├── .gitignore ├── Arial.ttf ├── CONTRIBUTING.md ├── Dockerfile ├── LICENSE ├── README.md ├── assets ├── data.png ├── data2.png ├── helmet.gif └── train.png ├── data ├── Argoverse.yaml ├── GlobalWheat2020.yaml ├── Objects365.yaml ├── SKU-110K.yaml ├── VOC.yaml ├── VisDrone.yaml ├── clda.yaml ├── coco.yaml ├── coco128.yaml ├── fire.yaml ├── helmet.yaml ├── hyps │ ├── hyp.finetune.yaml │ ├── hyp.finetune_objects365.yaml │ ├── hyp.scratch-p6.yaml │ └── hyp.scratch.yaml ├── images │ ├── bus.jpg │ └── zidane.jpg ├── scripts │ ├── download_weights.sh │ ├── get_coco.sh │ └── get_coco128.sh └── xView.yaml ├── detect.py ├── export.py ├── hubconf.py ├── models ├── __init__.py ├── common.py ├── experimental.py ├── hub │ ├── anchors.yaml │ ├── yolov3-spp.yaml │ ├── yolov3-tiny.yaml │ ├── yolov3.yaml │ ├── yolov5-bifpn.yaml │ ├── yolov5-fpn.yaml │ ├── yolov5-p2.yaml │ ├── yolov5-p6.yaml │ ├── yolov5-p7.yaml │ ├── yolov5-panet.yaml │ ├── yolov5l6.yaml │ ├── yolov5m6.yaml │ ├── yolov5s-ghost.yaml │ ├── yolov5s-transformer.yaml │ ├── yolov5s6.yaml │ └── yolov5x6.yaml ├── tf.py ├── yolo.py ├── yolov5l.yaml ├── yolov5m.yaml ├── yolov5s.yaml └── yolov5x.yaml ├── requirements.txt ├── train.py ├── tutorial.ipynb ├── utils ├── __init__.py ├── activations.py ├── augmentations.py ├── autoanchor.py ├── aws │ ├── __init__.py │ ├── mime.sh │ ├── resume.py │ └── userdata.sh ├── callbacks.py ├── datasets.py ├── downloads.py ├── flask_rest_api │ ├── README.md │ ├── example_request.py │ └── restapi.py ├── general.py ├── google_app_engine │ ├── Dockerfile │ ├── additional_requirements.txt │ └── app.yaml ├── loggers │ ├── __init__.py │ └── wandb │ │ ├── README.md │ │ ├── __init__.py │ │ ├── log_dataset.py │ │ ├── sweep.py │ │ ├── sweep.yaml │ │ └── wandb_utils.py ├── loss.py ├── metrics.py ├── plots.py └── torch_utils.py └── val.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /Arial.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/Arial.ttf -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | ## Contributing to YOLOv5 🚀 2 | 3 | We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible, whether it's: 4 | 5 | - Reporting a bug 6 | - Discussing the current state of the code 7 | - Submitting a fix 8 | - Proposing a new feature 9 | - Becoming a maintainer 10 | 11 | YOLOv5 works so well due to our combined community effort, and for every small improvement you contribute you will be 12 | helping push the frontiers of what's possible in AI 😃! 13 | 14 | ## Submitting a Pull Request (PR) 🛠️ 15 | 16 | Submitting a PR is easy! This example shows how to submit a PR for updating `requirements.txt` in 4 steps: 17 | 18 | ### 1. Select File to Update 19 | 20 | Select `requirements.txt` to update by clicking on it in GitHub. 21 |

PR_step1

22 | 23 | ### 2. Click 'Edit this file' 24 | 25 | Button is in top-right corner. 26 |

PR_step2

27 | 28 | ### 3. Make Changes 29 | 30 | Change `matplotlib` version from `3.2.2` to `3.3`. 31 |

PR_step3

32 | 33 | ### 4. Preview Changes and Submit PR 34 | 35 | Click on the **Preview changes** tab to verify your updates. At the bottom of the screen select 'Create a **new branch** 36 | for this commit', assign your branch a descriptive name such as `fix/matplotlib_version` and click the green **Propose 37 | changes** button. All done, your PR is now submitted to YOLOv5 for review and approval 😃! 38 |

PR_step4

39 | 40 | ### PR recommendations 41 | 42 | To allow your work to be integrated as seamlessly as possible, we advise you to: 43 | 44 | - ✅ Verify your PR is **up-to-date with origin/master.** If your PR is behind origin/master an 45 | automatic [GitHub actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) rebase may 46 | be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature' 47 | with the name of your local branch: 48 | 49 | ```bash 50 | git remote add upstream https://github.com/ultralytics/yolov5.git 51 | git fetch upstream 52 | git checkout feature # <----- replace 'feature' with local branch name 53 | git merge upstream/master 54 | git push -u origin -f 55 | ``` 56 | 57 | - ✅ Verify all Continuous Integration (CI) **checks are passing**. 58 | - ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase 59 | but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ -Bruce Lee 60 | 61 | ## Submitting a Bug Report 🐛 62 | 63 | If you spot a problem with YOLOv5 please submit a Bug Report! 64 | 65 | For us to start investigating a possibel problem we need to be able to reproduce it ourselves first. We've created a few 66 | short guidelines below to help users provide what we need in order to get started. 67 | 68 | When asking a question, people will be better able to provide help if you provide **code** that they can easily 69 | understand and use to **reproduce** the problem. This is referred to by community members as creating 70 | a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example). Your code that reproduces 71 | the problem should be: 72 | 73 | * ✅ **Minimal** – Use as little code as possible that still produces the same problem 74 | * ✅ **Complete** – Provide **all** parts someone else needs to reproduce your problem in the question itself 75 | * ✅ **Reproducible** – Test the code you're about to provide to make sure it reproduces the problem 76 | 77 | In addition to the above requirements, for [Ultralytics](https://ultralytics.com/) to provide assistance your code 78 | should be: 79 | 80 | * ✅ **Current** – Verify that your code is up-to-date with current 81 | GitHub [master](https://github.com/ultralytics/yolov5/tree/master), and if necessary `git pull` or `git clone` a new 82 | copy to ensure your problem has not already been resolved by previous commits. 83 | * ✅ **Unmodified** – Your problem must be reproducible without any modifications to the codebase in this 84 | repository. [Ultralytics](https://ultralytics.com/) does not provide support for custom code ⚠️. 85 | 86 | If you believe your problem meets all of the above criteria, please close this issue and raise a new one using the 🐛 ** 87 | Bug Report** [template](https://github.com/ultralytics/yolov5/issues/new/choose) and providing 88 | a [minimum reproducible example](https://stackoverflow.com/help/minimal-reproducible-example) to help us better 89 | understand and diagnose your problem. 90 | 91 | ## License 92 | 93 | By contributing, you agree that your contributions will be licensed under 94 | the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/) 95 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch 4 | FROM nvcr.io/nvidia/pytorch:21.05-py3 5 | 6 | # Install linux packages 7 | RUN apt update && apt install -y zip htop screen libgl1-mesa-glx 8 | 9 | # Install python dependencies 10 | COPY requirements.txt . 11 | RUN python -m pip install --upgrade pip 12 | RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof 13 | RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook 14 | RUN pip install --no-cache -U torch torchvision numpy 15 | # RUN pip install --no-cache torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html 16 | 17 | # Create working directory 18 | RUN mkdir -p /usr/src/app 19 | WORKDIR /usr/src/app 20 | 21 | # Copy contents 22 | COPY . /usr/src/app 23 | 24 | # Set environment variables 25 | ENV HOME=/usr/src/app 26 | 27 | 28 | # Usage Examples ------------------------------------------------------------------------------------------------------- 29 | 30 | # Build and Push 31 | # t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t 32 | 33 | # Pull and Run 34 | # t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t 35 | 36 | # Pull and Run with local directory access 37 | # t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t 38 | 39 | # Kill all 40 | # sudo docker kill $(sudo docker ps -q) 41 | 42 | # Kill all image-based 43 | # sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest) 44 | 45 | # Bash into running container 46 | # sudo docker exec -it 5a9b5863d93d bash 47 | 48 | # Bash into stopped container 49 | # id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash 50 | 51 | # Clean up 52 | # docker system prune -a --volumes 53 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # yolov5-helmet-detection-python 2 | A Python implementation of Yolov5 to detect head or helmet in the wild in Jetson Xavier nx and Jetson nano. In Jetson Xavier Nx, it can achieve 33 FPS. 3 | 4 | You can see video play in [BILIBILI](https://www.bilibili.com/video/BV1Kv411M7u2/), or [YOUTUBE](https://www.youtube.com/watch?v=ZFCIcMngP08). 5 | 6 | if you have problem in this project, you can see this [artical](https://blog.csdn.net/weixin_42264234/article/details/121241573). 7 | 8 | If you want to try to train your own model, you can see [yolov5-helmet-detection-python](https://github.com/RichardoMrMu/yolov5-helmet-detection-python). Follow the readme to get your own model. 9 | 10 | 11 | 12 | # Dataset 13 | You can get the dataset from this [aistudio url](https://aistudio.baidu.com/aistudio/datasetdetail/50329). And the head & helmet detect project pdpd version can be found in this [url](https://github.com/PaddlePaddle/awesome-DeepLearning/tree/master/Paddle_Enterprise_CaseBook/Hemtle%20Detection). It is an amazing project. 14 | 15 | ## Data 16 | This pro needs dataset like 17 | ``` 18 | ../datasets/coco128/images/im0.jpg #image 19 | ../datasets/coco128/labels/im0.txt #label 20 | ``` 21 | 22 | 23 | 24 | Download the dataset and unzip it. 25 | 26 | 27 | 28 | ```shell 29 | unzip annnotations.zip 30 | unzip images.zip 31 | ``` 32 | You can get this. 33 | ``` 34 | ├── dataset 35 | ├── annotations 36 | │ ├── fire_000001.xml 37 | │ ├── fire_000002.xml 38 | │ ├── fire_000003.xml 39 | │ | ... 40 | ├── images 41 | │ ├── fire_000001.jpg 42 | │ ├── fire_000003.jpg 43 | │ ├── fire_000003.jpg 44 | │ | ... 45 | ├── label_list.txt 46 | ├── train.txt 47 | └── valid.txt 48 | ``` 49 | You should turn xml files to txt files. You also can see [this](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data 50 | ). 51 | Open `script/sw2yolo.py`, Change `save_path` to your own save path,`root` as your data path, and `list_file` as `val_list.txt` and `train_list.txt` path. 52 | 53 | ```Python 54 | list_file = "./val_list.txt" 55 | xmls_path,imgs_path = get_file_path(list_file) 56 | 57 | # 将train_list中的xml 转成 txt， img放到img中 58 | save_path = './data/yolodata/fire/cocolike/val/' 59 | root = "./data/yolodata/fire/" 60 | train_img_root = root 61 | ``` 62 | 63 | Then you need `script/yolov5-split-label-img.py` to split img and txt file. 64 | 65 | 66 | ```shell 67 | mkdir images 68 | mkdir lables 69 | mv ./train/images/* ./images/train 70 | mv ./train/labels/* ./labels/train 71 | mv ./val/iamges/* ./images/val 72 | mv ./val/lables/* ./lables/val 73 | ``` 74 | 75 | Finally You can get this. 76 | ``` 77 | ├── cocolike 78 | ├── lables 79 | │ ├── val 80 | │ ├── fire_000001.xml 81 | | ├── ... 82 | │ ├── train 83 | │ ├── fire_000002.xml 84 | | ├── ... 85 | │ 86 | ├── images 87 | │ ├── val 88 | │ ├── fire_000001.jpg 89 | | ├── ... 90 | │ ├── train 91 | │ ├── fire_000003.jpg 92 | | ├── ... 93 | ├── label_list.txt 94 | ├── train.txt 95 | └── valid.txt 96 | ``` 97 | ## Datafile 98 | `{porject}/yolov5/data/` add your own yaml files like `helmet.yaml`. 99 | ```yaml 100 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 101 | # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) 102 | # Example usage: python train.py --data coco128.yaml 103 | # parent 104 | # ├── yolov5 105 | # └── datasets 106 | # └── coco128 downloads here 107 | 108 | 109 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 110 | path: /home/data/tbw_data/face-dataset/yolodata/helmet/cocolike/ # dataset root dir 111 | train: images/train # train images (relative to 'path') 128 images 112 | val: images/val # val images (relative to 'path') 128 images 113 | test: # test images (optional) 114 | 115 | # Classes 116 | nc: 2 # number of classes 117 | names: ['head','helmet'] # class names 118 | ``` 119 | 120 | # Train 121 | Change `{project}/train.py`'s data path as your own data yaml path. 122 | 123 | Change `batch-size ` as a suitable num. Change device if you have 2 or more gpu devices. 124 | Then 125 | 126 | ```shell 127 | python train.py 128 | ``` 129 | 130 | # Test 131 | Use `detect.py` to test. 132 | 133 | ```shell 134 | python detect.py --source ./data/yolodata/helmet/cocolike/images --weights ./runs/train/exp/weights/best.pt 135 | ``` 136 | You can see `{project}/runs/detect/` has png results. 137 | -------------------------------------------------------------------------------- /assets/data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/assets/data.png -------------------------------------------------------------------------------- /assets/data2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/assets/data2.png -------------------------------------------------------------------------------- /assets/helmet.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/assets/helmet.gif -------------------------------------------------------------------------------- /assets/train.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/assets/train.png -------------------------------------------------------------------------------- /data/Argoverse.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ 3 | # Example usage: python train.py --data Argoverse.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── Argoverse ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/Argoverse # dataset root dir 12 | train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images 13 | val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images 14 | test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview 15 | 16 | # Classes 17 | nc: 8 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'truck', 'traffic_light', 'stop_sign'] # class names 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | import json 24 | 25 | from tqdm import tqdm 26 | from utils.general import download, Path 27 | 28 | 29 | def argoverse2yolo(set): 30 | labels = {} 31 | a = json.load(open(set, "rb")) 32 | for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."): 33 | img_id = annot['image_id'] 34 | img_name = a['images'][img_id]['name'] 35 | img_label_name = img_name[:-3] + "txt" 36 | 37 | cls = annot['category_id'] # instance class id 38 | x_center, y_center, width, height = annot['bbox'] 39 | x_center = (x_center + width / 2) / 1920.0 # offset and scale 40 | y_center = (y_center + height / 2) / 1200.0 # offset and scale 41 | width /= 1920.0 # scale 42 | height /= 1200.0 # scale 43 | 44 | img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']] 45 | if not img_dir.exists(): 46 | img_dir.mkdir(parents=True, exist_ok=True) 47 | 48 | k = str(img_dir / img_label_name) 49 | if k not in labels: 50 | labels[k] = [] 51 | labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n") 52 | 53 | for k in labels: 54 | with open(k, "w") as f: 55 | f.writelines(labels[k]) 56 | 57 | 58 | # Download 59 | dir = Path('../datasets/Argoverse') # dataset root dir 60 | urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip'] 61 | download(urls, dir=dir, delete=False) 62 | 63 | # Convert 64 | annotations_dir = 'Argoverse-HD/annotations/' 65 | (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images') # rename 'tracking' to 'images' 66 | for d in "train.json", "val.json": 67 | argoverse2yolo(dir / annotations_dir / d) # convert VisDrone annotations to YOLO labels 68 | -------------------------------------------------------------------------------- /data/GlobalWheat2020.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Global Wheat 2020 dataset http://www.global-wheat.com/ 3 | # Example usage: python train.py --data GlobalWheat2020.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── GlobalWheat2020 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/GlobalWheat2020 # dataset root dir 12 | train: # train images (relative to 'path') 3422 images 13 | - images/arvalis_1 14 | - images/arvalis_2 15 | - images/arvalis_3 16 | - images/ethz_1 17 | - images/rres_1 18 | - images/inrae_1 19 | - images/usask_1 20 | val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1) 21 | - images/ethz_1 22 | test: # test images (optional) 1276 images 23 | - images/utokyo_1 24 | - images/utokyo_2 25 | - images/nau_1 26 | - images/uq_1 27 | 28 | # Classes 29 | nc: 1 # number of classes 30 | names: ['wheat_head'] # class names 31 | 32 | 33 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 34 | download: | 35 | from utils.general import download, Path 36 | 37 | # Download 38 | dir = Path(yaml['path']) # dataset root dir 39 | urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip', 40 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip'] 41 | download(urls, dir=dir) 42 | 43 | # Make Directories 44 | for p in 'annotations', 'images', 'labels': 45 | (dir / p).mkdir(parents=True, exist_ok=True) 46 | 47 | # Move 48 | for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \ 49 | 'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1': 50 | (dir / p).rename(dir / 'images' / p) # move to /images 51 | f = (dir / p).with_suffix('.json') # json file 52 | if f.exists(): 53 | f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations 54 | -------------------------------------------------------------------------------- /data/Objects365.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Objects365 dataset https://www.objects365.org/ 3 | # Example usage: python train.py --data Objects365.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── Objects365 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/Objects365 # dataset root dir 12 | train: images/train # train images (relative to 'path') 1742289 images 13 | val: images/val # val images (relative to 'path') 5570 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | nc: 365 # number of classes 18 | names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup', 19 | 'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book', 20 | 'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag', 21 | 'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV', 22 | 'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle', 23 | 'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird', 24 | 'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck', 25 | 'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning', 26 | 'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife', 27 | 'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock', 28 | 'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish', 29 | 'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan', 30 | 'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard', 31 | 'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign', 32 | 'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat', 33 | 'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard', 34 | 'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry', 35 | 'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks', 36 | 'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors', 37 | 'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape', 38 | 'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck', 39 | 'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette', 40 | 'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket', 41 | 'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine', 42 | 'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine', 43 | 'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon', 44 | 'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse', 45 | 'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball', 46 | 'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin', 47 | 'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts', 48 | 'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit', 49 | 'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD', 50 | 'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder', 51 | 'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips', 52 | 'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab', 53 | 'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal', 54 | 'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart', 55 | 'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French', 56 | 'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell', 57 | 'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil', 58 | 'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis'] 59 | 60 | 61 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 62 | download: | 63 | from pycocotools.coco import COCO 64 | from tqdm import tqdm 65 | 66 | from utils.general import download, Path 67 | 68 | # Make Directories 69 | dir = Path(yaml['path']) # dataset root dir 70 | for p in 'images', 'labels': 71 | (dir / p).mkdir(parents=True, exist_ok=True) 72 | for q in 'train', 'val': 73 | (dir / p / q).mkdir(parents=True, exist_ok=True) 74 | 75 | # Download 76 | url = "https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/train/" 77 | download([url + 'zhiyuan_objv2_train.tar.gz'], dir=dir, delete=False) # annotations json 78 | download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train', 79 | curl=True, delete=False, threads=8) 80 | 81 | # Move 82 | train = dir / 'images' / 'train' 83 | for f in tqdm(train.rglob('*.jpg'), desc=f'Moving images'): 84 | f.rename(train / f.name) # move to /images/train 85 | 86 | # Labels 87 | coco = COCO(dir / 'zhiyuan_objv2_train.json') 88 | names = [x["name"] for x in coco.loadCats(coco.getCatIds())] 89 | for cid, cat in enumerate(names): 90 | catIds = coco.getCatIds(catNms=[cat]) 91 | imgIds = coco.getImgIds(catIds=catIds) 92 | for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'): 93 | width, height = im["width"], im["height"] 94 | path = Path(im["file_name"]) # image filename 95 | try: 96 | with open(dir / 'labels' / 'train' / path.with_suffix('.txt').name, 'a') as file: 97 | annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None) 98 | for a in coco.loadAnns(annIds): 99 | x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner) 100 | x, y = x + w / 2, y + h / 2 # xy to center 101 | file.write(f"{cid} {x / width:.5f} {y / height:.5f} {w / width:.5f} {h / height:.5f}\n") 102 | 103 | except Exception as e: 104 | print(e) 105 | -------------------------------------------------------------------------------- /data/SKU-110K.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 3 | # Example usage: python train.py --data SKU-110K.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── SKU-110K ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/SKU-110K # dataset root dir 12 | train: train.txt # train images (relative to 'path') 8219 images 13 | val: val.txt # val images (relative to 'path') 588 images 14 | test: test.txt # test images (optional) 2936 images 15 | 16 | # Classes 17 | nc: 1 # number of classes 18 | names: ['object'] # class names 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | import shutil 24 | from tqdm import tqdm 25 | from utils.general import np, pd, Path, download, xyxy2xywh 26 | 27 | # Download 28 | dir = Path(yaml['path']) # dataset root dir 29 | parent = Path(dir.parent) # download dir 30 | urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz'] 31 | download(urls, dir=parent, delete=False) 32 | 33 | # Rename directories 34 | if dir.exists(): 35 | shutil.rmtree(dir) 36 | (parent / 'SKU110K_fixed').rename(dir) # rename dir 37 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # create labels dir 38 | 39 | # Convert labels 40 | names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height' # column names 41 | for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv': 42 | x = pd.read_csv(dir / 'annotations' / d, names=names).values # annotations 43 | images, unique_images = x[:, 0], np.unique(x[:, 0]) 44 | with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f: 45 | f.writelines(f'./images/{s}\n' for s in unique_images) 46 | for im in tqdm(unique_images, desc=f'Converting {dir / d}'): 47 | cls = 0 # single-class dataset 48 | with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f: 49 | for r in x[images == im]: 50 | w, h = r[6], r[7] # image width, height 51 | xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance 52 | f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label 53 | -------------------------------------------------------------------------------- /data/VOC.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC 3 | # Example usage: python train.py --data VOC.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── VOC ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VOC 12 | train: # train images (relative to 'path') 16551 images 13 | - images/train2012 14 | - images/train2007 15 | - images/val2012 16 | - images/val2007 17 | val: # val images (relative to 'path') 4952 images 18 | - images/test2007 19 | test: # test images (optional) 20 | - images/test2007 21 | 22 | # Classes 23 | nc: 20 # number of classes 24 | names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 25 | 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] # class names 26 | 27 | 28 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 29 | download: | 30 | import xml.etree.ElementTree as ET 31 | 32 | from tqdm import tqdm 33 | from utils.general import download, Path 34 | 35 | 36 | def convert_label(path, lb_path, year, image_id): 37 | def convert_box(size, box): 38 | dw, dh = 1. / size[0], 1. / size[1] 39 | x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2] 40 | return x * dw, y * dh, w * dw, h * dh 41 | 42 | in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml') 43 | out_file = open(lb_path, 'w') 44 | tree = ET.parse(in_file) 45 | root = tree.getroot() 46 | size = root.find('size') 47 | w = int(size.find('width').text) 48 | h = int(size.find('height').text) 49 | 50 | for obj in root.iter('object'): 51 | cls = obj.find('name').text 52 | if cls in yaml['names'] and not int(obj.find('difficult').text) == 1: 53 | xmlbox = obj.find('bndbox') 54 | bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')]) 55 | cls_id = yaml['names'].index(cls) # class id 56 | out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n') 57 | 58 | 59 | # Download 60 | dir = Path(yaml['path']) # dataset root dir 61 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 62 | urls = [url + 'VOCtrainval_06-Nov-2007.zip', # 446MB, 5012 images 63 | url + 'VOCtest_06-Nov-2007.zip', # 438MB, 4953 images 64 | url + 'VOCtrainval_11-May-2012.zip'] # 1.95GB, 17126 images 65 | download(urls, dir=dir / 'images', delete=False) 66 | 67 | # Convert 68 | path = dir / f'images/VOCdevkit' 69 | for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'): 70 | imgs_path = dir / 'images' / f'{image_set}{year}' 71 | lbs_path = dir / 'labels' / f'{image_set}{year}' 72 | imgs_path.mkdir(exist_ok=True, parents=True) 73 | lbs_path.mkdir(exist_ok=True, parents=True) 74 | 75 | image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split() 76 | for id in tqdm(image_ids, desc=f'{image_set}{year}'): 77 | f = path / f'VOC{year}/JPEGImages/{id}.jpg' # old img path 78 | lb_path = (lbs_path / f.name).with_suffix('.txt') # new label path 79 | f.rename(imgs_path / f.name) # move image 80 | convert_label(path, lb_path, year, id) # convert labels to YOLO format 81 | -------------------------------------------------------------------------------- /data/VisDrone.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset 3 | # Example usage: python train.py --data VisDrone.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── VisDrone ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/VisDrone # dataset root dir 12 | train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images 13 | val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images 14 | test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images 15 | 16 | # Classes 17 | nc: 10 # number of classes 18 | names: ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor'] 19 | 20 | 21 | # Download script/URL (optional) --------------------------------------------------------------------------------------- 22 | download: | 23 | from utils.general import download, os, Path 24 | 25 | def visdrone2yolo(dir): 26 | from PIL import Image 27 | from tqdm import tqdm 28 | 29 | def convert_box(size, box): 30 | # Convert VisDrone box to YOLO xywh box 31 | dw = 1. / size[0] 32 | dh = 1. / size[1] 33 | return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh 34 | 35 | (dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory 36 | pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}') 37 | for f in pbar: 38 | img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size 39 | lines = [] 40 | with open(f, 'r') as file: # read annotation.txt 41 | for row in [x.split(',') for x in file.read().strip().splitlines()]: 42 | if row[4] == '0': # VisDrone 'ignored regions' class 0 43 | continue 44 | cls = int(row[5]) - 1 45 | box = convert_box(img_size, tuple(map(int, row[:4]))) 46 | lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n") 47 | with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl: 48 | fl.writelines(lines) # write label.txt 49 | 50 | 51 | # Download 52 | dir = Path(yaml['path']) # dataset root dir 53 | urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip', 54 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip', 55 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip', 56 | 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip'] 57 | download(urls, dir=dir) 58 | 59 | # Convert 60 | for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev': 61 | visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels 62 | -------------------------------------------------------------------------------- /data/clda.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) 3 | # Example usage: python train.py --data coco128.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── coco128 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: /home/data/tbw_data/face-dataset/dataset_for_jiangbo/Train/yolov5-train # dataset root dir 12 | train: images # train images (relative to 'path') 128 images 13 | val: images # val images (relative to 'path') 128 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | nc: 2 # number of classes 18 | names: ['hp_1','hp_2'] # class names 19 | 20 | -------------------------------------------------------------------------------- /data/coco.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO 2017 dataset http://cocodataset.org 3 | # Example usage: python train.py --data coco.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── coco ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco # dataset root dir 12 | train: train2017.txt # train images (relative to 'path') 118287 images 13 | val: val2017.txt # train images (relative to 'path') 5000 images 14 | test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 15 | 16 | # Classes 17 | nc: 80 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 19 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 20 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 21 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 22 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 23 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 24 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 25 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 26 | 'hair drier', 'toothbrush'] # class names 27 | 28 | 29 | # Download script/URL (optional) 30 | download: | 31 | from utils.general import download, Path 32 | 33 | # Download labels 34 | segments = False # segment or box labels 35 | dir = Path(yaml['path']) # dataset root dir 36 | url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/' 37 | urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels 38 | download(urls, dir=dir.parent) 39 | 40 | # Download data 41 | urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images 42 | 'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images 43 | 'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional) 44 | download(urls, dir=dir / 'images', threads=3) 45 | -------------------------------------------------------------------------------- /data/coco128.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) 3 | # Example usage: python train.py --data coco128.yaml 4 | # parent 5 | # ├── yolov5 6 | # └── datasets 7 | # └── coco128 ← downloads here 8 | 9 | 10 | # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] 11 | path: ../datasets/coco128 # dataset root dir 12 | train: images/train2017 # train images (relative to 'path') 128 images 13 | val: images/train2017 # val images (relative to 'path') 128 images 14 | test: # test images (optional) 15 | 16 | # Classes 17 | nc: 80 # number of classes 18 | names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 19 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 20 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 21 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 22 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 23 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 24 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 25 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 26 | 'hair drier', 'toothbrush'] # class names 27 | 28 | 29 | # Download script/URL (optional) 30 | download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip -------------------------------------------------------------------------------- /data/fire.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/data/fire.yaml -------------------------------------------------------------------------------- /data/helmet.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/data/helmet.yaml -------------------------------------------------------------------------------- /data/hyps/hyp.finetune.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for VOC finetuning 3 | # python train.py --batch 64 --weights yolov5m.pt --data VOC.yaml --img 512 --epochs 50 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | # Hyperparameter Evolution Results 7 | # Generations: 306 8 | # P R mAP.5 mAP.5:.95 box obj cls 9 | # Metrics: 0.6 0.936 0.896 0.684 0.0115 0.00805 0.00146 10 | 11 | lr0: 0.0032 12 | lrf: 0.12 13 | momentum: 0.843 14 | weight_decay: 0.00036 15 | warmup_epochs: 2.0 16 | warmup_momentum: 0.5 17 | warmup_bias_lr: 0.05 18 | box: 0.0296 19 | cls: 0.243 20 | cls_pw: 0.631 21 | obj: 0.301 22 | obj_pw: 0.911 23 | iou_t: 0.2 24 | anchor_t: 2.91 25 | # anchors: 3.63 26 | fl_gamma: 0.0 27 | hsv_h: 0.0138 28 | hsv_s: 0.664 29 | hsv_v: 0.464 30 | degrees: 0.373 31 | translate: 0.245 32 | scale: 0.898 33 | shear: 0.602 34 | perspective: 0.0 35 | flipud: 0.00856 36 | fliplr: 0.5 37 | mosaic: 1.0 38 | mixup: 0.243 39 | copy_paste: 0.0 40 | -------------------------------------------------------------------------------- /data/hyps/hyp.finetune_objects365.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | lr0: 0.00258 4 | lrf: 0.17 5 | momentum: 0.779 6 | weight_decay: 0.00058 7 | warmup_epochs: 1.33 8 | warmup_momentum: 0.86 9 | warmup_bias_lr: 0.0711 10 | box: 0.0539 11 | cls: 0.299 12 | cls_pw: 0.825 13 | obj: 0.632 14 | obj_pw: 1.0 15 | iou_t: 0.2 16 | anchor_t: 3.44 17 | anchors: 3.2 18 | fl_gamma: 0.0 19 | hsv_h: 0.0188 20 | hsv_s: 0.704 21 | hsv_v: 0.36 22 | degrees: 0.0 23 | translate: 0.0902 24 | scale: 0.491 25 | shear: 0.0 26 | perspective: 0.0 27 | flipud: 0.0 28 | fliplr: 0.5 29 | mosaic: 1.0 30 | mixup: 0.0 31 | copy_paste: 0.0 32 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch-p6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for COCO training from scratch 3 | # python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.3 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 0.7 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.9 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.0 # image mixup (probability) 34 | copy_paste: 0.0 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for COCO training from scratch 3 | # python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300 4 | # See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials 5 | 6 | lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3) 7 | lrf: 0.2 # final OneCycleLR learning rate (lr0 * lrf) 8 | momentum: 0.937 # SGD momentum/Adam beta1 9 | weight_decay: 0.0005 # optimizer weight decay 5e-4 10 | warmup_epochs: 3.0 # warmup epochs (fractions ok) 11 | warmup_momentum: 0.8 # warmup initial momentum 12 | warmup_bias_lr: 0.1 # warmup initial bias lr 13 | box: 0.05 # box loss gain 14 | cls: 0.5 # cls loss gain 15 | cls_pw: 1.0 # cls BCELoss positive_weight 16 | obj: 1.0 # obj loss gain (scale with pixels) 17 | obj_pw: 1.0 # obj BCELoss positive_weight 18 | iou_t: 0.20 # IoU training threshold 19 | anchor_t: 4.0 # anchor-multiple threshold 20 | # anchors: 3 # anchors per output layer (0 to ignore) 21 | fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5) 22 | hsv_h: 0.015 # image HSV-Hue augmentation (fraction) 23 | hsv_s: 0.7 # image HSV-Saturation augmentation (fraction) 24 | hsv_v: 0.4 # image HSV-Value augmentation (fraction) 25 | degrees: 0.0 # image rotation (+/- deg) 26 | translate: 0.1 # image translation (+/- fraction) 27 | scale: 0.5 # image scale (+/- gain) 28 | shear: 0.0 # image shear (+/- deg) 29 | perspective: 0.0 # image perspective (+/- fraction), range 0-0.001 30 | flipud: 0.0 # image flip up-down (probability) 31 | fliplr: 0.5 # image flip left-right (probability) 32 | mosaic: 1.0 # image mosaic (probability) 33 | mixup: 0.0 # image mixup (probability) 34 | copy_paste: 0.0 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/images/bus.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/data/images/bus.jpg -------------------------------------------------------------------------------- /data/images/zidane.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/data/images/zidane.jpg -------------------------------------------------------------------------------- /data/scripts/download_weights.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 3 | # Download latest models from https://github.com/ultralytics/yolov5/releases 4 | # Example usage: bash path/to/download_weights.sh 5 | # parent 6 | # └── yolov5 7 | # ├── yolov5s.pt ← downloads here 8 | # ├── yolov5m.pt 9 | # └── ... 10 | 11 | python - <= cls >= 0, f'incorrect class index {cls}' 74 | 75 | # Write YOLO label 76 | if id not in shapes: 77 | shapes[id] = Image.open(file).size 78 | box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True) 79 | with open((labels / id).with_suffix('.txt'), 'a') as f: 80 | f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt 81 | except Exception as e: 82 | print(f'WARNING: skipping one label for {file}: {e}') 83 | 84 | 85 | # Download manually from https://challenge.xviewdataset.org 86 | dir = Path(yaml['path']) # dataset root dir 87 | # urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip', # train labels 88 | # 'https://d307kc0mrhucc3.cloudfront.net/train_images.zip', # 15G, 847 train images 89 | # 'https://d307kc0mrhucc3.cloudfront.net/val_images.zip'] # 5G, 282 val images (no labels) 90 | # download(urls, dir=dir, delete=False) 91 | 92 | # Convert labels 93 | convert_labels(dir / 'xView_train.geojson') 94 | 95 | # Move images 96 | images = Path(dir / 'images') 97 | images.mkdir(parents=True, exist_ok=True) 98 | Path(dir / 'train_images').rename(dir / 'images' / 'train') 99 | Path(dir / 'val_images').rename(dir / 'images' / 'val') 100 | 101 | # Split 102 | autosplit(dir / 'images' / 'train') 103 | -------------------------------------------------------------------------------- /export.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Export a PyTorch model to TorchScript, ONNX, CoreML formats 4 | 5 | Usage: 6 | $ python path/to/export.py --weights yolov5s.pt --img 640 --batch 1 7 | """ 8 | 9 | import argparse 10 | import sys 11 | import time 12 | from pathlib import Path 13 | 14 | import torch 15 | import torch.nn as nn 16 | from torch.utils.mobile_optimizer import optimize_for_mobile 17 | 18 | FILE = Path(__file__).absolute() 19 | sys.path.append(FILE.parents[0].as_posix()) # add yolov5/ to path 20 | 21 | from models.common import Conv 22 | from models.yolo import Detect 23 | from models.experimental import attempt_load 24 | from utils.activations import Hardswish, SiLU 25 | from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging 26 | from utils.torch_utils import select_device 27 | 28 | 29 | def export_torchscript(model, img, file, optimize): 30 | # TorchScript model export 31 | prefix = colorstr('TorchScript:') 32 | try: 33 | print(f'\n{prefix} starting export with torch {torch.__version__}...') 34 | f = file.with_suffix('.torchscript.pt') 35 | ts = torch.jit.trace(model, img, strict=False) 36 | (optimize_for_mobile(ts) if optimize else ts).save(f) 37 | print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') 38 | return ts 39 | except Exception as e: 40 | print(f'{prefix} export failure: {e}') 41 | 42 | 43 | def export_onnx(model, img, file, opset, train, dynamic, simplify): 44 | # ONNX model export 45 | prefix = colorstr('ONNX:') 46 | try: 47 | check_requirements(('onnx', 'onnx-simplifier')) 48 | import onnx 49 | 50 | print(f'\n{prefix} starting export with onnx {onnx.__version__}...') 51 | f = file.with_suffix('.onnx') 52 | torch.onnx.export(model, img, f, verbose=False, opset_version=opset, 53 | training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL, 54 | do_constant_folding=not train, 55 | input_names=['images'], 56 | output_names=['output'], 57 | dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640) 58 | 'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85) 59 | } if dynamic else None) 60 | 61 | # Checks 62 | model_onnx = onnx.load(f) # load onnx model 63 | onnx.checker.check_model(model_onnx) # check onnx model 64 | # print(onnx.helper.printable_graph(model_onnx.graph)) # print 65 | 66 | # Simplify 67 | if simplify: 68 | try: 69 | import onnxsim 70 | 71 | print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') 72 | model_onnx, check = onnxsim.simplify( 73 | model_onnx, 74 | dynamic_input_shape=dynamic, 75 | input_shapes={'images': list(img.shape)} if dynamic else None) 76 | assert check, 'assert check failed' 77 | onnx.save(model_onnx, f) 78 | except Exception as e: 79 | print(f'{prefix} simplifier failure: {e}') 80 | print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') 81 | print(f"{prefix} run --dynamic ONNX model inference with: 'python detect.py --weights {f}'") 82 | except Exception as e: 83 | print(f'{prefix} export failure: {e}') 84 | 85 | 86 | def export_coreml(model, img, file): 87 | # CoreML model export 88 | prefix = colorstr('CoreML:') 89 | try: 90 | check_requirements(('coremltools',)) 91 | import coremltools as ct 92 | 93 | print(f'\n{prefix} starting export with coremltools {ct.__version__}...') 94 | f = file.with_suffix('.mlmodel') 95 | model.train() # CoreML exports should be placed in model.train() mode 96 | ts = torch.jit.trace(model, img, strict=False) # TorchScript model 97 | model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])]) 98 | model.save(f) 99 | print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') 100 | except Exception as e: 101 | print(f'\n{prefix} export failure: {e}') 102 | 103 | 104 | def run(weights='./yolov5s.pt', # weights path 105 | img_size=(640, 640), # image (height, width) 106 | batch_size=1, # batch size 107 | device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu 108 | include=('torchscript', 'onnx', 'coreml'), # include formats 109 | half=False, # FP16 half-precision export 110 | inplace=False, # set YOLOv5 Detect() inplace=True 111 | train=False, # model.train() mode 112 | optimize=False, # TorchScript: optimize for mobile 113 | dynamic=False, # ONNX: dynamic axes 114 | simplify=False, # ONNX: simplify model 115 | opset=12, # ONNX: opset version 116 | ): 117 | t = time.time() 118 | include = [x.lower() for x in include] 119 | img_size *= 2 if len(img_size) == 1 else 1 # expand 120 | file = Path(weights) 121 | 122 | # Load PyTorch model 123 | device = select_device(device) 124 | assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0' 125 | model = attempt_load(weights, map_location=device) # load FP32 model 126 | names = model.names 127 | 128 | # Input 129 | gs = int(max(model.stride)) # grid size (max stride) 130 | img_size = [check_img_size(x, gs) for x in img_size] # verify img_size are gs-multiples 131 | img = torch.zeros(batch_size, 3, *img_size).to(device) # image size(1,3,320,192) iDetection 132 | 133 | # Update model 134 | if half: 135 | img, model = img.half(), model.half() # to FP16 136 | model.train() if train else model.eval() # training mode = no Detect() layer grid construction 137 | for k, m in model.named_modules(): 138 | if isinstance(m, Conv): # assign export-friendly activations 139 | if isinstance(m.act, nn.Hardswish): 140 | m.act = Hardswish() 141 | elif isinstance(m.act, nn.SiLU): 142 | m.act = SiLU() 143 | elif isinstance(m, Detect): 144 | m.inplace = inplace 145 | m.onnx_dynamic = dynamic 146 | # m.forward = m.forward_export # assign forward (optional) 147 | 148 | for _ in range(2): 149 | y = model(img) # dry runs 150 | print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)") 151 | 152 | # Exports 153 | if 'torchscript' in include: 154 | export_torchscript(model, img, file, optimize) 155 | if 'onnx' in include: 156 | export_onnx(model, img, file, opset, train, dynamic, simplify) 157 | if 'coreml' in include: 158 | export_coreml(model, img, file) 159 | 160 | # Finish 161 | print(f'\nExport complete ({time.time() - t:.2f}s)' 162 | f"\nResults saved to {colorstr('bold', file.parent.resolve())}" 163 | f'\nVisualize with https://netron.app') 164 | 165 | 166 | def parse_opt(): 167 | parser = argparse.ArgumentParser() 168 | parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path') 169 | parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image (height, width)') 170 | parser.add_argument('--batch-size', type=int, default=1, help='batch size') 171 | parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') 172 | parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats') 173 | parser.add_argument('--half', action='store_true', help='FP16 half-precision export') 174 | parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') 175 | parser.add_argument('--train', action='store_true', help='model.train() mode') 176 | parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile') 177 | parser.add_argument('--dynamic', action='store_true', help='ONNX: dynamic axes') 178 | parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model') 179 | parser.add_argument('--opset', type=int, default=13, help='ONNX: opset version') 180 | opt = parser.parse_args() 181 | return opt 182 | 183 | 184 | def main(opt): 185 | set_logging() 186 | print(colorstr('export: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items())) 187 | run(**vars(opt)) 188 | 189 | 190 | if __name__ == "__main__": 191 | opt = parse_opt() 192 | main(opt) 193 | -------------------------------------------------------------------------------- /hubconf.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/ 4 | 5 | Usage: 6 | import torch 7 | model = torch.hub.load('ultralytics/yolov5', 'yolov5s') 8 | """ 9 | 10 | import torch 11 | 12 | 13 | def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 14 | """Creates a specified YOLOv5 model 15 | 16 | Arguments: 17 | name (str): name of model, i.e. 'yolov5s' 18 | pretrained (bool): load pretrained weights into the model 19 | channels (int): number of input channels 20 | classes (int): number of model classes 21 | autoshape (bool): apply YOLOv5 .autoshape() wrapper to model 22 | verbose (bool): print all information to screen 23 | device (str, torch.device, None): device to use for model parameters 24 | 25 | Returns: 26 | YOLOv5 pytorch model 27 | """ 28 | from pathlib import Path 29 | 30 | from models.yolo import Model 31 | from models.experimental import attempt_load 32 | from utils.general import check_requirements, set_logging 33 | from utils.downloads import attempt_download 34 | from utils.torch_utils import select_device 35 | 36 | file = Path(__file__).absolute() 37 | check_requirements(requirements=file.parent / 'requirements.txt', exclude=('tensorboard', 'thop', 'opencv-python')) 38 | set_logging(verbose=verbose) 39 | 40 | save_dir = Path('') if str(name).endswith('.pt') else file.parent 41 | path = (save_dir / name).with_suffix('.pt') # checkpoint path 42 | try: 43 | device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device) 44 | 45 | if pretrained and channels == 3 and classes == 80: 46 | model = attempt_load(path, map_location=device) # download/load FP32 model 47 | else: 48 | cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path 49 | model = Model(cfg, channels, classes) # create model 50 | if pretrained: 51 | ckpt = torch.load(attempt_download(path), map_location=device) # load 52 | msd = model.state_dict() # model state_dict 53 | csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 54 | csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter 55 | model.load_state_dict(csd, strict=False) # load 56 | if len(ckpt['model'].names) == classes: 57 | model.names = ckpt['model'].names # set class names attribute 58 | if autoshape: 59 | model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS 60 | return model.to(device) 61 | 62 | except Exception as e: 63 | help_url = 'https://github.com/ultralytics/yolov5/issues/36' 64 | s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url 65 | raise Exception(s) from e 66 | 67 | 68 | def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None): 69 | # YOLOv5 custom or local model 70 | return _create(path, autoshape=autoshape, verbose=verbose, device=device) 71 | 72 | 73 | def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 74 | # YOLOv5-small model https://github.com/ultralytics/yolov5 75 | return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device) 76 | 77 | 78 | def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 79 | # YOLOv5-medium model https://github.com/ultralytics/yolov5 80 | return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device) 81 | 82 | 83 | def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 84 | # YOLOv5-large model https://github.com/ultralytics/yolov5 85 | return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device) 86 | 87 | 88 | def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 89 | # YOLOv5-xlarge model https://github.com/ultralytics/yolov5 90 | return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device) 91 | 92 | 93 | def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 94 | # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5 95 | return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device) 96 | 97 | 98 | def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 99 | # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5 100 | return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device) 101 | 102 | 103 | def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 104 | # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5 105 | return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device) 106 | 107 | 108 | def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 109 | # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5 110 | return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device) 111 | 112 | 113 | if __name__ == '__main__': 114 | model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained 115 | # model = custom(path='path/to/model.pt') # custom 116 | 117 | # Verify inference 118 | import cv2 119 | import numpy as np 120 | from PIL import Image 121 | from pathlib import Path 122 | 123 | imgs = ['data/images/zidane.jpg', # filename 124 | Path('data/images/zidane.jpg'), # Path 125 | 'https://ultralytics.com/images/zidane.jpg', # URI 126 | cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV 127 | Image.open('data/images/bus.jpg'), # PIL 128 | np.zeros((320, 640, 3))] # numpy 129 | 130 | results = model(imgs) # batched inference 131 | results.print() 132 | results.save() 133 | -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/models/__init__.py -------------------------------------------------------------------------------- /models/experimental.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Experimental modules 4 | """ 5 | 6 | import numpy as np 7 | import torch 8 | import torch.nn as nn 9 | 10 | from models.common import Conv 11 | from utils.downloads import attempt_download 12 | 13 | 14 | class CrossConv(nn.Module): 15 | # Cross Convolution Downsample 16 | def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): 17 | # ch_in, ch_out, kernel, stride, groups, expansion, shortcut 18 | super().__init__() 19 | c_ = int(c2 * e) # hidden channels 20 | self.cv1 = Conv(c1, c_, (1, k), (1, s)) 21 | self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) 22 | self.add = shortcut and c1 == c2 23 | 24 | def forward(self, x): 25 | return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) 26 | 27 | 28 | class Sum(nn.Module): 29 | # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 30 | def __init__(self, n, weight=False): # n: number of inputs 31 | super().__init__() 32 | self.weight = weight # apply weights boolean 33 | self.iter = range(n - 1) # iter object 34 | if weight: 35 | self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights 36 | 37 | def forward(self, x): 38 | y = x[0] # no weight 39 | if self.weight: 40 | w = torch.sigmoid(self.w) * 2 41 | for i in self.iter: 42 | y = y + x[i + 1] * w[i] 43 | else: 44 | for i in self.iter: 45 | y = y + x[i + 1] 46 | return y 47 | 48 | 49 | class MixConv2d(nn.Module): 50 | # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595 51 | def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): 52 | super().__init__() 53 | groups = len(k) 54 | if equal_ch: # equal c_ per group 55 | i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices 56 | c_ = [(i == g).sum() for g in range(groups)] # intermediate channels 57 | else: # equal weight.numel() per group 58 | b = [c2] + [0] * groups 59 | a = np.eye(groups + 1, groups, k=-1) 60 | a -= np.roll(a, 1, axis=1) 61 | a *= np.array(k) ** 2 62 | a[0] = 1 63 | c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b 64 | 65 | self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)]) 66 | self.bn = nn.BatchNorm2d(c2) 67 | self.act = nn.LeakyReLU(0.1, inplace=True) 68 | 69 | def forward(self, x): 70 | return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1))) 71 | 72 | 73 | class Ensemble(nn.ModuleList): 74 | # Ensemble of models 75 | def __init__(self): 76 | super().__init__() 77 | 78 | def forward(self, x, augment=False, profile=False, visualize=False): 79 | y = [] 80 | for module in self: 81 | y.append(module(x, augment, profile, visualize)[0]) 82 | # y = torch.stack(y).max(0)[0] # max ensemble 83 | # y = torch.stack(y).mean(0) # mean ensemble 84 | y = torch.cat(y, 1) # nms ensemble 85 | return y, None # inference, train output 86 | 87 | 88 | def attempt_load(weights, map_location=None, inplace=True, fuse=True): 89 | from models.yolo import Detect, Model 90 | 91 | # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a 92 | model = Ensemble() 93 | for w in weights if isinstance(weights, list) else [weights]: 94 | ckpt = torch.load(attempt_download(w), map_location=map_location) # load 95 | if fuse: 96 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model 97 | else: 98 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse 99 | 100 | 101 | # Compatibility updates 102 | for m in model.modules(): 103 | if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]: 104 | m.inplace = inplace # pytorch 1.7.0 compatibility 105 | elif type(m) is Conv: 106 | m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility 107 | 108 | if len(model) == 1: 109 | return model[-1] # return model 110 | else: 111 | print(f'Ensemble created with {weights}\n') 112 | for k in ['names']: 113 | setattr(model, k, getattr(model[-1], k)) 114 | model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride 115 | return model # return ensemble 116 | -------------------------------------------------------------------------------- /models/hub/anchors.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Default anchors for COCO data 3 | 4 | 5 | # P5 ------------------------------------------------------------------------------------------------------------------- 6 | # P5-640: 7 | anchors_p5_640: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | 13 | # P6 ------------------------------------------------------------------------------------------------------------------- 14 | # P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387 15 | anchors_p6_640: 16 | - [9,11, 21,19, 17,41] # P3/8 17 | - [43,32, 39,70, 86,64] # P4/16 18 | - [65,131, 134,130, 120,265] # P5/32 19 | - [282,180, 247,354, 512,387] # P6/64 20 | 21 | # P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792 22 | anchors_p6_1280: 23 | - [19,27, 44,40, 38,94] # P3/8 24 | - [96,68, 86,152, 180,137] # P4/16 25 | - [140,301, 303,264, 238,542] # P5/32 26 | - [436,615, 739,380, 925,792] # P6/64 27 | 28 | # P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187 29 | anchors_p6_1920: 30 | - [28,41, 67,59, 57,141] # P3/8 31 | - [144,103, 129,227, 270,205] # P4/16 32 | - [209,452, 455,396, 358,812] # P5/32 33 | - [653,922, 1109,570, 1387,1187] # P6/64 34 | 35 | 36 | # P7 ------------------------------------------------------------------------------------------------------------------- 37 | # P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372 38 | anchors_p7_640: 39 | - [11,11, 13,30, 29,20] # P3/8 40 | - [30,46, 61,38, 39,92] # P4/16 41 | - [78,80, 146,66, 79,163] # P5/32 42 | - [149,150, 321,143, 157,303] # P6/64 43 | - [257,402, 359,290, 524,372] # P7/128 44 | 45 | # P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818 46 | anchors_p7_1280: 47 | - [19,22, 54,36, 32,77] # P3/8 48 | - [70,83, 138,71, 75,173] # P4/16 49 | - [165,159, 148,334, 375,151] # P5/32 50 | - [334,317, 251,626, 499,474] # P6/64 51 | - [750,326, 534,814, 1079,818] # P7/128 52 | 53 | # P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227 54 | anchors_p7_1920: 55 | - [29,34, 81,55, 47,115] # P3/8 56 | - [105,124, 207,107, 113,259] # P4/16 57 | - [247,238, 222,500, 563,227] # P5/32 58 | - [501,476, 376,939, 749,711] # P6/64 59 | - [1126,489, 801,1222, 1618,1227] # P7/128 60 | -------------------------------------------------------------------------------- /models/hub/yolov3-spp.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # darknet53 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, Bottleneck, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, Bottleneck, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, Bottleneck, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, Bottleneck, [1024]], # 10 26 | ] 27 | 28 | # YOLOv3-SPP head 29 | head: 30 | [[-1, 1, Bottleneck, [1024, False]], 31 | [-1, 1, SPP, [512, [5, 9, 13]]], 32 | [-1, 1, Conv, [1024, 3, 1]], 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 35 | 36 | [-2, 1, Conv, [256, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 39 | [-1, 1, Bottleneck, [512, False]], 40 | [-1, 1, Bottleneck, [512, False]], 41 | [-1, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 43 | 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 46 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 47 | [-1, 1, Bottleneck, [256, False]], 48 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 49 | 50 | [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 51 | ] 52 | -------------------------------------------------------------------------------- /models/hub/yolov3-tiny.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,14, 23,27, 37,58] # P4/16 9 | - [81,82, 135,169, 344,319] # P5/32 10 | 11 | # YOLOv3-tiny backbone 12 | backbone: 13 | # [from, number, module, args] 14 | [[-1, 1, Conv, [16, 3, 1]], # 0 15 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2 16 | [-1, 1, Conv, [32, 3, 1]], 17 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4 18 | [-1, 1, Conv, [64, 3, 1]], 19 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8 20 | [-1, 1, Conv, [128, 3, 1]], 21 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16 22 | [-1, 1, Conv, [256, 3, 1]], 23 | [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32 24 | [-1, 1, Conv, [512, 3, 1]], 25 | [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11 26 | [-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12 27 | ] 28 | 29 | # YOLOv3-tiny head 30 | head: 31 | [[-1, 1, Conv, [1024, 3, 1]], 32 | [-1, 1, Conv, [256, 1, 1]], 33 | [-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large) 34 | 35 | [-2, 1, Conv, [128, 1, 1]], 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 38 | [-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium) 39 | 40 | [[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5) 41 | ] 42 | -------------------------------------------------------------------------------- /models/hub/yolov3.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # darknet53 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [32, 3, 1]], # 0 16 | [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 17 | [-1, 1, Bottleneck, [64]], 18 | [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 19 | [-1, 2, Bottleneck, [128]], 20 | [-1, 1, Conv, [256, 3, 2]], # 5-P3/8 21 | [-1, 8, Bottleneck, [256]], 22 | [-1, 1, Conv, [512, 3, 2]], # 7-P4/16 23 | [-1, 8, Bottleneck, [512]], 24 | [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32 25 | [-1, 4, Bottleneck, [1024]], # 10 26 | ] 27 | 28 | # YOLOv3 head 29 | head: 30 | [[-1, 1, Bottleneck, [1024, False]], 31 | [-1, 1, Conv, [512, [1, 1]]], 32 | [-1, 1, Conv, [1024, 3, 1]], 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large) 35 | 36 | [-2, 1, Conv, [256, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 8], 1, Concat, [1]], # cat backbone P4 39 | [-1, 1, Bottleneck, [512, False]], 40 | [-1, 1, Bottleneck, [512, False]], 41 | [-1, 1, Conv, [256, 1, 1]], 42 | [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium) 43 | 44 | [-2, 1, Conv, [128, 1, 1]], 45 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 46 | [[-1, 6], 1, Concat, [1]], # cat backbone P3 47 | [-1, 1, Bottleneck, [256, False]], 48 | [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small) 49 | 50 | [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 51 | ] 52 | -------------------------------------------------------------------------------- /models/hub/yolov5-bifpn.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]] 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 BiFPN head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14, 6], 1, Concat, [1]], # cat P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5-fpn.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, Bottleneck, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, BottleneckCSP, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, BottleneckCSP, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 6, BottleneckCSP, [1024]], # 9 25 | ] 26 | 27 | # YOLOv5 FPN head 28 | head: 29 | [[-1, 3, BottleneckCSP, [1024, False]], # 10 (P5/32-large) 30 | 31 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 32 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 3, BottleneckCSP, [512, False]], # 14 (P4/16-medium) 35 | 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 3, BottleneckCSP, [256, False]], # 18 (P3/8-small) 40 | 41 | [[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 42 | ] 43 | -------------------------------------------------------------------------------- /models/hub/yolov5-p2.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 8 | 9 | # YOLOv5 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 9, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 20 | [-1, 1, SPP, [1024, [5, 9, 13]]], 21 | [-1, 3, C3, [1024, False]], # 9 22 | ] 23 | 24 | # YOLOv5 head 25 | head: 26 | [[-1, 1, Conv, [512, 1, 1]], 27 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 28 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 29 | [-1, 3, C3, [512, False]], # 13 30 | 31 | [-1, 1, Conv, [256, 1, 1]], 32 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 33 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 34 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 35 | 36 | [-1, 1, Conv, [128, 1, 1]], 37 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 38 | [[-1, 2], 1, Concat, [1]], # cat backbone P2 39 | [-1, 1, C3, [128, False]], # 21 (P2/4-xsmall) 40 | 41 | [-1, 1, Conv, [128, 3, 2]], 42 | [[-1, 18], 1, Concat, [1]], # cat head P3 43 | [-1, 3, C3, [256, False]], # 24 (P3/8-small) 44 | 45 | [-1, 1, Conv, [256, 3, 2]], 46 | [[-1, 14], 1, Concat, [1]], # cat head P4 47 | [-1, 3, C3, [512, False]], # 27 (P4/16-medium) 48 | 49 | [-1, 1, Conv, [512, 3, 2]], 50 | [[-1, 10], 1, Concat, [1]], # cat head P5 51 | [-1, 3, C3, [1024, False]], # 30 (P5/32-large) 52 | 53 | [[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5) 54 | ] 55 | -------------------------------------------------------------------------------- /models/hub/yolov5-p6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 8 | 9 | # YOLOv5 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 9, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 20 | [-1, 3, C3, [768]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 22 | [-1, 1, SPP, [1024, [3, 5, 7]]], 23 | [-1, 3, C3, [1024, False]], # 11 24 | ] 25 | 26 | # YOLOv5 head 27 | head: 28 | [[-1, 1, Conv, [768, 1, 1]], 29 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 30 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 31 | [-1, 3, C3, [768, False]], # 15 32 | 33 | [-1, 1, Conv, [512, 1, 1]], 34 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 35 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 36 | [-1, 3, C3, [512, False]], # 19 37 | 38 | [-1, 1, Conv, [256, 1, 1]], 39 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 40 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 41 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 42 | 43 | [-1, 1, Conv, [256, 3, 2]], 44 | [[-1, 20], 1, Concat, [1]], # cat head P4 45 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 46 | 47 | [-1, 1, Conv, [512, 3, 2]], 48 | [[-1, 16], 1, Concat, [1]], # cat head P5 49 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 50 | 51 | [-1, 1, Conv, [768, 3, 2]], 52 | [[-1, 12], 1, Concat, [1]], # cat head P6 53 | [-1, 3, C3, [1024, False]], # 32 (P5/64-xlarge) 54 | 55 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 56 | ] 57 | -------------------------------------------------------------------------------- /models/hub/yolov5-p7.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 3 8 | 9 | # YOLOv5 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 13 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 14 | [-1, 3, C3, [128]], 15 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 16 | [-1, 9, C3, [256]], 17 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 18 | [-1, 9, C3, [512]], 19 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 20 | [-1, 3, C3, [768]], 21 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 22 | [-1, 3, C3, [1024]], 23 | [-1, 1, Conv, [1280, 3, 2]], # 11-P7/128 24 | [-1, 1, SPP, [1280, [3, 5]]], 25 | [-1, 3, C3, [1280, False]], # 13 26 | ] 27 | 28 | # YOLOv5 head 29 | head: 30 | [[-1, 1, Conv, [1024, 1, 1]], 31 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 32 | [[-1, 10], 1, Concat, [1]], # cat backbone P6 33 | [-1, 3, C3, [1024, False]], # 17 34 | 35 | [-1, 1, Conv, [768, 1, 1]], 36 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 37 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 38 | [-1, 3, C3, [768, False]], # 21 39 | 40 | [-1, 1, Conv, [512, 1, 1]], 41 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 42 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 43 | [-1, 3, C3, [512, False]], # 25 44 | 45 | [-1, 1, Conv, [256, 1, 1]], 46 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 47 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 48 | [-1, 3, C3, [256, False]], # 29 (P3/8-small) 49 | 50 | [-1, 1, Conv, [256, 3, 2]], 51 | [[-1, 26], 1, Concat, [1]], # cat head P4 52 | [-1, 3, C3, [512, False]], # 32 (P4/16-medium) 53 | 54 | [-1, 1, Conv, [512, 3, 2]], 55 | [[-1, 22], 1, Concat, [1]], # cat head P5 56 | [-1, 3, C3, [768, False]], # 35 (P5/32-large) 57 | 58 | [-1, 1, Conv, [768, 3, 2]], 59 | [[-1, 18], 1, Concat, [1]], # cat head P6 60 | [-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge) 61 | 62 | [-1, 1, Conv, [1024, 3, 2]], 63 | [[-1, 14], 1, Concat, [1]], # cat head P7 64 | [-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge) 65 | 66 | [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7) 67 | ] 68 | -------------------------------------------------------------------------------- /models/hub/yolov5-panet.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, BottleneckCSP, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, BottleneckCSP, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, BottleneckCSP, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, BottleneckCSP, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 PANet head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, BottleneckCSP, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5l6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [19,27, 44,40, 38,94] # P3/8 9 | - [96,68, 86,152, 180,137] # P4/16 10 | - [140,301, 303,264, 238,542] # P5/32 11 | - [436,615, 739,380, 925,792] # P6/64 12 | 13 | # YOLOv5 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 9, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 1, SPP, [1024, [3, 5, 7]]], 27 | [-1, 3, C3, [1024, False]], # 11 28 | ] 29 | 30 | # YOLOv5 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5m6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.67 # model depth multiple 6 | width_multiple: 0.75 # layer channel multiple 7 | anchors: 8 | - [19,27, 44,40, 38,94] # P3/8 9 | - [96,68, 86,152, 180,137] # P4/16 10 | - [140,301, 303,264, 238,542] # P5/32 11 | - [436,615, 739,380, 925,792] # P6/64 12 | 13 | # YOLOv5 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 9, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 1, SPP, [1024, [3, 5, 7]]], 27 | [-1, 3, C3, [1024, False]], # 11 28 | ] 29 | 30 | # YOLOv5 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5s-ghost.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3Ghost, [128]], 18 | [-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3Ghost, [256]], 20 | [-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3Ghost, [512]], 22 | [-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3Ghost, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, GhostConv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3Ghost, [512, False]], # 13 33 | 34 | [-1, 1, GhostConv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, GhostConv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, GhostConv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5s-transformer.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3TR, [1024, False]], # 9 <-------- C3TR() Transformer module 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/hub/yolov5s6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 7 | anchors: 8 | - [19,27, 44,40, 38,94] # P3/8 9 | - [96,68, 86,152, 180,137] # P4/16 10 | - [140,301, 303,264, 238,542] # P5/32 11 | - [436,615, 739,380, 925,792] # P6/64 12 | 13 | # YOLOv5 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 9, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 1, SPP, [1024, [3, 5, 7]]], 27 | [-1, 3, C3, [1024, False]], # 11 28 | ] 29 | 30 | # YOLOv5 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/hub/yolov5x6.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.33 # model depth multiple 6 | width_multiple: 1.25 # layer channel multiple 7 | anchors: 8 | - [19,27, 44,40, 38,94] # P3/8 9 | - [96,68, 86,152, 180,137] # P4/16 10 | - [140,301, 303,264, 238,542] # P5/32 11 | - [436,615, 739,380, 925,792] # P6/64 12 | 13 | # YOLOv5 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 17 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 18 | [-1, 3, C3, [128]], 19 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 20 | [-1, 9, C3, [256]], 21 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 22 | [-1, 9, C3, [512]], 23 | [-1, 1, Conv, [768, 3, 2]], # 7-P5/32 24 | [-1, 3, C3, [768]], 25 | [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64 26 | [-1, 1, SPP, [1024, [3, 5, 7]]], 27 | [-1, 3, C3, [1024, False]], # 11 28 | ] 29 | 30 | # YOLOv5 head 31 | head: 32 | [[-1, 1, Conv, [768, 1, 1]], 33 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 34 | [[-1, 8], 1, Concat, [1]], # cat backbone P5 35 | [-1, 3, C3, [768, False]], # 15 36 | 37 | [-1, 1, Conv, [512, 1, 1]], 38 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 39 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 40 | [-1, 3, C3, [512, False]], # 19 41 | 42 | [-1, 1, Conv, [256, 1, 1]], 43 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 44 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 45 | [-1, 3, C3, [256, False]], # 23 (P3/8-small) 46 | 47 | [-1, 1, Conv, [256, 3, 2]], 48 | [[-1, 20], 1, Concat, [1]], # cat head P4 49 | [-1, 3, C3, [512, False]], # 26 (P4/16-medium) 50 | 51 | [-1, 1, Conv, [512, 3, 2]], 52 | [[-1, 16], 1, Concat, [1]], # cat head P5 53 | [-1, 3, C3, [768, False]], # 29 (P5/32-large) 54 | 55 | [-1, 1, Conv, [768, 3, 2]], 56 | [[-1, 12], 1, Concat, [1]], # cat head P6 57 | [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge) 58 | 59 | [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6) 60 | ] 61 | -------------------------------------------------------------------------------- /models/yolo.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | YOLO-specific modules 4 | 5 | Usage: 6 | $ python path/to/models/yolo.py --cfg yolov5s.yaml 7 | """ 8 | 9 | import argparse 10 | import sys 11 | from copy import deepcopy 12 | from pathlib import Path 13 | 14 | FILE = Path(__file__).absolute() 15 | sys.path.append(FILE.parents[1].as_posix()) # add yolov5/ to path 16 | 17 | from models.common import * 18 | from models.experimental import * 19 | from utils.autoanchor import check_anchor_order 20 | from utils.general import make_divisible, check_file, set_logging 21 | from utils.plots import feature_visualization 22 | from utils.torch_utils import time_sync, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \ 23 | select_device, copy_attr 24 | 25 | try: 26 | import thop # for FLOPs computation 27 | except ImportError: 28 | thop = None 29 | 30 | LOGGER = logging.getLogger(__name__) 31 | 32 | 33 | class Detect(nn.Module): 34 | stride = None # strides computed during build 35 | onnx_dynamic = False # ONNX export parameter 36 | 37 | def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer 38 | super().__init__() 39 | self.nc = nc # number of classes 40 | self.no = nc + 5 # number of outputs per anchor 41 | self.nl = len(anchors) # number of detection layers 42 | self.na = len(anchors[0]) // 2 # number of anchors 43 | self.grid = [torch.zeros(1)] * self.nl # init grid 44 | a = torch.tensor(anchors).float().view(self.nl, -1, 2) 45 | self.register_buffer('anchors', a) # shape(nl,na,2) 46 | self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2) 47 | self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv 48 | self.inplace = inplace # use in-place ops (e.g. slice assignment) 49 | 50 | def forward(self, x): 51 | z = [] # inference output 52 | for i in range(self.nl): 53 | x[i] = self.m[i](x[i]) # conv 54 | bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85) 55 | x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous() 56 | 57 | if not self.training: # inference 58 | if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic: 59 | self.grid[i] = self._make_grid(nx, ny).to(x[i].device) 60 | 61 | y = x[i].sigmoid() 62 | if self.inplace: 63 | y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy 64 | y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh 65 | else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953 66 | xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy 67 | wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh 68 | y = torch.cat((xy, wh, y[..., 4:]), -1) 69 | z.append(y.view(bs, -1, self.no)) 70 | 71 | return x if self.training else (torch.cat(z, 1), x) 72 | 73 | @staticmethod 74 | def _make_grid(nx=20, ny=20): 75 | yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)]) 76 | return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float() 77 | 78 | 79 | class Model(nn.Module): 80 | def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes 81 | super().__init__() 82 | if isinstance(cfg, dict): 83 | self.yaml = cfg # model dict 84 | else: # is *.yaml 85 | import yaml # for torch hub 86 | self.yaml_file = Path(cfg).name 87 | with open(cfg) as f: 88 | self.yaml = yaml.safe_load(f) # model dict 89 | 90 | # Define model 91 | ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels 92 | if nc and nc != self.yaml['nc']: 93 | LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}") 94 | self.yaml['nc'] = nc # override yaml value 95 | if anchors: 96 | LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}') 97 | self.yaml['anchors'] = round(anchors) # override yaml value 98 | self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist 99 | self.names = [str(i) for i in range(self.yaml['nc'])] # default names 100 | self.inplace = self.yaml.get('inplace', True) 101 | # LOGGER.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))]) 102 | 103 | # Build strides, anchors 104 | m = self.model[-1] # Detect() 105 | if isinstance(m, Detect): 106 | s = 256 # 2x min stride 107 | m.inplace = self.inplace 108 | m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward 109 | m.anchors /= m.stride.view(-1, 1, 1) 110 | check_anchor_order(m) 111 | self.stride = m.stride 112 | self._initialize_biases() # only run once 113 | # LOGGER.info('Strides: %s' % m.stride.tolist()) 114 | 115 | # Init weights, biases 116 | initialize_weights(self) 117 | self.info() 118 | LOGGER.info('') 119 | 120 | def forward(self, x, augment=False, profile=False, visualize=False): 121 | if augment: 122 | return self.forward_augment(x) # augmented inference, None 123 | return self.forward_once(x, profile, visualize) # single-scale inference, train 124 | 125 | def forward_augment(self, x): 126 | img_size = x.shape[-2:] # height, width 127 | s = [1, 0.83, 0.67] # scales 128 | f = [None, 3, None] # flips (2-ud, 3-lr) 129 | y = [] # outputs 130 | for si, fi in zip(s, f): 131 | xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max())) 132 | yi = self.forward_once(xi)[0] # forward 133 | # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save 134 | yi = self._descale_pred(yi, fi, si, img_size) 135 | y.append(yi) 136 | return torch.cat(y, 1), None # augmented inference, train 137 | 138 | def forward_once(self, x, profile=False, visualize=False): 139 | y, dt = [], [] # outputs 140 | for m in self.model: 141 | if m.f != -1: # if not from previous layer 142 | x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers 143 | 144 | if profile: 145 | c = isinstance(m, Detect) # copy input as inplace fix 146 | o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs 147 | t = time_sync() 148 | for _ in range(10): 149 | m(x.copy() if c else x) 150 | dt.append((time_sync() - t) * 100) 151 | if m == self.model[0]: 152 | LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}") 153 | LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}') 154 | 155 | x = m(x) # run 156 | y.append(x if m.i in self.save else None) # save output 157 | 158 | if visualize: 159 | feature_visualization(x, m.type, m.i, save_dir=visualize) 160 | 161 | if profile: 162 | LOGGER.info('%.1fms total' % sum(dt)) 163 | return x 164 | 165 | def _descale_pred(self, p, flips, scale, img_size): 166 | # de-scale predictions following augmented inference (inverse operation) 167 | if self.inplace: 168 | p[..., :4] /= scale # de-scale 169 | if flips == 2: 170 | p[..., 1] = img_size[0] - p[..., 1] # de-flip ud 171 | elif flips == 3: 172 | p[..., 0] = img_size[1] - p[..., 0] # de-flip lr 173 | else: 174 | x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale 175 | if flips == 2: 176 | y = img_size[0] - y # de-flip ud 177 | elif flips == 3: 178 | x = img_size[1] - x # de-flip lr 179 | p = torch.cat((x, y, wh, p[..., 4:]), -1) 180 | return p 181 | 182 | def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency 183 | # https://arxiv.org/abs/1708.02002 section 3.3 184 | # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1. 185 | m = self.model[-1] # Detect() module 186 | for mi, s in zip(m.m, m.stride): # from 187 | b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85) 188 | b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image) 189 | b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls 190 | mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True) 191 | 192 | def _print_biases(self): 193 | m = self.model[-1] # Detect() module 194 | for mi in m.m: # from 195 | b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85) 196 | LOGGER.info( 197 | ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean())) 198 | 199 | # def _print_weights(self): 200 | # for m in self.model.modules(): 201 | # if type(m) is Bottleneck: 202 | # LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights 203 | 204 | def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers 205 | LOGGER.info('Fusing layers... ') 206 | for m in self.model.modules(): 207 | if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'): 208 | m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv 209 | delattr(m, 'bn') # remove batchnorm 210 | m.forward = m.forward_fuse # update forward 211 | self.info() 212 | return self 213 | 214 | def autoshape(self): # add AutoShape module 215 | LOGGER.info('Adding AutoShape... ') 216 | m = AutoShape(self) # wrap model 217 | copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes 218 | return m 219 | 220 | def info(self, verbose=False, img_size=640): # print model information 221 | model_info(self, verbose, img_size) 222 | 223 | 224 | def parse_model(d, ch): # model_dict, input_channels(3) 225 | LOGGER.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments')) 226 | anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] 227 | na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors 228 | no = na * (nc + 5) # number of outputs = anchors * (classes + 5) 229 | 230 | layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out 231 | for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args 232 | m = eval(m) if isinstance(m, str) else m # eval strings 233 | for j, a in enumerate(args): 234 | try: 235 | args[j] = eval(a) if isinstance(a, str) else a # eval strings 236 | except: 237 | pass 238 | 239 | n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain 240 | if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, 241 | BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]: 242 | c1, c2 = ch[f], args[0] 243 | if c2 != no: # if not output 244 | c2 = make_divisible(c2 * gw, 8) 245 | 246 | args = [c1, c2, *args[1:]] 247 | if m in [BottleneckCSP, C3, C3TR, C3Ghost]: 248 | args.insert(2, n) # number of repeats 249 | n = 1 250 | elif m is nn.BatchNorm2d: 251 | args = [ch[f]] 252 | elif m is Concat: 253 | c2 = sum([ch[x] for x in f]) 254 | elif m is Detect: 255 | args.append([ch[x] for x in f]) 256 | if isinstance(args[1], int): # number of anchors 257 | args[1] = [list(range(args[1] * 2))] * len(f) 258 | elif m is Contract: 259 | c2 = ch[f] * args[0] ** 2 260 | elif m is Expand: 261 | c2 = ch[f] // args[0] ** 2 262 | else: 263 | c2 = ch[f] 264 | 265 | m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module 266 | t = str(m)[8:-2].replace('__main__.', '') # module type 267 | np = sum([x.numel() for x in m_.parameters()]) # number params 268 | m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params 269 | LOGGER.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n_, np, t, args)) # print 270 | save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist 271 | layers.append(m_) 272 | if i == 0: 273 | ch = [] 274 | ch.append(c2) 275 | return nn.Sequential(*layers), sorted(save) 276 | 277 | 278 | if __name__ == '__main__': 279 | parser = argparse.ArgumentParser() 280 | parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml') 281 | parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') 282 | parser.add_argument('--profile', action='store_true', help='profile model speed') 283 | opt = parser.parse_args() 284 | opt.cfg = check_file(opt.cfg) # check file 285 | set_logging() 286 | device = select_device(opt.device) 287 | 288 | # Create model 289 | model = Model(opt.cfg).to(device) 290 | model.train() 291 | 292 | # Profile 293 | if opt.profile: 294 | img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device) 295 | y = model(img, profile=True) 296 | 297 | # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898) 298 | # from torch.utils.tensorboard import SummaryWriter 299 | # tb_writer = SummaryWriter('.') 300 | # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/") 301 | # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph 302 | -------------------------------------------------------------------------------- /models/yolov5l.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.0 # model depth multiple 6 | width_multiple: 1.0 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5m.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.67 # model depth multiple 6 | width_multiple: 0.75 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5s.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 0.33 # model depth multiple 6 | width_multiple: 0.50 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /models/yolov5x.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | 3 | # Parameters 4 | nc: 80 # number of classes 5 | depth_multiple: 1.33 # model depth multiple 6 | width_multiple: 1.25 # layer channel multiple 7 | anchors: 8 | - [10,13, 16,30, 33,23] # P3/8 9 | - [30,61, 62,45, 59,119] # P4/16 10 | - [116,90, 156,198, 373,326] # P5/32 11 | 12 | # YOLOv5 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Focus, [64, 3]], # 0-P1/2 16 | [-1, 1, Conv, [128, 3, 2]], # 1-P2/4 17 | [-1, 3, C3, [128]], 18 | [-1, 1, Conv, [256, 3, 2]], # 3-P3/8 19 | [-1, 9, C3, [256]], 20 | [-1, 1, Conv, [512, 3, 2]], # 5-P4/16 21 | [-1, 9, C3, [512]], 22 | [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32 23 | [-1, 1, SPP, [1024, [5, 9, 13]]], 24 | [-1, 3, C3, [1024, False]], # 9 25 | ] 26 | 27 | # YOLOv5 head 28 | head: 29 | [[-1, 1, Conv, [512, 1, 1]], 30 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 31 | [[-1, 6], 1, Concat, [1]], # cat backbone P4 32 | [-1, 3, C3, [512, False]], # 13 33 | 34 | [-1, 1, Conv, [256, 1, 1]], 35 | [-1, 1, nn.Upsample, [None, 2, 'nearest']], 36 | [[-1, 4], 1, Concat, [1]], # cat backbone P3 37 | [-1, 3, C3, [256, False]], # 17 (P3/8-small) 38 | 39 | [-1, 1, Conv, [256, 3, 2]], 40 | [[-1, 14], 1, Concat, [1]], # cat head P4 41 | [-1, 3, C3, [512, False]], # 20 (P4/16-medium) 42 | 43 | [-1, 1, Conv, [512, 3, 2]], 44 | [[-1, 10], 1, Concat, [1]], # cat head P5 45 | [-1, 3, C3, [1024, False]], # 23 (P5/32-large) 46 | 47 | [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) 48 | ] 49 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | # pip install -r requirements.txt 2 | 3 | # base ---------------------------------------- 4 | matplotlib>=3.2.2 5 | numpy>=1.18.5 6 | opencv-python>=4.1.2 7 | Pillow>=8.0.0 8 | PyYAML>=5.3.1 9 | scipy>=1.4.1 10 | torch>=1.7.0 11 | torchvision>=0.8.1 12 | tqdm>=4.41.0 13 | 14 | # logging ------------------------------------- 15 | tensorboard>=2.4.1 16 | # wandb 17 | 18 | # plotting ------------------------------------ 19 | seaborn>=0.11.0 20 | pandas 21 | 22 | # export -------------------------------------- 23 | # coremltools>=4.1 24 | # onnx>=1.9.0 25 | # scikit-learn==0.19.2 # for coreml quantization 26 | # tensorflow==2.4.1 # for TFLite export 27 | 28 | # extras -------------------------------------- 29 | # Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172 30 | # pycocotools>=2.0 # COCO mAP 31 | # albumentations>=1.0.3 32 | thop # FLOPs computation 33 | -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | import torch 4 | from PIL import ImageFont 5 | 6 | FILE = Path(__file__).absolute() 7 | ROOT = FILE.parents[1] # yolov5/ dir 8 | 9 | # Check YOLOv5 Annotator font 10 | font = 'Arial.ttf' 11 | try: 12 | ImageFont.truetype(font) 13 | except Exception as e: # download if missing 14 | url = "https://ultralytics.com/assets/" + font 15 | print(f'Downloading {url} to {ROOT / font}...') 16 | torch.hub.download_url_to_file(url, str(ROOT / font)) 17 | -------------------------------------------------------------------------------- /utils/activations.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Activation functions 4 | """ 5 | 6 | import torch 7 | import torch.nn as nn 8 | import torch.nn.functional as F 9 | 10 | 11 | # SiLU https://arxiv.org/pdf/1606.08415.pdf ---------------------------------------------------------------------------- 12 | class SiLU(nn.Module): # export-friendly version of nn.SiLU() 13 | @staticmethod 14 | def forward(x): 15 | return x * torch.sigmoid(x) 16 | 17 | 18 | class Hardswish(nn.Module): # export-friendly version of nn.Hardswish() 19 | @staticmethod 20 | def forward(x): 21 | # return x * F.hardsigmoid(x) # for torchscript and CoreML 22 | return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX 23 | 24 | 25 | # Mish https://github.com/digantamisra98/Mish -------------------------------------------------------------------------- 26 | class Mish(nn.Module): 27 | @staticmethod 28 | def forward(x): 29 | return x * F.softplus(x).tanh() 30 | 31 | 32 | class MemoryEfficientMish(nn.Module): 33 | class F(torch.autograd.Function): 34 | @staticmethod 35 | def forward(ctx, x): 36 | ctx.save_for_backward(x) 37 | return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x))) 38 | 39 | @staticmethod 40 | def backward(ctx, grad_output): 41 | x = ctx.saved_tensors[0] 42 | sx = torch.sigmoid(x) 43 | fx = F.softplus(x).tanh() 44 | return grad_output * (fx + x * sx * (1 - fx * fx)) 45 | 46 | def forward(self, x): 47 | return self.F.apply(x) 48 | 49 | 50 | # FReLU https://arxiv.org/abs/2007.11824 ------------------------------------------------------------------------------- 51 | class FReLU(nn.Module): 52 | def __init__(self, c1, k=3): # ch_in, kernel 53 | super().__init__() 54 | self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False) 55 | self.bn = nn.BatchNorm2d(c1) 56 | 57 | def forward(self, x): 58 | return torch.max(x, self.bn(self.conv(x))) 59 | 60 | 61 | # ACON https://arxiv.org/pdf/2009.04759.pdf ---------------------------------------------------------------------------- 62 | class AconC(nn.Module): 63 | r""" ACON activation (activate or not). 64 | AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter 65 | according to "Activate or Not: Learning Customized Activation" . 66 | """ 67 | 68 | def __init__(self, c1): 69 | super().__init__() 70 | self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) 71 | self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) 72 | self.beta = nn.Parameter(torch.ones(1, c1, 1, 1)) 73 | 74 | def forward(self, x): 75 | dpx = (self.p1 - self.p2) * x 76 | return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x 77 | 78 | 79 | class MetaAconC(nn.Module): 80 | r""" ACON activation (activate or not). 81 | MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network 82 | according to "Activate or Not: Learning Customized Activation" . 83 | """ 84 | 85 | def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r 86 | super().__init__() 87 | c2 = max(r, c1 // r) 88 | self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1)) 89 | self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1)) 90 | self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True) 91 | self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True) 92 | # self.bn1 = nn.BatchNorm2d(c2) 93 | # self.bn2 = nn.BatchNorm2d(c1) 94 | 95 | def forward(self, x): 96 | y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True) 97 | # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891 98 | # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable 99 | beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed 100 | dpx = (self.p1 - self.p2) * x 101 | return dpx * torch.sigmoid(beta * dpx) + self.p2 * x 102 | -------------------------------------------------------------------------------- /utils/augmentations.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Image augmentation functions 4 | """ 5 | 6 | import logging 7 | import math 8 | import random 9 | 10 | import cv2 11 | import numpy as np 12 | 13 | from utils.general import colorstr, segment2box, resample_segments, check_version 14 | from utils.metrics import bbox_ioa 15 | 16 | 17 | class Albumentations: 18 | # YOLOv5 Albumentations class (optional, only used if package is installed) 19 | def __init__(self): 20 | self.transform = None 21 | try: 22 | import albumentations as A 23 | check_version(A.__version__, '1.0.3') # version requirement 24 | 25 | self.transform = A.Compose([ 26 | A.Blur(p=0.1), 27 | A.MedianBlur(p=0.1), 28 | A.ToGray(p=0.01)], 29 | bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels'])) 30 | 31 | logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p)) 32 | except ImportError: # package not installed, skip 33 | pass 34 | except Exception as e: 35 | logging.info(colorstr('albumentations: ') + f'{e}') 36 | 37 | def __call__(self, im, labels, p=1.0): 38 | if self.transform and random.random() < p: 39 | new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed 40 | im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) 41 | return im, labels 42 | 43 | 44 | def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5): 45 | # HSV color-space augmentation 46 | if hgain or sgain or vgain: 47 | r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains 48 | hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV)) 49 | dtype = im.dtype # uint8 50 | 51 | x = np.arange(0, 256, dtype=r.dtype) 52 | lut_hue = ((x * r[0]) % 180).astype(dtype) 53 | lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) 54 | lut_val = np.clip(x * r[2], 0, 255).astype(dtype) 55 | 56 | im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) 57 | cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed 58 | 59 | 60 | def hist_equalize(im, clahe=True, bgr=False): 61 | # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255 62 | yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) 63 | if clahe: 64 | c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) 65 | yuv[:, :, 0] = c.apply(yuv[:, :, 0]) 66 | else: 67 | yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram 68 | return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB 69 | 70 | 71 | def replicate(im, labels): 72 | # Replicate labels 73 | h, w = im.shape[:2] 74 | boxes = labels[:, 1:].astype(int) 75 | x1, y1, x2, y2 = boxes.T 76 | s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) 77 | for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices 78 | x1b, y1b, x2b, y2b = boxes[i] 79 | bh, bw = y2b - y1b, x2b - x1b 80 | yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y 81 | x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] 82 | im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax] 83 | labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) 84 | 85 | return im, labels 86 | 87 | 88 | def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): 89 | # Resize and pad image while meeting stride-multiple constraints 90 | shape = im.shape[:2] # current shape [height, width] 91 | if isinstance(new_shape, int): 92 | new_shape = (new_shape, new_shape) 93 | 94 | # Scale ratio (new / old) 95 | r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) 96 | if not scaleup: # only scale down, do not scale up (for better val mAP) 97 | r = min(r, 1.0) 98 | 99 | # Compute padding 100 | ratio = r, r # width, height ratios 101 | new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) 102 | dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding 103 | if auto: # minimum rectangle 104 | dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding 105 | elif scaleFill: # stretch 106 | dw, dh = 0.0, 0.0 107 | new_unpad = (new_shape[1], new_shape[0]) 108 | ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios 109 | 110 | dw /= 2 # divide padding into 2 sides 111 | dh /= 2 112 | 113 | if shape[::-1] != new_unpad: # resize 114 | im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) 115 | top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) 116 | left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) 117 | im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border 118 | return im, ratio, (dw, dh) 119 | 120 | 121 | def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, 122 | border=(0, 0)): 123 | # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10)) 124 | # targets = [cls, xyxy] 125 | 126 | height = im.shape[0] + border[0] * 2 # shape(h,w,c) 127 | width = im.shape[1] + border[1] * 2 128 | 129 | # Center 130 | C = np.eye(3) 131 | C[0, 2] = -im.shape[1] / 2 # x translation (pixels) 132 | C[1, 2] = -im.shape[0] / 2 # y translation (pixels) 133 | 134 | # Perspective 135 | P = np.eye(3) 136 | P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) 137 | P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) 138 | 139 | # Rotation and Scale 140 | R = np.eye(3) 141 | a = random.uniform(-degrees, degrees) 142 | # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations 143 | s = random.uniform(1 - scale, 1 + scale) 144 | # s = 2 ** random.uniform(-scale, scale) 145 | R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) 146 | 147 | # Shear 148 | S = np.eye(3) 149 | S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) 150 | S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) 151 | 152 | # Translation 153 | T = np.eye(3) 154 | T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) 155 | T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) 156 | 157 | # Combined rotation matrix 158 | M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT 159 | if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed 160 | if perspective: 161 | im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) 162 | else: # affine 163 | im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) 164 | 165 | # Visualize 166 | # import matplotlib.pyplot as plt 167 | # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() 168 | # ax[0].imshow(im[:, :, ::-1]) # base 169 | # ax[1].imshow(im2[:, :, ::-1]) # warped 170 | 171 | # Transform label coordinates 172 | n = len(targets) 173 | if n: 174 | use_segments = any(x.any() for x in segments) 175 | new = np.zeros((n, 4)) 176 | if use_segments: # warp segments 177 | segments = resample_segments(segments) # upsample 178 | for i, segment in enumerate(segments): 179 | xy = np.ones((len(segment), 3)) 180 | xy[:, :2] = segment 181 | xy = xy @ M.T # transform 182 | xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine 183 | 184 | # clip 185 | new[i] = segment2box(xy, width, height) 186 | 187 | else: # warp boxes 188 | xy = np.ones((n * 4, 3)) 189 | xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 190 | xy = xy @ M.T # transform 191 | xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine 192 | 193 | # create new boxes 194 | x = xy[:, [0, 2, 4, 6]] 195 | y = xy[:, [1, 3, 5, 7]] 196 | new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T 197 | 198 | # clip 199 | new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) 200 | new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) 201 | 202 | # filter candidates 203 | i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) 204 | targets = targets[i] 205 | targets[:, 1:5] = new[i] 206 | 207 | return im, targets 208 | 209 | 210 | def copy_paste(im, labels, segments, p=0.5): 211 | # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) 212 | n = len(segments) 213 | if p and n: 214 | h, w, c = im.shape # height, width, channels 215 | im_new = np.zeros(im.shape, np.uint8) 216 | for j in random.sample(range(n), k=round(p * n)): 217 | l, s = labels[j], segments[j] 218 | box = w - l[3], l[2], w - l[1], l[4] 219 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 220 | if (ioa < 0.30).all(): # allow 30% obscuration of existing labels 221 | labels = np.concatenate((labels, [[l[0], *box]]), 0) 222 | segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) 223 | cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) 224 | 225 | result = cv2.bitwise_and(src1=im, src2=im_new) 226 | result = cv2.flip(result, 1) # augment segments (flip left-right) 227 | i = result > 0 # pixels to replace 228 | # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch 229 | im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug 230 | 231 | return im, labels, segments 232 | 233 | 234 | def cutout(im, labels, p=0.5): 235 | # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 236 | if random.random() < p: 237 | h, w = im.shape[:2] 238 | scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction 239 | for s in scales: 240 | mask_h = random.randint(1, int(h * s)) # create random masks 241 | mask_w = random.randint(1, int(w * s)) 242 | 243 | # box 244 | xmin = max(0, random.randint(0, w) - mask_w // 2) 245 | ymin = max(0, random.randint(0, h) - mask_h // 2) 246 | xmax = min(w, xmin + mask_w) 247 | ymax = min(h, ymin + mask_h) 248 | 249 | # apply random color mask 250 | im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] 251 | 252 | # return unobscured labels 253 | if len(labels) and s > 0.03: 254 | box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) 255 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 256 | labels = labels[ioa < 0.60] # remove >60% obscured labels 257 | 258 | return labels 259 | 260 | 261 | def mixup(im, labels, im2, labels2): 262 | # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf 263 | r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 264 | im = (im * r + im2 * (1 - r)).astype(np.uint8) 265 | labels = np.concatenate((labels, labels2), 0) 266 | return im, labels 267 | 268 | 269 | def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) 270 | # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio 271 | w1, h1 = box1[2] - box1[0], box1[3] - box1[1] 272 | w2, h2 = box2[2] - box2[0], box2[3] - box2[1] 273 | ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio 274 | return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates 275 | -------------------------------------------------------------------------------- /utils/autoanchor.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Auto-anchor utils 4 | """ 5 | 6 | import random 7 | 8 | import numpy as np 9 | import torch 10 | import yaml 11 | from tqdm import tqdm 12 | 13 | from utils.general import colorstr 14 | 15 | 16 | def check_anchor_order(m): 17 | # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary 18 | a = m.anchor_grid.prod(-1).view(-1) # anchor area 19 | da = a[-1] - a[0] # delta a 20 | ds = m.stride[-1] - m.stride[0] # delta s 21 | if da.sign() != ds.sign(): # same order 22 | print('Reversing anchor order') 23 | m.anchors[:] = m.anchors.flip(0) 24 | m.anchor_grid[:] = m.anchor_grid.flip(0) 25 | 26 | 27 | def check_anchors(dataset, model, thr=4.0, imgsz=640): 28 | # Check anchor fit to data, recompute if necessary 29 | prefix = colorstr('autoanchor: ') 30 | print(f'\n{prefix}Analyzing anchors... ', end='') 31 | m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() 32 | shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) 33 | scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale 34 | wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh 35 | 36 | def metric(k): # compute metric 37 | r = wh[:, None] / k[None] 38 | x = torch.min(r, 1. / r).min(2)[0] # ratio metric 39 | best = x.max(1)[0] # best_x 40 | aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold 41 | bpr = (best > 1. / thr).float().mean() # best possible recall 42 | return bpr, aat 43 | 44 | anchors = m.anchor_grid.clone().cpu().view(-1, 2) # current anchors 45 | bpr, aat = metric(anchors) 46 | print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='') 47 | if bpr < 0.98: # threshold to recompute 48 | print('. Attempting to improve anchors, please wait...') 49 | na = m.anchor_grid.numel() // 2 # number of anchors 50 | try: 51 | anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) 52 | except Exception as e: 53 | print(f'{prefix}ERROR: {e}') 54 | new_bpr = metric(anchors)[0] 55 | if new_bpr > bpr: # replace anchors 56 | anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) 57 | m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid) # for inference 58 | m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss 59 | check_anchor_order(m) 60 | print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.') 61 | else: 62 | print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.') 63 | print('') # newline 64 | 65 | 66 | def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): 67 | """ Creates kmeans-evolved anchors from training dataset 68 | 69 | Arguments: 70 | dataset: path to data.yaml, or a loaded dataset 71 | n: number of anchors 72 | img_size: image size used for training 73 | thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 74 | gen: generations to evolve anchors using genetic algorithm 75 | verbose: print all results 76 | 77 | Return: 78 | k: kmeans evolved anchors 79 | 80 | Usage: 81 | from utils.autoanchor import *; _ = kmean_anchors() 82 | """ 83 | from scipy.cluster.vq import kmeans 84 | 85 | thr = 1. / thr 86 | prefix = colorstr('autoanchor: ') 87 | 88 | def metric(k, wh): # compute metrics 89 | r = wh[:, None] / k[None] 90 | x = torch.min(r, 1. / r).min(2)[0] # ratio metric 91 | # x = wh_iou(wh, torch.tensor(k)) # iou metric 92 | return x, x.max(1)[0] # x, best_x 93 | 94 | def anchor_fitness(k): # mutation fitness 95 | _, best = metric(torch.tensor(k, dtype=torch.float32), wh) 96 | return (best * (best > thr).float()).mean() # fitness 97 | 98 | def print_results(k): 99 | k = k[np.argsort(k.prod(1))] # sort small to large 100 | x, best = metric(k, wh0) 101 | bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr 102 | print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr') 103 | print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' 104 | f'past_thr={x[x > thr].mean():.3f}-mean: ', end='') 105 | for i, x in enumerate(k): 106 | print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg 107 | return k 108 | 109 | if isinstance(dataset, str): # *.yaml file 110 | with open(dataset, errors='ignore') as f: 111 | data_dict = yaml.safe_load(f) # model dict 112 | from utils.datasets import LoadImagesAndLabels 113 | dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True) 114 | 115 | # Get label wh 116 | shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True) 117 | wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh 118 | 119 | # Filter 120 | i = (wh0 < 3.0).any(1).sum() 121 | if i: 122 | print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.') 123 | wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels 124 | # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1 125 | 126 | # Kmeans calculation 127 | print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...') 128 | s = wh.std(0) # sigmas for whitening 129 | k, dist = kmeans(wh / s, n, iter=30) # points, mean distance 130 | assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}') 131 | k *= s 132 | wh = torch.tensor(wh, dtype=torch.float32) # filtered 133 | wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered 134 | k = print_results(k) 135 | 136 | # Plot 137 | # k, d = [None] * 20, [None] * 20 138 | # for i in tqdm(range(1, 21)): 139 | # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance 140 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True) 141 | # ax = ax.ravel() 142 | # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.') 143 | # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh 144 | # ax[0].hist(wh[wh[:, 0]<100, 0],400) 145 | # ax[1].hist(wh[wh[:, 1]<100, 1],400) 146 | # fig.savefig('wh.png', dpi=200) 147 | 148 | # Evolve 149 | npr = np.random 150 | f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma 151 | pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar 152 | for _ in pbar: 153 | v = np.ones(sh) 154 | while (v == 1).all(): # mutate until a change occurs (prevent duplicates) 155 | v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0) 156 | kg = (k.copy() * v).clip(min=2.0) 157 | fg = anchor_fitness(kg) 158 | if fg > f: 159 | f, k = fg, kg.copy() 160 | pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}' 161 | if verbose: 162 | print_results(k) 163 | 164 | return print_results(k) 165 | -------------------------------------------------------------------------------- /utils/aws/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/utils/aws/__init__.py -------------------------------------------------------------------------------- /utils/aws/mime.sh: -------------------------------------------------------------------------------- 1 | # AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/ 2 | # This script will run on every instance restart, not only on first start 3 | # --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA --- 4 | 5 | Content-Type: multipart/mixed; boundary="//" 6 | MIME-Version: 1.0 7 | 8 | --// 9 | Content-Type: text/cloud-config; charset="us-ascii" 10 | MIME-Version: 1.0 11 | Content-Transfer-Encoding: 7bit 12 | Content-Disposition: attachment; filename="cloud-config.txt" 13 | 14 | #cloud-config 15 | cloud_final_modules: 16 | - [scripts-user, always] 17 | 18 | --// 19 | Content-Type: text/x-shellscript; charset="us-ascii" 20 | MIME-Version: 1.0 21 | Content-Transfer-Encoding: 7bit 22 | Content-Disposition: attachment; filename="userdata.txt" 23 | 24 | #!/bin/bash 25 | # --- paste contents of userdata.sh here --- 26 | --// 27 | -------------------------------------------------------------------------------- /utils/aws/resume.py: -------------------------------------------------------------------------------- 1 | # Resume all interrupted trainings in yolov5/ dir including DDP trainings 2 | # Usage: $ python utils/aws/resume.py 3 | 4 | import os 5 | import sys 6 | from pathlib import Path 7 | 8 | import torch 9 | import yaml 10 | 11 | sys.path.append('./') # to run '$ python *.py' files in subdirectories 12 | 13 | port = 0 # --master_port 14 | path = Path('').resolve() 15 | for last in path.rglob('*/**/last.pt'): 16 | ckpt = torch.load(last) 17 | if ckpt['optimizer'] is None: 18 | continue 19 | 20 | # Load opt.yaml 21 | with open(last.parent.parent / 'opt.yaml') as f: 22 | opt = yaml.safe_load(f) 23 | 24 | # Get device count 25 | d = opt['device'].split(',') # devices 26 | nd = len(d) # number of devices 27 | ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel 28 | 29 | if ddp: # multi-GPU 30 | port += 1 31 | cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}' 32 | else: # single-GPU 33 | cmd = f'python train.py --resume {last}' 34 | 35 | cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread 36 | print(cmd) 37 | os.system(cmd) 38 | -------------------------------------------------------------------------------- /utils/aws/userdata.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html 3 | # This script will run only once on first instance start (for a re-start script see mime.sh) 4 | # /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir 5 | # Use >300 GB SSD 6 | 7 | cd home/ubuntu 8 | if [ ! -d yolov5 ]; then 9 | echo "Running first-time script." # install dependencies, download COCO, pull Docker 10 | git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5 11 | cd yolov5 12 | bash data/scripts/get_coco.sh && echo "COCO done." & 13 | sudo docker pull ultralytics/yolov5:latest && echo "Docker done." & 14 | python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." & 15 | wait && echo "All tasks done." # finish background tasks 16 | else 17 | echo "Running re-start script." # resume interrupted runs 18 | i=0 19 | list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour' 20 | while IFS= read -r id; do 21 | ((i++)) 22 | echo "restarting container $i: $id" 23 | sudo docker start $id 24 | # sudo docker exec -it $id python train.py --resume # single-GPU 25 | sudo docker exec -d $id python utils/aws/resume.py # multi-scenario 26 | done <<<"$list" 27 | fi 28 | -------------------------------------------------------------------------------- /utils/callbacks.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Callback utils 4 | """ 5 | 6 | 7 | class Callbacks: 8 | """" 9 | Handles all registered callbacks for YOLOv5 Hooks 10 | """ 11 | 12 | _callbacks = { 13 | 'on_pretrain_routine_start': [], 14 | 'on_pretrain_routine_end': [], 15 | 16 | 'on_train_start': [], 17 | 'on_train_epoch_start': [], 18 | 'on_train_batch_start': [], 19 | 'optimizer_step': [], 20 | 'on_before_zero_grad': [], 21 | 'on_train_batch_end': [], 22 | 'on_train_epoch_end': [], 23 | 24 | 'on_val_start': [], 25 | 'on_val_batch_start': [], 26 | 'on_val_image_end': [], 27 | 'on_val_batch_end': [], 28 | 'on_val_end': [], 29 | 30 | 'on_fit_epoch_end': [], # fit = train + val 31 | 'on_model_save': [], 32 | 'on_train_end': [], 33 | 34 | 'teardown': [], 35 | } 36 | 37 | def __init__(self): 38 | return 39 | 40 | def register_action(self, hook, name='', callback=None): 41 | """ 42 | Register a new action to a callback hook 43 | 44 | Args: 45 | hook The callback hook name to register the action to 46 | name The name of the action 47 | callback The callback to fire 48 | """ 49 | assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" 50 | assert callable(callback), f"callback '{callback}' is not callable" 51 | self._callbacks[hook].append({'name': name, 'callback': callback}) 52 | 53 | def get_registered_actions(self, hook=None): 54 | """" 55 | Returns all the registered actions by callback hook 56 | 57 | Args: 58 | hook The name of the hook to check, defaults to all 59 | """ 60 | if hook: 61 | return self._callbacks[hook] 62 | else: 63 | return self._callbacks 64 | 65 | def run_callbacks(self, hook, *args, **kwargs): 66 | """ 67 | Loop through the registered actions and fire all callbacks 68 | """ 69 | for logger in self._callbacks[hook]: 70 | # print(f"Running callbacks.{logger['callback'].__name__}()") 71 | logger['callback'](*args, **kwargs) 72 | 73 | def on_pretrain_routine_start(self, *args, **kwargs): 74 | """ 75 | Fires all registered callbacks at the start of each pretraining routine 76 | """ 77 | self.run_callbacks('on_pretrain_routine_start', *args, **kwargs) 78 | 79 | def on_pretrain_routine_end(self, *args, **kwargs): 80 | """ 81 | Fires all registered callbacks at the end of each pretraining routine 82 | """ 83 | self.run_callbacks('on_pretrain_routine_end', *args, **kwargs) 84 | 85 | def on_train_start(self, *args, **kwargs): 86 | """ 87 | Fires all registered callbacks at the start of each training 88 | """ 89 | self.run_callbacks('on_train_start', *args, **kwargs) 90 | 91 | def on_train_epoch_start(self, *args, **kwargs): 92 | """ 93 | Fires all registered callbacks at the start of each training epoch 94 | """ 95 | self.run_callbacks('on_train_epoch_start', *args, **kwargs) 96 | 97 | def on_train_batch_start(self, *args, **kwargs): 98 | """ 99 | Fires all registered callbacks at the start of each training batch 100 | """ 101 | self.run_callbacks('on_train_batch_start', *args, **kwargs) 102 | 103 | def optimizer_step(self, *args, **kwargs): 104 | """ 105 | Fires all registered callbacks on each optimizer step 106 | """ 107 | self.run_callbacks('optimizer_step', *args, **kwargs) 108 | 109 | def on_before_zero_grad(self, *args, **kwargs): 110 | """ 111 | Fires all registered callbacks before zero grad 112 | """ 113 | self.run_callbacks('on_before_zero_grad', *args, **kwargs) 114 | 115 | def on_train_batch_end(self, *args, **kwargs): 116 | """ 117 | Fires all registered callbacks at the end of each training batch 118 | """ 119 | self.run_callbacks('on_train_batch_end', *args, **kwargs) 120 | 121 | def on_train_epoch_end(self, *args, **kwargs): 122 | """ 123 | Fires all registered callbacks at the end of each training epoch 124 | """ 125 | self.run_callbacks('on_train_epoch_end', *args, **kwargs) 126 | 127 | def on_val_start(self, *args, **kwargs): 128 | """ 129 | Fires all registered callbacks at the start of the validation 130 | """ 131 | self.run_callbacks('on_val_start', *args, **kwargs) 132 | 133 | def on_val_batch_start(self, *args, **kwargs): 134 | """ 135 | Fires all registered callbacks at the start of each validation batch 136 | """ 137 | self.run_callbacks('on_val_batch_start', *args, **kwargs) 138 | 139 | def on_val_image_end(self, *args, **kwargs): 140 | """ 141 | Fires all registered callbacks at the end of each val image 142 | """ 143 | self.run_callbacks('on_val_image_end', *args, **kwargs) 144 | 145 | def on_val_batch_end(self, *args, **kwargs): 146 | """ 147 | Fires all registered callbacks at the end of each validation batch 148 | """ 149 | self.run_callbacks('on_val_batch_end', *args, **kwargs) 150 | 151 | def on_val_end(self, *args, **kwargs): 152 | """ 153 | Fires all registered callbacks at the end of the validation 154 | """ 155 | self.run_callbacks('on_val_end', *args, **kwargs) 156 | 157 | def on_fit_epoch_end(self, *args, **kwargs): 158 | """ 159 | Fires all registered callbacks at the end of each fit (train+val) epoch 160 | """ 161 | self.run_callbacks('on_fit_epoch_end', *args, **kwargs) 162 | 163 | def on_model_save(self, *args, **kwargs): 164 | """ 165 | Fires all registered callbacks after each model save 166 | """ 167 | self.run_callbacks('on_model_save', *args, **kwargs) 168 | 169 | def on_train_end(self, *args, **kwargs): 170 | """ 171 | Fires all registered callbacks at the end of training 172 | """ 173 | self.run_callbacks('on_train_end', *args, **kwargs) 174 | 175 | def teardown(self, *args, **kwargs): 176 | """ 177 | Fires all registered callbacks before teardown 178 | """ 179 | self.run_callbacks('teardown', *args, **kwargs) 180 | -------------------------------------------------------------------------------- /utils/downloads.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Download utils 4 | """ 5 | 6 | import os 7 | import platform 8 | import subprocess 9 | import time 10 | import urllib 11 | from pathlib import Path 12 | 13 | import requests 14 | import torch 15 | 16 | 17 | def gsutil_getsize(url=''): 18 | # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du 19 | s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') 20 | return eval(s.split(' ')[0]) if len(s) else 0 # bytes 21 | 22 | 23 | def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): 24 | # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes 25 | file = Path(file) 26 | assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}" 27 | try: # url1 28 | print(f'Downloading {url} to {file}...') 29 | torch.hub.download_url_to_file(url, str(file)) 30 | assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check 31 | except Exception as e: # url2 32 | file.unlink(missing_ok=True) # remove partial downloads 33 | print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') 34 | os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail 35 | finally: 36 | if not file.exists() or file.stat().st_size < min_bytes: # check 37 | file.unlink(missing_ok=True) # remove partial downloads 38 | print(f"ERROR: {assert_msg}\n{error_msg}") 39 | print('') 40 | 41 | 42 | def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download() 43 | # Attempt file download if does not exist 44 | file = Path(str(file).strip().replace("'", '')) 45 | 46 | if not file.exists(): 47 | # URL specified 48 | name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc. 49 | if str(file).startswith(('http:/', 'https:/')): # download 50 | url = str(file).replace(':/', '://') # Pathlib turns :// -> :/ 51 | name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth... 52 | safe_download(file=name, url=url, min_bytes=1E5) 53 | return name 54 | 55 | # GitHub assets 56 | file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) 57 | try: 58 | response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api 59 | assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...] 60 | tag = response['tag_name'] # i.e. 'v1.0' 61 | except: # fallback plan 62 | assets = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 63 | 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt'] 64 | try: 65 | tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1] 66 | except: 67 | tag = 'v5.0' # current release 68 | 69 | if name in assets: 70 | safe_download(file, 71 | url=f'https://github.com/{repo}/releases/download/{tag}/{name}', 72 | # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional) 73 | min_bytes=1E5, 74 | error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/') 75 | 76 | return str(file) 77 | 78 | 79 | def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'): 80 | # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download() 81 | t = time.time() 82 | file = Path(file) 83 | cookie = Path('cookie') # gdrive cookie 84 | print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='') 85 | file.unlink(missing_ok=True) # remove existing file 86 | cookie.unlink(missing_ok=True) # remove existing cookie 87 | 88 | # Attempt file download 89 | out = "NUL" if platform.system() == "Windows" else "/dev/null" 90 | os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}') 91 | if os.path.exists('cookie'): # large file 92 | s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}' 93 | else: # small file 94 | s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"' 95 | r = os.system(s) # execute, capture return 96 | cookie.unlink(missing_ok=True) # remove existing cookie 97 | 98 | # Error check 99 | if r != 0: 100 | file.unlink(missing_ok=True) # remove partial 101 | print('Download error ') # raise Exception('Download error') 102 | return r 103 | 104 | # Unzip if archive 105 | if file.suffix == '.zip': 106 | print('unzipping... ', end='') 107 | os.system(f'unzip -q {file}') # unzip 108 | file.unlink() # remove zip to free space 109 | 110 | print(f'Done ({time.time() - t:.1f}s)') 111 | return r 112 | 113 | 114 | def get_token(cookie="./cookie"): 115 | with open(cookie) as f: 116 | for line in f: 117 | if "download" in line: 118 | return line.split()[-1] 119 | return "" 120 | 121 | # Google utils: https://cloud.google.com/storage/docs/reference/libraries ---------------------------------------------- 122 | # 123 | # 124 | # def upload_blob(bucket_name, source_file_name, destination_blob_name): 125 | # # Uploads a file to a bucket 126 | # # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python 127 | # 128 | # storage_client = storage.Client() 129 | # bucket = storage_client.get_bucket(bucket_name) 130 | # blob = bucket.blob(destination_blob_name) 131 | # 132 | # blob.upload_from_filename(source_file_name) 133 | # 134 | # print('File {} uploaded to {}.'.format( 135 | # source_file_name, 136 | # destination_blob_name)) 137 | # 138 | # 139 | # def download_blob(bucket_name, source_blob_name, destination_file_name): 140 | # # Uploads a blob from a bucket 141 | # storage_client = storage.Client() 142 | # bucket = storage_client.get_bucket(bucket_name) 143 | # blob = bucket.blob(source_blob_name) 144 | # 145 | # blob.download_to_filename(destination_file_name) 146 | # 147 | # print('Blob {} downloaded to {}.'.format( 148 | # source_blob_name, 149 | # destination_file_name)) 150 | -------------------------------------------------------------------------------- /utils/flask_rest_api/README.md: -------------------------------------------------------------------------------- 1 | # Flask REST API 2 | 3 | [REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are 4 | commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API 5 | created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/). 6 | 7 | ## Requirements 8 | 9 | [Flask](https://palletsprojects.com/p/flask/) is required. Install with: 10 | 11 | ```shell 12 | $ pip install Flask 13 | ``` 14 | 15 | ## Run 16 | 17 | After Flask installation run: 18 | 19 | ```shell 20 | $ python3 restapi.py --port 5000 21 | ``` 22 | 23 | Then use [curl](https://curl.se/) to perform a request: 24 | 25 | ```shell 26 | $ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s' 27 | ``` 28 | 29 | The model inference results are returned as a JSON response: 30 | 31 | ```json 32 | [ 33 | { 34 | "class": 0, 35 | "confidence": 0.8900438547, 36 | "height": 0.9318675399, 37 | "name": "person", 38 | "width": 0.3264600933, 39 | "xcenter": 0.7438579798, 40 | "ycenter": 0.5207948685 41 | }, 42 | { 43 | "class": 0, 44 | "confidence": 0.8440024257, 45 | "height": 0.7155083418, 46 | "name": "person", 47 | "width": 0.6546785235, 48 | "xcenter": 0.427829951, 49 | "ycenter": 0.6334488392 50 | }, 51 | { 52 | "class": 27, 53 | "confidence": 0.3771208823, 54 | "height": 0.3902671337, 55 | "name": "tie", 56 | "width": 0.0696444362, 57 | "xcenter": 0.3675483763, 58 | "ycenter": 0.7991207838 59 | }, 60 | { 61 | "class": 27, 62 | "confidence": 0.3527112305, 63 | "height": 0.1540903747, 64 | "name": "tie", 65 | "width": 0.0336618312, 66 | "xcenter": 0.7814827561, 67 | "ycenter": 0.5065554976 68 | } 69 | ] 70 | ``` 71 | 72 | An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given 73 | in `example_request.py` 74 | -------------------------------------------------------------------------------- /utils/flask_rest_api/example_request.py: -------------------------------------------------------------------------------- 1 | """Perform test request""" 2 | import pprint 3 | 4 | import requests 5 | 6 | DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s" 7 | TEST_IMAGE = "zidane.jpg" 8 | 9 | image_data = open(TEST_IMAGE, "rb").read() 10 | 11 | response = requests.post(DETECTION_URL, files={"image": image_data}).json() 12 | 13 | pprint.pprint(response) 14 | -------------------------------------------------------------------------------- /utils/flask_rest_api/restapi.py: -------------------------------------------------------------------------------- 1 | """ 2 | Run a rest API exposing the yolov5s object detection model 3 | """ 4 | import argparse 5 | import io 6 | 7 | import torch 8 | from PIL import Image 9 | from flask import Flask, request 10 | 11 | app = Flask(__name__) 12 | 13 | DETECTION_URL = "/v1/object-detection/yolov5s" 14 | 15 | 16 | @app.route(DETECTION_URL, methods=["POST"]) 17 | def predict(): 18 | if not request.method == "POST": 19 | return 20 | 21 | if request.files.get("image"): 22 | image_file = request.files["image"] 23 | image_bytes = image_file.read() 24 | 25 | img = Image.open(io.BytesIO(image_bytes)) 26 | 27 | results = model(img, size=640) # reduce size=320 for faster inference 28 | return results.pandas().xyxy[0].to_json(orient="records") 29 | 30 | 31 | if __name__ == "__main__": 32 | parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model") 33 | parser.add_argument("--port", default=5000, type=int, help="port number") 34 | args = parser.parse_args() 35 | 36 | model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache 37 | app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat 38 | -------------------------------------------------------------------------------- /utils/google_app_engine/Dockerfile: -------------------------------------------------------------------------------- 1 | FROM gcr.io/google-appengine/python 2 | 3 | # Create a virtualenv for dependencies. This isolates these packages from 4 | # system-level packages. 5 | # Use -p python3 or -p python3.7 to select python version. Default is version 2. 6 | RUN virtualenv /env -p python3 7 | 8 | # Setting these environment variables are the same as running 9 | # source /env/bin/activate. 10 | ENV VIRTUAL_ENV /env 11 | ENV PATH /env/bin:$PATH 12 | 13 | RUN apt-get update && apt-get install -y python-opencv 14 | 15 | # Copy the application's requirements.txt and run pip to install all 16 | # dependencies into the virtualenv. 17 | ADD requirements.txt /app/requirements.txt 18 | RUN pip install -r /app/requirements.txt 19 | 20 | # Add the application source code. 21 | ADD . /app 22 | 23 | # Run a WSGI server to serve the application. gunicorn must be declared as 24 | # a dependency in requirements.txt. 25 | CMD gunicorn -b :$PORT main:app 26 | -------------------------------------------------------------------------------- /utils/google_app_engine/additional_requirements.txt: -------------------------------------------------------------------------------- 1 | # add these requirements in your app on top of the existing ones 2 | pip==19.2 3 | Flask==1.0.2 4 | gunicorn==19.9.0 5 | -------------------------------------------------------------------------------- /utils/google_app_engine/app.yaml: -------------------------------------------------------------------------------- 1 | runtime: custom 2 | env: flex 3 | 4 | service: yolov5app 5 | 6 | liveness_check: 7 | initial_delay_sec: 600 8 | 9 | manual_scaling: 10 | instances: 1 11 | resources: 12 | cpu: 1 13 | memory_gb: 4 14 | disk_size_gb: 20 -------------------------------------------------------------------------------- /utils/loggers/__init__.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Logging utils 4 | """ 5 | 6 | import warnings 7 | from threading import Thread 8 | 9 | import torch 10 | from torch.utils.tensorboard import SummaryWriter 11 | 12 | from utils.general import colorstr, emojis 13 | from utils.loggers.wandb.wandb_utils import WandbLogger 14 | from utils.plots import plot_images, plot_results 15 | from utils.torch_utils import de_parallel 16 | 17 | LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases 18 | 19 | try: 20 | import wandb 21 | 22 | assert hasattr(wandb, '__version__') # verify package import not local dir 23 | except (ImportError, AssertionError): 24 | wandb = None 25 | 26 | 27 | class Loggers(): 28 | # YOLOv5 Loggers class 29 | def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS): 30 | self.save_dir = save_dir 31 | self.weights = weights 32 | self.opt = opt 33 | self.hyp = hyp 34 | self.logger = logger # for printing results to console 35 | self.include = include 36 | self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss 37 | 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics 38 | 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss 39 | 'x/lr0', 'x/lr1', 'x/lr2'] # params 40 | for k in LOGGERS: 41 | setattr(self, k, None) # init empty logger dictionary 42 | self.csv = True # always log to csv 43 | 44 | # Message 45 | if not wandb: 46 | prefix = colorstr('Weights & Biases: ') 47 | s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)" 48 | print(emojis(s)) 49 | 50 | # TensorBoard 51 | s = self.save_dir 52 | if 'tb' in self.include and not self.opt.evolve: 53 | prefix = colorstr('TensorBoard: ') 54 | self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/") 55 | self.tb = SummaryWriter(str(s)) 56 | 57 | # W&B 58 | if wandb and 'wandb' in self.include: 59 | wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') 60 | run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None 61 | self.opt.hyp = self.hyp # add hyperparameters 62 | self.wandb = WandbLogger(self.opt, run_id) 63 | else: 64 | self.wandb = None 65 | 66 | def on_pretrain_routine_end(self): 67 | # Callback runs on pre-train routine end 68 | paths = self.save_dir.glob('*labels*.jpg') # training labels 69 | if self.wandb: 70 | self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) 71 | 72 | def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn): 73 | # Callback runs on train batch end 74 | if plots: 75 | if ni == 0: 76 | if not sync_bn: # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754 77 | with warnings.catch_warnings(): 78 | warnings.simplefilter('ignore') # suppress jit trace warning 79 | self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), []) 80 | if ni < 3: 81 | f = self.save_dir / f'train_batch{ni}.jpg' # filename 82 | Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start() 83 | if self.wandb and ni == 10: 84 | files = sorted(self.save_dir.glob('train*.jpg')) 85 | self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]}) 86 | 87 | def on_train_epoch_end(self, epoch): 88 | # Callback runs on train epoch end 89 | if self.wandb: 90 | self.wandb.current_epoch = epoch + 1 91 | 92 | def on_val_image_end(self, pred, predn, path, names, im): 93 | # Callback runs on val image end 94 | if self.wandb: 95 | self.wandb.val_one_image(pred, predn, path, names, im) 96 | 97 | def on_val_end(self): 98 | # Callback runs on val end 99 | if self.wandb: 100 | files = sorted(self.save_dir.glob('val*.jpg')) 101 | self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) 102 | 103 | def on_fit_epoch_end(self, vals, epoch, best_fitness, fi): 104 | # Callback runs at the end of each fit (train+val) epoch 105 | x = {k: v for k, v in zip(self.keys, vals)} # dict 106 | if self.csv: 107 | file = self.save_dir / 'results.csv' 108 | n = len(x) + 1 # number of cols 109 | s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header 110 | with open(file, 'a') as f: 111 | f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') 112 | 113 | if self.tb: 114 | for k, v in x.items(): 115 | self.tb.add_scalar(k, v, epoch) 116 | 117 | if self.wandb: 118 | self.wandb.log(x) 119 | self.wandb.end_epoch(best_result=best_fitness == fi) 120 | 121 | def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): 122 | # Callback runs on model save event 123 | if self.wandb: 124 | if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1: 125 | self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) 126 | 127 | def on_train_end(self, last, best, plots, epoch): 128 | # Callback runs on training end 129 | if plots: 130 | plot_results(file=self.save_dir / 'results.csv') # save results.png 131 | files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]] 132 | files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter 133 | 134 | if self.tb: 135 | import cv2 136 | for f in files: 137 | self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') 138 | 139 | if self.wandb: 140 | self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) 141 | # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model 142 | if not self.opt.evolve: 143 | wandb.log_artifact(str(best if best.exists() else last), type='model', 144 | name='run_' + self.wandb.wandb_run.id + '_model', 145 | aliases=['latest', 'best', 'stripped']) 146 | self.wandb.finish_run() 147 | else: 148 | self.wandb.finish_run() 149 | self.wandb = WandbLogger(self.opt) 150 | -------------------------------------------------------------------------------- /utils/loggers/wandb/README.md: -------------------------------------------------------------------------------- 1 | 📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. 2 | * [About Weights & Biases](#about-weights-&-biases) 3 | * [First-Time Setup](#first-time-setup) 4 | * [Viewing runs](#viewing-runs) 5 | * [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) 6 | * [Reports: Share your work with the world!](#reports) 7 | 8 | ## About Weights & Biases 9 | Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions. 10 | 11 | Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows: 12 | 13 | * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time 14 | * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4), visualized automatically 15 | * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization 16 | * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators 17 | * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently 18 | * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models 19 | 20 | ## First-Time Setup 21 |
22 | Toggle Details 23 | When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device. 24 | 25 | W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as: 26 | 27 | ```shell 28 | $ python train.py --project ... --name ... 29 | ``` 30 | 31 | 32 |
33 | 34 | ## Viewing Runs 35 |
36 | Toggle Details 37 | Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged: 38 | 39 | * Training & Validation losses 40 | * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 41 | * Learning Rate over time 42 | * A bounding box debugging panel, showing the training progress over time 43 | * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** 44 | * System: Disk I/0, CPU utilization, RAM memory usage 45 | * Your trained model as W&B Artifact 46 | * Environment: OS and Python types, Git repository and state, **training command** 47 | 48 | 49 |
50 | 51 | ## Advanced Usage 52 | You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started. 53 |
54 |

1. Visualize and Version Datasets

55 | Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact. 56 |
57 | Usage 58 | Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. 59 | 60 | ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) 61 |
62 | 63 |

2: Train and Log Evaluation simultaneousy

64 | This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table 65 | Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, 66 | so no images will be uploaded from your system more than once. 67 |
68 | Usage 69 | Code $ python utils/logger/wandb/log_dataset.py --data .. --upload_data 70 | 71 | ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) 72 |
73 | 74 |

3: Train using dataset artifact

75 | When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that 76 | can be used to train a model directly from the dataset artifact. This also logs evaluation 77 |
78 | Usage 79 | Code $ python utils/logger/wandb/log_dataset.py --data {data}_wandb.yaml 80 | 81 | ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) 82 |
83 | 84 |

4: Save model checkpoints as artifacts

85 | To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. 86 | You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged 87 | 88 |
89 | Usage 90 | Code $ python train.py --save_period 1 91 | 92 | ![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) 93 |
94 | 95 |
96 | 97 |

5: Resume runs from checkpoint artifacts.

98 | Any run can be resumed using artifacts if the --resume argument starts with wandb-artifact:// prefix followed by the run path, i.e, wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system. 99 | 100 |
101 | Usage 102 | Code $ python train.py --resume wandb-artifact://{run_path} 103 | 104 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 105 |
106 | 107 |

6: Resume runs from dataset artifact & checkpoint artifacts.

108 | Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device 109 | The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset or 110 | train from _wandb.yaml file and set --save_period 111 | 112 |
113 | Usage 114 | Code $ python train.py --resume wandb-artifact://{run_path} 115 | 116 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 117 |
118 | 119 | 120 | 121 | 122 | 123 |

Reports

124 | W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)). 125 | 126 | 127 | 128 | ## Environments 129 | YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): 130 | 131 | * **Google Colab and Kaggle** notebooks with free GPU: [![Open In Colab](https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667)](https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb) [![Open In Kaggle](https://camo.githubusercontent.com/a08ca511178e691ace596a95d334f73cf4ce06e83a5c4a5169b8bb68cac27bef/68747470733a2f2f6b6167676c652e636f6d2f7374617469632f696d616765732f6f70656e2d696e2d6b6167676c652e737667)](https://www.kaggle.com/ultralytics/yolov5) 132 | * **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 133 | * **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) 134 | * **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) [![Docker Pulls](https://camo.githubusercontent.com/280faedaf431e4c0c24fdb30ec00a66d627404e5c4c498210d3f014dd58c2c7e/68747470733a2f2f696d672e736869656c64732e696f2f646f636b65722f70756c6c732f756c7472616c79746963732f796f6c6f76353f6c6f676f3d646f636b6572)](https://hub.docker.com/r/ultralytics/yolov5) 135 | 136 | ## Status 137 | ![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) 138 | 139 | If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit. 140 | 141 | -------------------------------------------------------------------------------- /utils/loggers/wandb/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RichardoMrMu/yolov5-helmet-detection-python/6a4083f0eefe502fe6ce9dd679beebe0b7569d41/utils/loggers/wandb/__init__.py -------------------------------------------------------------------------------- /utils/loggers/wandb/log_dataset.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | from wandb_utils import WandbLogger 4 | 5 | WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' 6 | 7 | 8 | def create_dataset_artifact(opt): 9 | logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused 10 | 11 | 12 | if __name__ == '__main__': 13 | parser = argparse.ArgumentParser() 14 | parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path') 15 | parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') 16 | parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project') 17 | parser.add_argument('--entity', default=None, help='W&B entity') 18 | parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run') 19 | 20 | opt = parser.parse_args() 21 | opt.resume = False # Explicitly disallow resume check for dataset upload job 22 | 23 | create_dataset_artifact(opt) 24 | -------------------------------------------------------------------------------- /utils/loggers/wandb/sweep.py: -------------------------------------------------------------------------------- 1 | import sys 2 | from pathlib import Path 3 | 4 | import wandb 5 | 6 | FILE = Path(__file__).absolute() 7 | sys.path.append(FILE.parents[3].as_posix()) # add utils/ to path 8 | 9 | from train import train, parse_opt 10 | from utils.general import increment_path 11 | from utils.torch_utils import select_device 12 | 13 | 14 | def sweep(): 15 | wandb.init() 16 | # Get hyp dict from sweep agent 17 | hyp_dict = vars(wandb.config).get("_items") 18 | 19 | # Workaround: get necessary opt args 20 | opt = parse_opt(known=True) 21 | opt.batch_size = hyp_dict.get("batch_size") 22 | opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) 23 | opt.epochs = hyp_dict.get("epochs") 24 | opt.nosave = True 25 | opt.data = hyp_dict.get("data") 26 | device = select_device(opt.device, batch_size=opt.batch_size) 27 | 28 | # train 29 | train(hyp_dict, opt, device) 30 | 31 | 32 | if __name__ == "__main__": 33 | sweep() 34 | -------------------------------------------------------------------------------- /utils/loggers/wandb/sweep.yaml: -------------------------------------------------------------------------------- 1 | # Hyperparameters for training 2 | # To set range- 3 | # Provide min and max values as: 4 | # parameter: 5 | # 6 | # min: scalar 7 | # max: scalar 8 | # OR 9 | # 10 | # Set a specific list of search space- 11 | # parameter: 12 | # values: [scalar1, scalar2, scalar3...] 13 | # 14 | # You can use grid, bayesian and hyperopt search strategy 15 | # For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration 16 | 17 | program: utils/loggers/wandb/sweep.py 18 | method: random 19 | metric: 20 | name: metrics/mAP_0.5 21 | goal: maximize 22 | 23 | parameters: 24 | # hyperparameters: set either min, max range or values list 25 | data: 26 | value: "data/coco128.yaml" 27 | batch_size: 28 | values: [64] 29 | epochs: 30 | values: [10] 31 | 32 | lr0: 33 | distribution: uniform 34 | min: 1e-5 35 | max: 1e-1 36 | lrf: 37 | distribution: uniform 38 | min: 0.01 39 | max: 1.0 40 | momentum: 41 | distribution: uniform 42 | min: 0.6 43 | max: 0.98 44 | weight_decay: 45 | distribution: uniform 46 | min: 0.0 47 | max: 0.001 48 | warmup_epochs: 49 | distribution: uniform 50 | min: 0.0 51 | max: 5.0 52 | warmup_momentum: 53 | distribution: uniform 54 | min: 0.0 55 | max: 0.95 56 | warmup_bias_lr: 57 | distribution: uniform 58 | min: 0.0 59 | max: 0.2 60 | box: 61 | distribution: uniform 62 | min: 0.02 63 | max: 0.2 64 | cls: 65 | distribution: uniform 66 | min: 0.2 67 | max: 4.0 68 | cls_pw: 69 | distribution: uniform 70 | min: 0.5 71 | max: 2.0 72 | obj: 73 | distribution: uniform 74 | min: 0.2 75 | max: 4.0 76 | obj_pw: 77 | distribution: uniform 78 | min: 0.5 79 | max: 2.0 80 | iou_t: 81 | distribution: uniform 82 | min: 0.1 83 | max: 0.7 84 | anchor_t: 85 | distribution: uniform 86 | min: 2.0 87 | max: 8.0 88 | fl_gamma: 89 | distribution: uniform 90 | min: 0.0 91 | max: 0.1 92 | hsv_h: 93 | distribution: uniform 94 | min: 0.0 95 | max: 0.1 96 | hsv_s: 97 | distribution: uniform 98 | min: 0.0 99 | max: 0.9 100 | hsv_v: 101 | distribution: uniform 102 | min: 0.0 103 | max: 0.9 104 | degrees: 105 | distribution: uniform 106 | min: 0.0 107 | max: 45.0 108 | translate: 109 | distribution: uniform 110 | min: 0.0 111 | max: 0.9 112 | scale: 113 | distribution: uniform 114 | min: 0.0 115 | max: 0.9 116 | shear: 117 | distribution: uniform 118 | min: 0.0 119 | max: 10.0 120 | perspective: 121 | distribution: uniform 122 | min: 0.0 123 | max: 0.001 124 | flipud: 125 | distribution: uniform 126 | min: 0.0 127 | max: 1.0 128 | fliplr: 129 | distribution: uniform 130 | min: 0.0 131 | max: 1.0 132 | mosaic: 133 | distribution: uniform 134 | min: 0.0 135 | max: 1.0 136 | mixup: 137 | distribution: uniform 138 | min: 0.0 139 | max: 1.0 140 | copy_paste: 141 | distribution: uniform 142 | min: 0.0 143 | max: 1.0 144 | -------------------------------------------------------------------------------- /utils/loss.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Loss functions 4 | """ 5 | 6 | import torch 7 | import torch.nn as nn 8 | 9 | from utils.metrics import bbox_iou 10 | from utils.torch_utils import is_parallel 11 | 12 | 13 | def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441 14 | # return positive, negative label smoothing BCE targets 15 | return 1.0 - 0.5 * eps, 0.5 * eps 16 | 17 | 18 | class BCEBlurWithLogitsLoss(nn.Module): 19 | # BCEwithLogitLoss() with reduced missing label effects. 20 | def __init__(self, alpha=0.05): 21 | super(BCEBlurWithLogitsLoss, self).__init__() 22 | self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss() 23 | self.alpha = alpha 24 | 25 | def forward(self, pred, true): 26 | loss = self.loss_fcn(pred, true) 27 | pred = torch.sigmoid(pred) # prob from logits 28 | dx = pred - true # reduce only missing label effects 29 | # dx = (pred - true).abs() # reduce missing label and false label effects 30 | alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4)) 31 | loss *= alpha_factor 32 | return loss.mean() 33 | 34 | 35 | class FocalLoss(nn.Module): 36 | # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) 37 | def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): 38 | super(FocalLoss, self).__init__() 39 | self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() 40 | self.gamma = gamma 41 | self.alpha = alpha 42 | self.reduction = loss_fcn.reduction 43 | self.loss_fcn.reduction = 'none' # required to apply FL to each element 44 | 45 | def forward(self, pred, true): 46 | loss = self.loss_fcn(pred, true) 47 | # p_t = torch.exp(-loss) 48 | # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability 49 | 50 | # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py 51 | pred_prob = torch.sigmoid(pred) # prob from logits 52 | p_t = true * pred_prob + (1 - true) * (1 - pred_prob) 53 | alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) 54 | modulating_factor = (1.0 - p_t) ** self.gamma 55 | loss *= alpha_factor * modulating_factor 56 | 57 | if self.reduction == 'mean': 58 | return loss.mean() 59 | elif self.reduction == 'sum': 60 | return loss.sum() 61 | else: # 'none' 62 | return loss 63 | 64 | 65 | class QFocalLoss(nn.Module): 66 | # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5) 67 | def __init__(self, loss_fcn, gamma=1.5, alpha=0.25): 68 | super(QFocalLoss, self).__init__() 69 | self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss() 70 | self.gamma = gamma 71 | self.alpha = alpha 72 | self.reduction = loss_fcn.reduction 73 | self.loss_fcn.reduction = 'none' # required to apply FL to each element 74 | 75 | def forward(self, pred, true): 76 | loss = self.loss_fcn(pred, true) 77 | 78 | pred_prob = torch.sigmoid(pred) # prob from logits 79 | alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha) 80 | modulating_factor = torch.abs(true - pred_prob) ** self.gamma 81 | loss *= alpha_factor * modulating_factor 82 | 83 | if self.reduction == 'mean': 84 | return loss.mean() 85 | elif self.reduction == 'sum': 86 | return loss.sum() 87 | else: # 'none' 88 | return loss 89 | 90 | 91 | class ComputeLoss: 92 | # Compute losses 93 | def __init__(self, model, autobalance=False): 94 | super(ComputeLoss, self).__init__() 95 | self.sort_obj_iou = False 96 | device = next(model.parameters()).device # get model device 97 | h = model.hyp # hyperparameters 98 | 99 | # Define criteria 100 | BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) 101 | BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) 102 | 103 | # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 104 | self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets 105 | 106 | # Focal loss 107 | g = h['fl_gamma'] # focal loss gamma 108 | if g > 0: 109 | BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) 110 | 111 | det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module 112 | self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02]) # P3-P7 113 | self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index 114 | self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance 115 | for k in 'na', 'nc', 'nl', 'anchors': 116 | setattr(self, k, getattr(det, k)) 117 | 118 | def __call__(self, p, targets): # predictions, targets, model 119 | device = targets.device 120 | lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device) 121 | tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets 122 | 123 | # Losses 124 | for i, pi in enumerate(p): # layer index, layer predictions 125 | b, a, gj, gi = indices[i] # image, anchor, gridy, gridx 126 | tobj = torch.zeros_like(pi[..., 0], device=device) # target obj 127 | 128 | n = b.shape[0] # number of targets 129 | if n: 130 | ps = pi[b, a, gj, gi] # prediction subset corresponding to targets 131 | 132 | # Regression 133 | pxy = ps[:, :2].sigmoid() * 2. - 0.5 134 | pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i] 135 | pbox = torch.cat((pxy, pwh), 1) # predicted box 136 | iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) 137 | lbox += (1.0 - iou).mean() # iou loss 138 | 139 | # Objectness 140 | score_iou = iou.detach().clamp(0).type(tobj.dtype) 141 | if self.sort_obj_iou: 142 | sort_id = torch.argsort(score_iou) 143 | b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id] 144 | tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio 145 | 146 | # Classification 147 | if self.nc > 1: # cls loss (only if multiple classes) 148 | t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets 149 | t[range(n), tcls[i]] = self.cp 150 | lcls += self.BCEcls(ps[:, 5:], t) # BCE 151 | 152 | # Append targets to text file 153 | # with open('targets.txt', 'a') as file: 154 | # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] 155 | 156 | obji = self.BCEobj(pi[..., 4], tobj) 157 | lobj += obji * self.balance[i] # obj loss 158 | if self.autobalance: 159 | self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() 160 | 161 | if self.autobalance: 162 | self.balance = [x / self.balance[self.ssi] for x in self.balance] 163 | lbox *= self.hyp['box'] 164 | lobj *= self.hyp['obj'] 165 | lcls *= self.hyp['cls'] 166 | bs = tobj.shape[0] # batch size 167 | 168 | return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach() 169 | 170 | def build_targets(self, p, targets): 171 | # Build targets for compute_loss(), input targets(image,class,x,y,w,h) 172 | na, nt = self.na, targets.shape[0] # number of anchors, targets 173 | tcls, tbox, indices, anch = [], [], [], [] 174 | gain = torch.ones(7, device=targets.device) # normalized to gridspace gain 175 | ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) 176 | targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices 177 | 178 | g = 0.5 # bias 179 | off = torch.tensor([[0, 0], 180 | [1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m 181 | # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm 182 | ], device=targets.device).float() * g # offsets 183 | 184 | for i in range(self.nl): 185 | anchors = self.anchors[i] 186 | gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain 187 | 188 | # Match targets to anchors 189 | t = targets * gain 190 | if nt: 191 | # Matches 192 | r = t[:, :, 4:6] / anchors[:, None] # wh ratio 193 | j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t'] # compare 194 | # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) 195 | t = t[j] # filter 196 | 197 | # Offsets 198 | gxy = t[:, 2:4] # grid xy 199 | gxi = gain[[2, 3]] - gxy # inverse 200 | j, k = ((gxy % 1. < g) & (gxy > 1.)).T 201 | l, m = ((gxi % 1. < g) & (gxi > 1.)).T 202 | j = torch.stack((torch.ones_like(j), j, k, l, m)) 203 | t = t.repeat((5, 1, 1))[j] 204 | offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] 205 | else: 206 | t = targets[0] 207 | offsets = 0 208 | 209 | # Define 210 | b, c = t[:, :2].long().T # image, class 211 | gxy = t[:, 2:4] # grid xy 212 | gwh = t[:, 4:6] # grid wh 213 | gij = (gxy - offsets).long() 214 | gi, gj = gij.T # grid xy indices 215 | 216 | # Append 217 | a = t[:, 6].long() # anchor indices 218 | indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices 219 | tbox.append(torch.cat((gxy - gij, gwh), 1)) # box 220 | anch.append(anchors[a]) # anchors 221 | tcls.append(c) # class 222 | 223 | return tcls, tbox, indices, anch 224 | -------------------------------------------------------------------------------- /utils/metrics.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Model validation metrics 4 | """ 5 | 6 | import math 7 | import warnings 8 | from pathlib import Path 9 | 10 | import matplotlib.pyplot as plt 11 | import numpy as np 12 | import torch 13 | 14 | 15 | def fitness(x): 16 | # Model fitness as a weighted combination of metrics 17 | w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95] 18 | return (x[:, :4] * w).sum(1) 19 | 20 | 21 | def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()): 22 | """ Compute the average precision, given the recall and precision curves. 23 | Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. 24 | # Arguments 25 | tp: True positives (nparray, nx1 or nx10). 26 | conf: Objectness value from 0-1 (nparray). 27 | pred_cls: Predicted object classes (nparray). 28 | target_cls: True object classes (nparray). 29 | plot: Plot precision-recall curve at mAP@0.5 30 | save_dir: Plot save directory 31 | # Returns 32 | The average precision as computed in py-faster-rcnn. 33 | """ 34 | 35 | # Sort by objectness 36 | i = np.argsort(-conf) 37 | tp, conf, pred_cls = tp[i], conf[i], pred_cls[i] 38 | 39 | # Find unique classes 40 | unique_classes = np.unique(target_cls) 41 | nc = unique_classes.shape[0] # number of classes, number of detections 42 | 43 | # Create Precision-Recall curve and compute AP for each class 44 | px, py = np.linspace(0, 1, 1000), [] # for plotting 45 | ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000)) 46 | for ci, c in enumerate(unique_classes): 47 | i = pred_cls == c 48 | n_l = (target_cls == c).sum() # number of labels 49 | n_p = i.sum() # number of predictions 50 | 51 | if n_p == 0 or n_l == 0: 52 | continue 53 | else: 54 | # Accumulate FPs and TPs 55 | fpc = (1 - tp[i]).cumsum(0) 56 | tpc = tp[i].cumsum(0) 57 | 58 | # Recall 59 | recall = tpc / (n_l + 1e-16) # recall curve 60 | r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases 61 | 62 | # Precision 63 | precision = tpc / (tpc + fpc) # precision curve 64 | p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score 65 | 66 | # AP from recall-precision curve 67 | for j in range(tp.shape[1]): 68 | ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j]) 69 | if plot and j == 0: 70 | py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5 71 | 72 | # Compute F1 (harmonic mean of precision and recall) 73 | f1 = 2 * p * r / (p + r + 1e-16) 74 | if plot: 75 | plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names) 76 | plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1') 77 | plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision') 78 | plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall') 79 | 80 | i = f1.mean(0).argmax() # max F1 index 81 | return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32') 82 | 83 | 84 | def compute_ap(recall, precision): 85 | """ Compute the average precision, given the recall and precision curves 86 | # Arguments 87 | recall: The recall curve (list) 88 | precision: The precision curve (list) 89 | # Returns 90 | Average precision, precision curve, recall curve 91 | """ 92 | 93 | # Append sentinel values to beginning and end 94 | mrec = np.concatenate(([0.0], recall, [1.0])) 95 | mpre = np.concatenate(([1.0], precision, [0.0])) 96 | 97 | # Compute the precision envelope 98 | mpre = np.flip(np.maximum.accumulate(np.flip(mpre))) 99 | 100 | # Integrate area under curve 101 | method = 'interp' # methods: 'continuous', 'interp' 102 | if method == 'interp': 103 | x = np.linspace(0, 1, 101) # 101-point interp (COCO) 104 | ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate 105 | else: # 'continuous' 106 | i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes 107 | ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve 108 | 109 | return ap, mpre, mrec 110 | 111 | 112 | class ConfusionMatrix: 113 | # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix 114 | def __init__(self, nc, conf=0.25, iou_thres=0.45): 115 | self.matrix = np.zeros((nc + 1, nc + 1)) 116 | self.nc = nc # number of classes 117 | self.conf = conf 118 | self.iou_thres = iou_thres 119 | 120 | def process_batch(self, detections, labels): 121 | """ 122 | Return intersection-over-union (Jaccard index) of boxes. 123 | Both sets of boxes are expected to be in (x1, y1, x2, y2) format. 124 | Arguments: 125 | detections (Array[N, 6]), x1, y1, x2, y2, conf, class 126 | labels (Array[M, 5]), class, x1, y1, x2, y2 127 | Returns: 128 | None, updates confusion matrix accordingly 129 | """ 130 | detections = detections[detections[:, 4] > self.conf] 131 | gt_classes = labels[:, 0].int() 132 | detection_classes = detections[:, 5].int() 133 | iou = box_iou(labels[:, 1:], detections[:, :4]) 134 | 135 | x = torch.where(iou > self.iou_thres) 136 | if x[0].shape[0]: 137 | matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy() 138 | if x[0].shape[0] > 1: 139 | matches = matches[matches[:, 2].argsort()[::-1]] 140 | matches = matches[np.unique(matches[:, 1], return_index=True)[1]] 141 | matches = matches[matches[:, 2].argsort()[::-1]] 142 | matches = matches[np.unique(matches[:, 0], return_index=True)[1]] 143 | else: 144 | matches = np.zeros((0, 3)) 145 | 146 | n = matches.shape[0] > 0 147 | m0, m1, _ = matches.transpose().astype(np.int16) 148 | for i, gc in enumerate(gt_classes): 149 | j = m0 == i 150 | if n and sum(j) == 1: 151 | self.matrix[detection_classes[m1[j]], gc] += 1 # correct 152 | else: 153 | self.matrix[self.nc, gc] += 1 # background FP 154 | 155 | if n: 156 | for i, dc in enumerate(detection_classes): 157 | if not any(m1 == i): 158 | self.matrix[dc, self.nc] += 1 # background FN 159 | 160 | def matrix(self): 161 | return self.matrix 162 | 163 | def plot(self, normalize=True, save_dir='', names=()): 164 | try: 165 | import seaborn as sn 166 | 167 | array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-6) if normalize else 1) # normalize columns 168 | array[array < 0.005] = np.nan # don't annotate (would appear as 0.00) 169 | 170 | fig = plt.figure(figsize=(12, 9), tight_layout=True) 171 | sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size 172 | labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels 173 | with warnings.catch_warnings(): 174 | warnings.simplefilter('ignore') # suppress empty matrix RuntimeWarning: All-NaN slice encountered 175 | sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True, 176 | xticklabels=names + ['background FP'] if labels else "auto", 177 | yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1)) 178 | fig.axes[0].set_xlabel('True') 179 | fig.axes[0].set_ylabel('Predicted') 180 | fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250) 181 | plt.close() 182 | except Exception as e: 183 | print(f'WARNING: ConfusionMatrix plot failure: {e}') 184 | 185 | def print(self): 186 | for i in range(self.nc + 1): 187 | print(' '.join(map(str, self.matrix[i]))) 188 | 189 | 190 | def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7): 191 | # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4 192 | box2 = box2.T 193 | 194 | # Get the coordinates of bounding boxes 195 | if x1y1x2y2: # x1, y1, x2, y2 = box1 196 | b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] 197 | b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] 198 | else: # transform from xywh to xyxy 199 | b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2 200 | b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2 201 | b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2 202 | b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2 203 | 204 | # Intersection area 205 | inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \ 206 | (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0) 207 | 208 | # Union Area 209 | w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps 210 | w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps 211 | union = w1 * h1 + w2 * h2 - inter + eps 212 | 213 | iou = inter / union 214 | if GIoU or DIoU or CIoU: 215 | cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width 216 | ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height 217 | if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1 218 | c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared 219 | rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + 220 | (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared 221 | if DIoU: 222 | return iou - rho2 / c2 # DIoU 223 | elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47 224 | v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2) 225 | with torch.no_grad(): 226 | alpha = v / (v - iou + (1 + eps)) 227 | return iou - (rho2 / c2 + v * alpha) # CIoU 228 | else: # GIoU https://arxiv.org/pdf/1902.09630.pdf 229 | c_area = cw * ch + eps # convex area 230 | return iou - (c_area - union) / c_area # GIoU 231 | else: 232 | return iou # IoU 233 | 234 | 235 | def box_iou(box1, box2): 236 | # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py 237 | """ 238 | Return intersection-over-union (Jaccard index) of boxes. 239 | Both sets of boxes are expected to be in (x1, y1, x2, y2) format. 240 | Arguments: 241 | box1 (Tensor[N, 4]) 242 | box2 (Tensor[M, 4]) 243 | Returns: 244 | iou (Tensor[N, M]): the NxM matrix containing the pairwise 245 | IoU values for every element in boxes1 and boxes2 246 | """ 247 | 248 | def box_area(box): 249 | # box = 4xn 250 | return (box[2] - box[0]) * (box[3] - box[1]) 251 | 252 | area1 = box_area(box1.T) 253 | area2 = box_area(box2.T) 254 | 255 | # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2) 256 | inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2) 257 | return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter) 258 | 259 | 260 | def bbox_ioa(box1, box2, eps=1E-7): 261 | """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2 262 | box1: np.array of shape(4) 263 | box2: np.array of shape(nx4) 264 | returns: np.array of shape(n) 265 | """ 266 | 267 | box2 = box2.transpose() 268 | 269 | # Get the coordinates of bounding boxes 270 | b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] 271 | b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] 272 | 273 | # Intersection area 274 | inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ 275 | (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0) 276 | 277 | # box2 area 278 | box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps 279 | 280 | # Intersection over box2 area 281 | return inter_area / box2_area 282 | 283 | 284 | def wh_iou(wh1, wh2): 285 | # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2 286 | wh1 = wh1[:, None] # [N,1,2] 287 | wh2 = wh2[None] # [1,M,2] 288 | inter = torch.min(wh1, wh2).prod(2) # [N,M] 289 | return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter) 290 | 291 | 292 | # Plots ---------------------------------------------------------------------------------------------------------------- 293 | 294 | def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()): 295 | # Precision-recall curve 296 | fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) 297 | py = np.stack(py, axis=1) 298 | 299 | if 0 < len(names) < 21: # display per-class legend if < 21 classes 300 | for i, y in enumerate(py.T): 301 | ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision) 302 | else: 303 | ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision) 304 | 305 | ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean()) 306 | ax.set_xlabel('Recall') 307 | ax.set_ylabel('Precision') 308 | ax.set_xlim(0, 1) 309 | ax.set_ylim(0, 1) 310 | plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") 311 | fig.savefig(Path(save_dir), dpi=250) 312 | plt.close() 313 | 314 | 315 | def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'): 316 | # Metric-confidence curve 317 | fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True) 318 | 319 | if 0 < len(names) < 21: # display per-class legend if < 21 classes 320 | for i, y in enumerate(py): 321 | ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric) 322 | else: 323 | ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric) 324 | 325 | y = py.mean(0) 326 | ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}') 327 | ax.set_xlabel(xlabel) 328 | ax.set_ylabel(ylabel) 329 | ax.set_xlim(0, 1) 330 | ax.set_ylim(0, 1) 331 | plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left") 332 | fig.savefig(Path(save_dir), dpi=250) 333 | plt.close() 334 | --------------------------------------------------------------------------------