.add_argument('--use_lmdb', type=int, choices=[0, 1], default=0) # whether datasets are in lmdb format
92 | parser.add_argument('--script_prv', type=str, default=None, help='Name of the train script of previous model.')
93 | parser.add_argument('--config_prv', type=str, default=None, help="Name of the config file of previous model.")
94 | parser.add_argument('--use_wandb', type=int, choices=[0, 1], default=0) # whether to use wandb
95 | # for knowledge distillation
96 | parser.add_argument('--distill', type=int, choices=[0, 1], default=0) # whether to use knowledge distillation
97 | parser.add_argument('--script_teacher', type=str, help='teacher script name')
98 | parser.add_argument('--config_teacher', type=str, help='teacher yaml configure file name')
99 |
100 | args = parser.parse_args()
101 |
102 |
103 | if args.local_rank != -1:
104 | dist.init_process_group(backend='nccl')
105 | torch.cuda.set_device(args.local_rank)
106 | else:
107 | torch.cuda.set_device(0)
108 | run_training(args.script, args.config, cudnn_benchmark=args.cudnn_benchmark,
109 | local_rank=args.local_rank, save_dir=args.save_dir, base_seed=args.seed,
110 | use_lmdb=args.use_lmdb, script_name_prv=args.script_prv, config_name_prv=args.config_prv,
111 | use_wandb=args.use_wandb,
112 | distill=args.distill, script_teacher=args.script_teacher, config_teacher=args.config_teacher)
113 |
114 |
115 | if __name__ == '__main__':
116 | main()
117 |
--------------------------------------------------------------------------------
/lib/train/train_script.py:
--------------------------------------------------------------------------------
1 | import os
2 | # loss function related
3 | from lib.utils.box_ops import giou_loss
4 | from torch.nn.functional import l1_loss
5 | from torch.nn import BCEWithLogitsLoss
6 | # train pipeline related
7 | from lib.train.trainers import LTRTrainer
8 | # distributed training related
9 | from torch.nn.parallel import DistributedDataParallel as DDP
10 | # some more advanced functions
11 | from .base_functions import *
12 | # network related
13 | from lib.models.untrack import build_ostrack
14 | from lib.models.untrack import build_untrack
15 | # forward propagation related
16 | from lib.train.actors import UntrackActor
17 | # for import modules
18 | import importlib
19 |
20 | from ..utils.focal_loss import FocalLoss
21 |
22 |
23 | def run(settings):
24 | settings.description = 'Training script for untrack'
25 |
26 | # update the default configs with config file
27 | if not os.path.exists(settings.cfg_file):
28 | raise ValueError("%s doesn't exist." % settings.cfg_file)
29 | config_module = importlib.import_module("lib.config.%s.config" % settings.script_name)
30 | cfg = config_module.cfg
31 | config_module.update_config_from_file(settings.cfg_file)
32 | if settings.local_rank in [-1, 0]:
33 | print("New configuration is shown below.")
34 | for key in cfg.keys():
35 | print("%s configuration:" % key, cfg[key])
36 | print('\n')
37 |
38 | # update settings based on cfg
39 | update_settings(settings, cfg)
40 |
41 | # Record the training log
42 | log_dir = os.path.join(settings.save_dir, 'logs')
43 | if settings.local_rank in [-1, 0]:
44 | if not os.path.exists(log_dir):
45 | os.makedirs(log_dir)
46 | settings.log_file = os.path.join(log_dir, "%s-%s.log" % (settings.script_name, settings.config_name))
47 |
48 | # Build dataloaders
49 | loader_train, loader_val = build_dataloaders(cfg, settings)
50 | # Create network
51 | if settings.script_name == "untrack":
52 | net = build_untrack(cfg)
53 | else:
54 | raise ValueError("illegal script name")
55 |
56 | # wrap networks to distributed one
57 | net.cuda()
58 | if settings.local_rank != -1:
59 | # net = torch.nn.SyncBatchNorm.convert_sync_batchnorm(net) # add syncBN converter
60 | net = DDP(net, device_ids=[settings.local_rank], find_unused_parameters=True)
61 | settings.device = torch.device("cuda:%d" % settings.local_rank)
62 | else:
63 | settings.device = torch.device("cuda:0")
64 | settings.deep_sup = getattr(cfg.TRAIN, "DEEP_SUPERVISION", False)
65 | settings.distill = getattr(cfg.TRAIN, "DISTILL", False)
66 | settings.distill_loss_type = getattr(cfg.TRAIN, "DISTILL_LOSS_TYPE", "KL")
67 | # Loss functions and Actors
68 | if settings.script_name == "untrack":
69 | # here cls loss and cls weight are not use
70 | focal_loss = FocalLoss()
71 | objective = {'giou': giou_loss, 'l1': l1_loss, 'focal': focal_loss, 'cls': BCEWithLogitsLoss()}
72 | loss_weight = {'giou': cfg.TRAIN.GIOU_WEIGHT, 'l1': cfg.TRAIN.L1_WEIGHT, 'focal': 1., 'cls': 1.0, 'nce': 1.0}
73 | actor = UntrackActor(net=net, objective=objective, loss_weight=loss_weight, settings=settings, cfg=cfg)
74 | else:
75 | raise ValueError("illegal script name")
76 |
77 | # Optimizer, parameters, and learning rates
78 | optimizer, lr_scheduler = get_optimizer_scheduler(net, cfg)
79 | use_amp = getattr(cfg.TRAIN, "AMP", False)
80 | settings.save_epoch_interval = getattr(cfg.TRAIN, "SAVE_EPOCH_INTERVAL", 1)
81 | settings.save_last_n_epoch = getattr(cfg.TRAIN, "SAVE_LAST_N_EPOCH", 1)
82 |
83 | if loader_val is None:
84 | trainer = LTRTrainer(actor, [loader_train], optimizer, settings, lr_scheduler, use_amp=use_amp)
85 | else:
86 | trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer, settings, lr_scheduler, use_amp=use_amp)
87 |
88 | # train process
89 | trainer.train(cfg.TRAIN.EPOCH, load_latest=True, fail_safe=True)
90 |
--------------------------------------------------------------------------------
/lib/train/trainers/__init__.py:
--------------------------------------------------------------------------------
1 | from .base_trainer import BaseTrainer
2 | from .ltr_trainer import LTRTrainer
3 |
--------------------------------------------------------------------------------
/lib/train/trainers/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/trainers/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/trainers/__pycache__/base_trainer.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/trainers/__pycache__/base_trainer.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/train/trainers/__pycache__/ltr_trainer.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/train/trainers/__pycache__/ltr_trainer.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__init__.py:
--------------------------------------------------------------------------------
1 | from .tensor import TensorDict, TensorList
2 |
--------------------------------------------------------------------------------
/lib/utils/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/box_ops.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/box_ops.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/ce_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/ce_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/focal_loss.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/focal_loss.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/heapmap_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/heapmap_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/lmdb_utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/lmdb_utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/misc.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/misc.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/__pycache__/tensor.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/utils/__pycache__/tensor.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/utils/box_ops.py:
--------------------------------------------------------------------------------
1 | import torch
2 | from torchvision.ops.boxes import box_area
3 | import numpy as np
4 |
5 |
6 | def box_cxcywh_to_xyxy(x):
7 | x_c, y_c, w, h = x.unbind(-1)
8 | b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
9 | (x_c + 0.5 * w), (y_c + 0.5 * h)]
10 | return torch.stack(b, dim=-1)
11 |
12 |
13 | def box_xywh_to_xyxy(x):
14 | x1, y1, w, h = x.unbind(-1)
15 | b = [x1, y1, x1 + w, y1 + h]
16 | return torch.stack(b, dim=-1)
17 |
18 |
19 | def box_xyxy_to_xywh(x):
20 | x1, y1, x2, y2 = x.unbind(-1)
21 | b = [x1, y1, x2 - x1, y2 - y1]
22 | return torch.stack(b, dim=-1)
23 |
24 |
25 | def box_xyxy_to_cxcywh(x):
26 | x0, y0, x1, y1 = x.unbind(-1)
27 | b = [(x0 + x1) / 2, (y0 + y1) / 2,
28 | (x1 - x0), (y1 - y0)]
29 | return torch.stack(b, dim=-1)
30 |
31 |
32 | # modified from torchvision to also return the union
33 | '''Note that this function only supports shape (N,4)'''
34 |
35 |
36 | def box_iou(boxes1, boxes2):
37 | """
38 |
39 | :param boxes1: (N, 4) (x1,y1,x2,y2)
40 | :param boxes2: (N, 4) (x1,y1,x2,y2)
41 | :return:
42 | """
43 | area1 = box_area(boxes1) # (N,)
44 | area2 = box_area(boxes2) # (N,)
45 |
46 | lt = torch.max(boxes1[:, :2], boxes2[:, :2]) # (N,2)
47 | rb = torch.min(boxes1[:, 2:], boxes2[:, 2:]) # (N,2)
48 |
49 | wh = (rb - lt).clamp(min=0) # (N,2)
50 | inter = wh[:, 0] * wh[:, 1] # (N,)
51 |
52 | union = area1 + area2 - inter
53 |
54 | iou = inter / union
55 | return iou, union
56 |
57 |
58 | '''Note that this implementation is different from DETR's'''
59 |
60 |
61 | def generalized_box_iou(boxes1, boxes2):
62 | """
63 | Generalized IoU from https://giou.stanford.edu/
64 |
65 | The boxes should be in [x0, y0, x1, y1] format
66 |
67 | boxes1: (N, 4)
68 | boxes2: (N, 4)
69 | """
70 | # degenerate boxes gives inf / nan results
71 | # so do an early check
72 | # try:
73 | assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
74 | assert (boxes2[:, 2:] >= boxes2[:, :2]).all()
75 | iou, union = box_iou(boxes1, boxes2) # (N,)
76 |
77 | lt = torch.min(boxes1[:, :2], boxes2[:, :2])
78 | rb = torch.max(boxes1[:, 2:], boxes2[:, 2:])
79 |
80 | wh = (rb - lt).clamp(min=0) # (N,2)
81 | area = wh[:, 0] * wh[:, 1] # (N,)
82 |
83 | return iou - (area - union) / area, iou
84 |
85 |
86 | def giou_loss(boxes1, boxes2):
87 | """
88 |
89 | :param boxes1: (N, 4) (x1,y1,x2,y2)
90 | :param boxes2: (N, 4) (x1,y1,x2,y2)
91 | :return:
92 | """
93 | giou, iou = generalized_box_iou(boxes1, boxes2)
94 | return (1 - giou).mean(), iou
95 |
96 |
97 | def clip_box(box: list, H, W, margin=0):
98 | x1, y1, w, h = box
99 | x2, y2 = x1 + w, y1 + h
100 | x1 = min(max(0, x1), W-margin)
101 | x2 = min(max(margin, x2), W)
102 | y1 = min(max(0, y1), H-margin)
103 | y2 = min(max(margin, y2), H)
104 | w = max(margin, x2-x1)
105 | h = max(margin, y2-y1)
106 | return [x1, y1, w, h]
107 |
--------------------------------------------------------------------------------
/lib/utils/ce_utils.py:
--------------------------------------------------------------------------------
1 | import math
2 |
3 | import torch
4 | import torch.nn.functional as F
5 |
6 |
7 | def generate_bbox_mask(bbox_mask, bbox):
8 | b, h, w = bbox_mask.shape
9 | for i in range(b):
10 | bbox_i = bbox[i].cpu().tolist()
11 | bbox_mask[i, int(bbox_i[1]):int(bbox_i[1] + bbox_i[3] - 1), int(bbox_i[0]):int(bbox_i[0] + bbox_i[2] - 1)] = 1
12 | return bbox_mask
13 |
14 |
15 | def generate_mask_cond(cfg, bs, device, gt_bbox):
16 | template_size = cfg.DATA.TEMPLATE.SIZE
17 | stride = cfg.MODEL.BACKBONE.STRIDE
18 | template_feat_size = template_size // stride
19 |
20 | if cfg.MODEL.BACKBONE.CE_TEMPLATE_RANGE == 'ALL':
21 | box_mask_z = None
22 | elif cfg.MODEL.BACKBONE.CE_TEMPLATE_RANGE == 'CTR_POINT':
23 | if template_feat_size == 8:
24 | index = slice(3, 4)
25 | elif template_feat_size == 12:
26 | index = slice(5, 6)
27 | elif template_feat_size == 7:
28 | index = slice(3, 4)
29 | elif template_feat_size == 14:
30 | index = slice(6, 7)
31 | else:
32 | raise NotImplementedError
33 | box_mask_z = torch.zeros([bs, template_feat_size, template_feat_size], device=device)
34 | box_mask_z[:, index, index] = 1
35 | box_mask_z = box_mask_z.flatten(1).to(torch.bool)
36 | elif cfg.MODEL.BACKBONE.CE_TEMPLATE_RANGE == 'CTR_REC':
37 | # use fixed 4x4 region, 3:5 for 8x8
38 | # use fixed 4x4 region 5:6 for 12x12
39 | if template_feat_size == 8:
40 | index = slice(3, 5)
41 | elif template_feat_size == 12:
42 | index = slice(5, 7)
43 | elif template_feat_size == 7:
44 | index = slice(3, 4)
45 | else:
46 | raise NotImplementedError
47 | box_mask_z = torch.zeros([bs, template_feat_size, template_feat_size], device=device)
48 | box_mask_z[:, index, index] = 1
49 | box_mask_z = box_mask_z.flatten(1).to(torch.bool)
50 |
51 | elif cfg.MODEL.BACKBONE.CE_TEMPLATE_RANGE == 'GT_BOX':
52 | box_mask_z = torch.zeros([bs, template_size, template_size], device=device)
53 | # box_mask_z_ori = data['template_seg'][0].view(-1, 1, *data['template_seg'].shape[2:]) # (batch, 1, 128, 128)
54 | box_mask_z = generate_bbox_mask(box_mask_z, gt_bbox * template_size).unsqueeze(1).to(
55 | torch.float) # (batch, 1, 128, 128)
56 | # box_mask_z_vis = box_mask_z.cpu().numpy()
57 | box_mask_z = F.interpolate(box_mask_z, scale_factor=1. / cfg.MODEL.BACKBONE.STRIDE, mode='bilinear',
58 | align_corners=False)
59 | box_mask_z = box_mask_z.flatten(1).to(torch.bool)
60 | # box_mask_z_vis = box_mask_z[:, 0, ...].cpu().numpy()
61 | # gaussian_maps_vis = generate_heatmap(data['template_anno'], self.cfg.DATA.TEMPLATE.SIZE, self.cfg.MODEL.STRIDE)[0].cpu().numpy()
62 | else:
63 | raise NotImplementedError
64 |
65 | return box_mask_z
66 |
67 |
68 | def adjust_keep_rate(epoch, warmup_epochs, total_epochs, ITERS_PER_EPOCH, base_keep_rate=0.5, max_keep_rate=1, iters=-1):
69 | if epoch < warmup_epochs:
70 | return 1
71 | if epoch >= total_epochs:
72 | return base_keep_rate
73 | if iters == -1:
74 | iters = epoch * ITERS_PER_EPOCH
75 | total_iters = ITERS_PER_EPOCH * (total_epochs - warmup_epochs)
76 | iters = iters - ITERS_PER_EPOCH * warmup_epochs
77 | keep_rate = base_keep_rate + (max_keep_rate - base_keep_rate) \
78 | * (math.cos(iters / total_iters * math.pi) + 1) * 0.5
79 |
80 | return keep_rate
81 |
--------------------------------------------------------------------------------
/lib/utils/focal_loss.py:
--------------------------------------------------------------------------------
1 | from abc import ABC
2 |
3 | import torch
4 | import torch.nn as nn
5 | import torch.nn.functional as F
6 |
7 |
8 | class FocalLoss(nn.Module, ABC):
9 | def __init__(self, alpha=2, beta=4):
10 | super(FocalLoss, self).__init__()
11 | self.alpha = alpha
12 | self.beta = beta
13 |
14 | def forward(self, prediction, target):
15 | positive_index = target.eq(1).float()
16 | negative_index = target.lt(1).float()
17 |
18 | negative_weights = torch.pow(1 - target, self.beta)
19 | # clamp min value is set to 1e-12 to maintain the numerical stability
20 | prediction = torch.clamp(prediction, 1e-12)
21 |
22 | positive_loss = torch.log(prediction) * torch.pow(1 - prediction, self.alpha) * positive_index
23 | negative_loss = torch.log(1 - prediction) * torch.pow(prediction,
24 | self.alpha) * negative_weights * negative_index
25 |
26 | num_positive = positive_index.float().sum()
27 | positive_loss = positive_loss.sum()
28 | negative_loss = negative_loss.sum()
29 |
30 | if num_positive == 0:
31 | loss = -negative_loss
32 | else:
33 | loss = -(positive_loss + negative_loss) / num_positive
34 |
35 | return loss
36 |
37 |
38 | class LBHinge(nn.Module):
39 | """Loss that uses a 'hinge' on the lower bound.
40 | This means that for samples with a label value smaller than the threshold, the loss is zero if the prediction is
41 | also smaller than that threshold.
42 | args:
43 | error_matric: What base loss to use (MSE by default).
44 | threshold: Threshold to use for the hinge.
45 | clip: Clip the loss if it is above this value.
46 | """
47 | def __init__(self, error_metric=nn.MSELoss(), threshold=None, clip=None):
48 | super().__init__()
49 | self.error_metric = error_metric
50 | self.threshold = threshold if threshold is not None else -100
51 | self.clip = clip
52 |
53 | def forward(self, prediction, label, target_bb=None):
54 | negative_mask = (label < self.threshold).float()
55 | positive_mask = (1.0 - negative_mask)
56 |
57 | prediction = negative_mask * F.relu(prediction) + positive_mask * prediction
58 |
59 | loss = self.error_metric(prediction, positive_mask * label)
60 |
61 | if self.clip is not None:
62 | loss = torch.min(loss, torch.tensor([self.clip], device=loss.device))
63 | return loss
--------------------------------------------------------------------------------
/lib/utils/lmdb_utils.py:
--------------------------------------------------------------------------------
1 | import lmdb
2 | import numpy as np
3 | import cv2
4 | import json
5 |
6 | LMDB_ENVS = dict()
7 | LMDB_HANDLES = dict()
8 | LMDB_FILELISTS = dict()
9 |
10 |
11 | def get_lmdb_handle(name):
12 | global LMDB_HANDLES, LMDB_FILELISTS
13 | item = LMDB_HANDLES.get(name, None)
14 | if item is None:
15 | env = lmdb.open(name, readonly=True, lock=False, readahead=False, meminit=False)
16 | LMDB_ENVS[name] = env
17 | item = env.begin(write=False)
18 | LMDB_HANDLES[name] = item
19 |
20 | return item
21 |
22 |
23 | def decode_img(lmdb_fname, key_name):
24 | handle = get_lmdb_handle(lmdb_fname)
25 | binfile = handle.get(key_name.encode())
26 | if binfile is None:
27 | print("Illegal data detected. %s %s" % (lmdb_fname, key_name))
28 | s = np.frombuffer(binfile, np.uint8)
29 | x = cv2.cvtColor(cv2.imdecode(s, cv2.IMREAD_COLOR), cv2.COLOR_BGR2RGB)
30 | return x
31 |
32 |
33 | def decode_str(lmdb_fname, key_name):
34 | handle = get_lmdb_handle(lmdb_fname)
35 | binfile = handle.get(key_name.encode())
36 | string = binfile.decode()
37 | return string
38 |
39 |
40 | def decode_json(lmdb_fname, key_name):
41 | return json.loads(decode_str(lmdb_fname, key_name))
42 |
43 |
44 | if __name__ == "__main__":
45 | lmdb_fname = "/data/sda/v-yanbi/iccv21/LittleBoy_clean/data/got10k_lmdb"
46 | '''Decode image'''
47 | # key_name = "test/GOT-10k_Test_000001/00000001.jpg"
48 | # img = decode_img(lmdb_fname, key_name)
49 | # cv2.imwrite("001.jpg", img)
50 | '''Decode str'''
51 | # key_name = "test/list.txt"
52 | # key_name = "train/GOT-10k_Train_000001/groundtruth.txt"
53 | key_name = "train/GOT-10k_Train_000001/absence.label"
54 | str_ = decode_str(lmdb_fname, key_name)
55 | print(str_)
56 |
--------------------------------------------------------------------------------
/lib/utils/merge.py:
--------------------------------------------------------------------------------
1 | import torch
2 |
3 |
4 | def merge_template_search(inp_list, return_search=False, return_template=False):
5 | """NOTICE: search region related features must be in the last place"""
6 | seq_dict = {"feat": torch.cat([x["feat"] for x in inp_list], dim=0),
7 | "mask": torch.cat([x["mask"] for x in inp_list], dim=1),
8 | "pos": torch.cat([x["pos"] for x in inp_list], dim=0)}
9 | if return_search:
10 | x = inp_list[-1]
11 | seq_dict.update({"feat_x": x["feat"], "mask_x": x["mask"], "pos_x": x["pos"]})
12 | if return_template:
13 | z = inp_list[0]
14 | seq_dict.update({"feat_z": z["feat"], "mask_z": z["mask"], "pos_z": z["pos"]})
15 | return seq_dict
16 |
17 |
18 | def get_qkv(inp_list):
19 | """The 1st element of the inp_list is about the template,
20 | the 2nd (the last) element is about the search region"""
21 | dict_x = inp_list[-1]
22 | dict_c = {"feat": torch.cat([x["feat"] for x in inp_list], dim=0),
23 | "mask": torch.cat([x["mask"] for x in inp_list], dim=1),
24 | "pos": torch.cat([x["pos"] for x in inp_list], dim=0)} # concatenated dict
25 | q = dict_x["feat"] + dict_x["pos"]
26 | k = dict_c["feat"] + dict_c["pos"]
27 | v = dict_c["feat"]
28 | key_padding_mask = dict_c["mask"]
29 | return q, k, v, key_padding_mask
30 |
--------------------------------------------------------------------------------
/lib/vis/__init__.py:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/vis/__init__.py
--------------------------------------------------------------------------------
/lib/vis/__pycache__/__init__.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/vis/__pycache__/__init__.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/vis/__pycache__/plotting.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/vis/__pycache__/plotting.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/vis/__pycache__/utils.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/vis/__pycache__/utils.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/vis/__pycache__/visdom_cus.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/lib/vis/__pycache__/visdom_cus.cpython-37.pyc
--------------------------------------------------------------------------------
/lib/vis/plotting.py:
--------------------------------------------------------------------------------
1 | import matplotlib.pyplot as plt
2 | import numpy as np
3 | import torch
4 | import cv2
5 |
6 |
7 | def draw_figure(fig):
8 | fig.canvas.draw()
9 | fig.canvas.flush_events()
10 | plt.pause(0.001)
11 |
12 |
13 | def show_tensor(a: torch.Tensor, fig_num = None, title = None, range=(None, None), ax=None):
14 | """Display a 2D tensor.
15 | args:
16 | fig_num: Figure number.
17 | title: Title of figure.
18 | """
19 | a_np = a.squeeze().cpu().clone().detach().numpy()
20 | if a_np.ndim == 3:
21 | a_np = np.transpose(a_np, (1, 2, 0))
22 |
23 | if ax is None:
24 | fig = plt.figure(fig_num)
25 | plt.tight_layout()
26 | plt.cla()
27 | plt.imshow(a_np, vmin=range[0], vmax=range[1])
28 | plt.axis('off')
29 | plt.axis('equal')
30 | if title is not None:
31 | plt.title(title)
32 | draw_figure(fig)
33 | else:
34 | ax.cla()
35 | ax.imshow(a_np, vmin=range[0], vmax=range[1])
36 | ax.set_axis_off()
37 | ax.axis('equal')
38 | if title is not None:
39 | ax.set_title(title)
40 | draw_figure(plt.gcf())
41 |
42 |
43 | def plot_graph(a: torch.Tensor, fig_num = None, title = None):
44 | """Plot graph. Data is a 1D tensor.
45 | args:
46 | fig_num: Figure number.
47 | title: Title of figure.
48 | """
49 | a_np = a.squeeze().cpu().clone().detach().numpy()
50 | if a_np.ndim > 1:
51 | raise ValueError
52 | fig = plt.figure(fig_num)
53 | # plt.tight_layout()
54 | plt.cla()
55 | plt.plot(a_np)
56 | if title is not None:
57 | plt.title(title)
58 | draw_figure(fig)
59 |
60 |
61 | def show_image_with_boxes(im, boxes, iou_pred=None, disp_ids=None):
62 | im_np = im.clone().cpu().squeeze().numpy()
63 | im_np = np.ascontiguousarray(im_np.transpose(1, 2, 0).astype(np.uint8))
64 |
65 | boxes = boxes.view(-1, 4).cpu().numpy().round().astype(int)
66 |
67 | # Draw proposals
68 | for i_ in range(boxes.shape[0]):
69 | if disp_ids is None or disp_ids[i_]:
70 | bb = boxes[i_, :]
71 | disp_color = (i_*38 % 256, (255 - i_*97) % 256, (123 + i_*66) % 256)
72 | cv2.rectangle(im_np, (bb[0], bb[1]), (bb[0] + bb[2], bb[1] + bb[3]),
73 | disp_color, 1)
74 |
75 | if iou_pred is not None:
76 | text_pos = (bb[0], bb[1] - 5)
77 | cv2.putText(im_np, 'ID={} IOU = {:3.2f}'.format(i_, iou_pred[i_]), text_pos,
78 | cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1, bottomLeftOrigin=False)
79 |
80 | im_tensor = torch.from_numpy(im_np.transpose(2, 0, 1)).float()
81 |
82 | return im_tensor
83 |
84 |
85 |
86 | def _pascal_color_map(N=256, normalized=False):
87 | """
88 | Python implementation of the color map function for the PASCAL VOC data set.
89 | Official Matlab version can be found in the PASCAL VOC devkit
90 | http://host.robots.ox.ac.uk/pascal/VOC/voc2012/index.html#devkit
91 | """
92 |
93 | def bitget(byteval, idx):
94 | return (byteval & (1 << idx)) != 0
95 |
96 | dtype = 'float32' if normalized else 'uint8'
97 | cmap = np.zeros((N, 3), dtype=dtype)
98 | for i in range(N):
99 | r = g = b = 0
100 | c = i
101 | for j in range(8):
102 | r = r | (bitget(c, 0) << 7 - j)
103 | g = g | (bitget(c, 1) << 7 - j)
104 | b = b | (bitget(c, 2) << 7 - j)
105 | c = c >> 3
106 |
107 | cmap[i] = np.array([r, g, b])
108 |
109 | cmap = cmap / 255 if normalized else cmap
110 | return cmap
111 |
112 |
113 | def overlay_mask(im, ann, alpha=0.5, colors=None, contour_thickness=None):
114 | """ Overlay mask over image.
115 | Source: https://github.com/albertomontesg/davis-interactive/blob/master/davisinteractive/utils/visualization.py
116 | This function allows you to overlay a mask over an image with some
117 | transparency.
118 | # Arguments
119 | im: Numpy Array. Array with the image. The shape must be (H, W, 3) and
120 | the pixels must be represented as `np.uint8` data type.
121 | ann: Numpy Array. Array with the mask. The shape must be (H, W) and the
122 | values must be intergers
123 | alpha: Float. Proportion of alpha to apply at the overlaid mask.
124 | colors: Numpy Array. Optional custom colormap. It must have shape (N, 3)
125 | being N the maximum number of colors to represent.
126 | contour_thickness: Integer. Thickness of each object index contour draw
127 | over the overlay. This function requires to have installed the
128 | package `opencv-python`.
129 | # Returns
130 | Numpy Array: Image of the overlay with shape (H, W, 3) and data type
131 | `np.uint8`.
132 | """
133 | im, ann = np.asarray(im, dtype=np.uint8), np.asarray(ann, dtype=np.int)
134 | if im.shape[:-1] != ann.shape:
135 | raise ValueError('First two dimensions of `im` and `ann` must match')
136 | if im.shape[-1] != 3:
137 | raise ValueError('im must have three channels at the 3 dimension')
138 |
139 | colors = colors or _pascal_color_map()
140 | colors = np.asarray(colors, dtype=np.uint8)
141 |
142 | mask = colors[ann]
143 | fg = im * alpha + (1 - alpha) * mask
144 |
145 | img = im.copy()
146 | img[ann > 0] = fg[ann > 0]
147 |
148 | if contour_thickness: # pragma: no cover
149 | import cv2
150 | for obj_id in np.unique(ann[ann > 0]):
151 | contours = cv2.findContours((ann == obj_id).astype(
152 | np.uint8), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)[-2:]
153 | cv2.drawContours(img, contours[0], -1, colors[obj_id].tolist(),
154 | contour_thickness)
155 | return img
156 |
--------------------------------------------------------------------------------
/lib/vis/utils.py:
--------------------------------------------------------------------------------
1 | import torch
2 | import numpy as np
3 |
4 |
5 | def numpy_to_torch(a: np.ndarray):
6 | return torch.from_numpy(a).float().permute(2, 0, 1).unsqueeze(0)
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | absl-py==1.4.0
2 | appdirs==1.4.4
3 | attributee==0.1.8
4 | attrs==23.1.0
5 | bidict==0.22.1
6 | brotlipy==0.7.0
7 | cachetools==5.3.1
8 | certifi @ file:///croot/certifi_1671487769961/work/certifi
9 | cffi @ file:///croot/cffi_1670423208954/work
10 | chardet @ file:///tmp/build/80754af9/chardet_1607706768982/work
11 | charset-normalizer==3.2.0
12 | click==8.1.7
13 | colorama==0.4.6
14 | cryptography @ file:///croot/cryptography_1677533068310/work
15 | cycler==0.11.0
16 | Cython==3.0.0
17 | dataclasses==0.6
18 | docker-pycreds==0.4.0
19 | dominate==2.8.0
20 | easydict==1.10
21 | fonttools==4.38.0
22 | future==0.18.3
23 | gitdb==4.0.10
24 | GitPython==3.1.32
25 | google-auth==2.22.0
26 | google-auth-oauthlib==0.4.6
27 | grpcio==1.56.2
28 | idna @ file:///croot/idna_1666125576474/work
29 | importlib-metadata==6.7.0
30 | importlib-resources==5.12.0
31 | info-nce-pytorch==0.1.4
32 | install==1.3.5
33 | jpeg4py==0.1.4
34 | jsonpatch==1.33
35 | jsonpointer==2.4
36 | jsonschema==4.17.3
37 | kiwisolver==1.4.4
38 | lazy-object-proxy==1.9.0
39 | llvmlite==0.39.1
40 | lmdb==1.4.1
41 | Markdown==3.4.3
42 | MarkupSafe==2.1.3
43 | matplotlib==3.5.3
44 | mkl-fft==1.3.1
45 | mkl-random @ file:///tmp/build/80754af9/mkl_random_1626179032232/work
46 | mkl-service==2.4.0
47 | networkx==2.6.3
48 | numba==0.56.4
49 | numpy @ file:///opt/conda/conda-bld/numpy_and_numpy_base_1653915516269/work
50 | oauthlib==3.2.2
51 | opencv-python==4.8.0.74
52 | ordered-set==4.1.0
53 | packaging==23.1
54 | pandas==1.3.5
55 | pathtools==0.1.2
56 | phx-class-registry==4.0.6
57 | Pillow==9.4.0
58 | pkgutil_resolve_name==1.3.10
59 | protobuf==3.20.3
60 | psutil==5.9.5
61 | pyasn1==0.5.0
62 | pyasn1-modules==0.3.0
63 | pycocotools==2.0.6
64 | pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
65 | PyLaTeX==1.4.1
66 | pyOpenSSL @ file:///croot/pyopenssl_1677607685877/work
67 | pyparsing==3.1.0
68 | pyrsistent==0.19.3
69 | PySocks @ file:///tmp/build/80754af9/pysocks_1594394576006/work
70 | python-dateutil==2.8.2
71 | pytz==2023.3
72 | PyYAML==6.0.1
73 | requests==2.31.0
74 | requests-oauthlib==1.3.1
75 | rsa==4.9
76 | scipy==1.7.3
77 | sentry-sdk==1.30.0
78 | setproctitle==1.3.2
79 | six @ file:///tmp/build/80754af9/six_1644875935023/work
80 | smmap==5.0.0
81 | tb-nightly==2.12.0a20230113
82 | tensorboard-data-server==0.6.1
83 | tensorboard-plugin-wit==1.8.1
84 | tensorly==0.8.1
85 | timm==0.5.4
86 | torch==1.13.1
87 | torchaudio==0.13.1
88 | torchvision==0.14.1
89 | tornado==6.2
90 | tqdm @ file:///opt/conda/conda-bld/tqdm_1664392687731/work
91 | typing_extensions @ file:///tmp/abs_ben9emwtky/croots/recipe/typing_extensions_1659638822008/work
92 | urllib3==1.26.16
93 | visdom==0.2.4
94 | vot-toolkit==0.5.3
95 | vot-trax==3.0.2
96 | wandb==0.15.9
97 | websocket-client==1.6.1
98 | Werkzeug==2.2.3
99 | zipp==3.15.0
100 |
--------------------------------------------------------------------------------
/tracking/__pycache__/_init_paths.cpython-37.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Zongwei97/UnTrack/8eec76ec912c19e326e2b0020444f8f20c7d4355/tracking/__pycache__/_init_paths.cpython-37.pyc
--------------------------------------------------------------------------------
/tracking/_init_paths.py:
--------------------------------------------------------------------------------
1 | from __future__ import absolute_import
2 | from __future__ import division
3 | from __future__ import print_function
4 |
5 | import os.path as osp
6 | import sys
7 |
8 |
9 | def add_path(path):
10 | if path not in sys.path:
11 | sys.path.insert(0, path)
12 |
13 |
14 | this_dir = osp.dirname(__file__)
15 |
16 | prj_path = osp.join(this_dir, '..')
17 | add_path(prj_path)
18 |
--------------------------------------------------------------------------------
/tracking/create_default_local_file.py:
--------------------------------------------------------------------------------
1 | import argparse
2 | import os
3 | import _init_paths
4 | from lib.train.admin import create_default_local_file_train
5 | from lib.test.evaluation import create_default_local_file_test
6 |
7 |
8 | def parse_args():
9 | parser = argparse.ArgumentParser(description='Create default local file on ITP or PAI')
10 | parser.add_argument("--workspace_dir", type=str, required=True)
11 | parser.add_argument("--data_dir", type=str, required=True)
12 | parser.add_argument("--save_dir", type=str, required=True)
13 | args = parser.parse_args()
14 | return args
15 |
16 |
17 | if __name__ == "__main__":
18 | args = parse_args()
19 | workspace_dir = os.path.realpath(args.workspace_dir)
20 | data_dir = os.path.realpath(args.data_dir)
21 | save_dir = os.path.realpath(args.save_dir)
22 | create_default_local_file_train(workspace_dir, data_dir)
23 | create_default_local_file_test(workspace_dir, data_dir, save_dir)
24 |
--------------------------------------------------------------------------------
/tracking/test.py:
--------------------------------------------------------------------------------
1 | import os
2 | import sys
3 | import argparse
4 |
5 | prj_path = os.path.join(os.path.dirname(__file__), '..')
6 | if prj_path not in sys.path:
7 | sys.path.append(prj_path)
8 |
9 | from lib.test.evaluation import get_dataset
10 | from lib.test.evaluation.running import run_dataset
11 | from lib.test.evaluation.tracker import Tracker
12 |
13 |
14 | def run_tracker(tracker_name, tracker_param, run_id=None, dataset_name='otb', sequence=None, debug=0, threads=0,
15 | num_gpus=8):
16 | """Run tracker on sequence or dataset.
17 | args:
18 | tracker_name: Name of tracking method.
19 | tracker_param: Name of parameter file.
20 | run_id: The run id.
21 | dataset_name: Name of dataset (otb, nfs, uav, tpl, vot, tn, gott, gotv, lasot).
22 | sequence: Sequence number or name.
23 | debug: Debug level.
24 | threads: Number of threads.
25 | """
26 |
27 | dataset = get_dataset(dataset_name)
28 |
29 | if sequence is not None:
30 | dataset = [dataset[sequence]]
31 |
32 | trackers = [Tracker(tracker_name, tracker_param, dataset_name, run_id)]
33 |
34 | run_dataset(dataset, trackers, debug, threads, num_gpus=num_gpus)
35 |
36 |
37 | def main():
38 | parser = argparse.ArgumentParser(description='Run tracker on sequence or dataset.')
39 | parser.add_argument('tracker_name', type=str, help='Name of tracking method.')
40 | parser.add_argument('tracker_param', type=str, help='Name of config file.')
41 | parser.add_argument('--runid', type=int, default=None, help='The run id.')
42 | parser.add_argument('--dataset_name', type=str, default='otb', help='Name of dataset (otb, nfs, uav, tpl, vot, tn, gott, gotv, lasot).')
43 | parser.add_argument('--sequence', type=str, default=None, help='Sequence number or name.')
44 | parser.add_argument('--debug', type=int, default=0, help='Debug level.')
45 | parser.add_argument('--threads', type=int, default=1, help='Number of threads.')
46 | parser.add_argument('--num_gpus', type=int, default=1)
47 |
48 | args = parser.parse_args()
49 |
50 | try:
51 | seq_name = int(args.sequence)
52 | except:
53 | seq_name = args.sequence
54 |
55 | run_tracker(args.tracker_name, args.tracker_param, args.runid, args.dataset_name, seq_name, args.debug,
56 | args.threads, num_gpus=args.num_gpus)
57 |
58 |
59 | if __name__ == '__main__':
60 | main()
--------------------------------------------------------------------------------
/tracking/train.py:
--------------------------------------------------------------------------------
1 | import os
2 | import argparse
3 | import random
4 | import torch
5 |
6 |
7 | def parse_args():
8 | """
9 | args for training. --script untrack --config deep_rgbx --save_dir ./output_x --mode multiple
10 | """
11 | parser = argparse.ArgumentParser(description='Parse args for training')
12 | # for train
13 | parser.add_argument('--script', type=str, default='untrack', help='training script name')
14 | parser.add_argument('--config', type=str, default='deep_rgbx', help='yaml configure file name')
15 | parser.add_argument('--save_dir', type=str, default='./output_x', help='root directory to save checkpoints, logs, and tensorboard')
16 | parser.add_argument('--mode', type=str, choices=["single", "multiple", "multi_node"], default="multiple",
17 | help="train on single gpu or multiple gpus")
18 | parser.add_argument('--nproc_per_node', type=int, default=torch.cuda.device_count(), help="number of GPUs per node") # specify when mode is multiple
19 | parser.add_argument('--use_lmdb', type=int, choices=[0, 1], default=0) # whether datasets are in lmdb format
20 | parser.add_argument('--script_prv', type=str, help='training script name')
21 | parser.add_argument('--config_prv', type=str, default='baseline', help='yaml configure file name')
22 | parser.add_argument('--use_wandb', type=int, choices=[0, 1], default=1) # whether to use wandb
23 | # for knowledge distillation
24 | parser.add_argument('--distill', type=int, choices=[0, 1], default=0) # whether to use knowledge distillation
25 | parser.add_argument('--script_teacher', type=str, help='teacher script name')
26 | parser.add_argument('--config_teacher', type=str, help='teacher yaml configure file name')
27 |
28 | # for multiple machines
29 | parser.add_argument('--rank', type=int, help='Rank of the current process.')
30 | parser.add_argument('--world-size', type=int, help='Number of processes participating in the job.')
31 | parser.add_argument('--ip', type=str, default='127.0.0.1', help='IP of the current rank 0.')
32 | parser.add_argument('--port', type=int, default='20000', help='Port of the current rank 0.')
33 |
34 | args = parser.parse_args()
35 |
36 | return args
37 |
38 |
39 | def main():
40 | args = parse_args()
41 | print('args.config ', args.config)
42 | if args.mode == "single":
43 | train_cmd = "python lib/train/run_training.py --script %s --config %s --save_dir %s --use_lmdb %d " \
44 | "--script_prv %s --config_prv %s --distill %d --script_teacher %s --config_teacher %s --use_wandb %d"\
45 | % (args.script, args.config, args.save_dir, args.use_lmdb, args.script_prv, args.config_prv,
46 | args.distill, args.script_teacher, args.config_teacher, args.use_wandb)
47 | # elif args.mode == "multiple":
48 | # train_cmd = "python -m torch.distributed.launch --nproc_per_node %d --master_port %d lib/train/run_training.py " \
49 | # "--script %s --config %s --save_dir %s --use_lmdb %d --script_prv %s --config_prv %s --use_wandb %d " \
50 | # "--distill %d --script_teacher %s --config_teacher %s" \
51 | # % (args.nproc_per_node, random.randint(10000, 50000), args.script, args.config, args.save_dir, args.use_lmdb, args.script_prv, args.config_prv, args.use_wandb,
52 | # args.distill, args.script_teacher, args.config_teacher)
53 | elif args.mode == "multiple":
54 | train_cmd = "python /home/zwu/Tracking/lib/train/run_training.py " \
55 | "--script %s --config %s --save_dir %s --use_lmdb %d --script_prv %s --config_prv %s --use_wandb %d " \
56 | "--distill %d --script_teacher %s --config_teacher %s" \
57 | % (args.script, args.config, args.save_dir, args.use_lmdb, args.script_prv, args.config_prv, args.use_wandb,
58 | args.distill, args.script_teacher, args.config_teacher)
59 | elif args.mode == "multi_node":
60 | train_cmd = "python -m torch.distributed.launch --nproc_per_node %d --master_addr %s --master_port %d --nnodes %d --node_rank %d lib/train/run_training.py " \
61 | "--script %s --config %s --save_dir %s --use_lmdb %d --script_prv %s --config_prv %s --use_wandb %d " \
62 | "--distill %d --script_teacher %s --config_teacher %s" \
63 | % (args.nproc_per_node, args.ip, args.port, args.world_size, args.rank, args.script, args.config, args.save_dir, args.use_lmdb, args.script_prv, args.config_prv, args.use_wandb,
64 | args.distill, args.script_teacher, args.config_teacher)
65 | else:
66 | raise ValueError("mode should be 'single' or 'multiple' or 'multi_node'.")
67 | os.system(train_cmd)
68 |
69 |
70 | if __name__ == "__main__":
71 | main()
72 |
--------------------------------------------------------------------------------
/train.sh:
--------------------------------------------------------------------------------
1 | # Training UnTrack
2 | python tracking/train.py --script untrack --config deep_rgbx --save_dir ./output_x --mode single
3 |
--------------------------------------------------------------------------------