├── .dockerignore ├── .gitattributes ├── .github ├── ISSUE_TEMPLATE │ ├── bug-report.md │ ├── feature-request.md │ └── question.md ├── dependabot.yml └── workflows │ ├── ci-testing.yml │ ├── codeql-analysis.yml │ ├── greetings.yml │ ├── rebase.yml │ └── stale.yml ├── .gitignore ├── .pre-commit-config.yaml ├── CONTRIBUTING.md ├── Dockerfile ├── LICENSE ├── README.md ├── data ├── Argoverse.yaml ├── GlobalWheat2020.yaml ├── Objects365.yaml ├── SKU-110K.yaml ├── VisDrone.yaml ├── coco.yaml ├── coco128.yaml ├── hyps │ ├── hyp.finetune.yaml │ ├── hyp.finetune_objects365.yaml │ ├── hyp.scratch-high.yaml │ ├── hyp.scratch-low.yaml │ ├── hyp.scratch-med.yaml │ └── hyp.scratch.yaml ├── images │ ├── test-1.jpg │ └── test-2.jpg ├── mask.yaml ├── scripts │ ├── download_weights.sh │ ├── get_coco.sh │ └── get_coco128.sh ├── voc.yaml └── xView.yaml ├── detect.py ├── export.py ├── hubconf.py ├── models ├── __init__.py ├── common.py ├── common_rk_plug_in.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 │ ├── yolov5n6.yaml │ ├── yolov5s-ghost.yaml │ ├── yolov5s-transformer.yaml │ ├── yolov5s6.yaml │ └── yolov5x6.yaml ├── tf.py ├── yolo.py ├── yolov5l.yaml ├── yolov5m.yaml ├── yolov5n.yaml ├── yolov5s.yaml └── yolov5x.yaml ├── photo └── image.jpg ├── requirements.txt ├── setup.cfg ├── train.py ├── tutorial.ipynb ├── utils ├── __init__.py ├── activations.py ├── augmentations.py ├── autoanchor.py ├── autobatch.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 /.dockerignore: -------------------------------------------------------------------------------- 1 | # Repo-specific DockerIgnore ------------------------------------------------------------------------------------------- 2 | #.git 3 | .cache 4 | .idea 5 | runs 6 | output 7 | coco 8 | storage.googleapis.com 9 | 10 | data/samples/* 11 | **/results*.csv 12 | *.jpg 13 | 14 | # Neural Network weights ----------------------------------------------------------------------------------------------- 15 | **/*.pt 16 | **/*.pth 17 | **/*.onnx 18 | **/*.engine 19 | **/*.mlmodel 20 | **/*.torchscript 21 | **/*.torchscript.pt 22 | **/*.tflite 23 | **/*.h5 24 | **/*.pb 25 | *_saved_model/ 26 | *_web_model/ 27 | 28 | # Below Copied From .gitignore ----------------------------------------------------------------------------------------- 29 | # Below Copied From .gitignore ----------------------------------------------------------------------------------------- 30 | 31 | 32 | # GitHub Python GitIgnore ---------------------------------------------------------------------------------------------- 33 | # Byte-compiled / optimized / DLL files 34 | __pycache__/ 35 | *.py[cod] 36 | *$py.class 37 | 38 | # C extensions 39 | *.so 40 | 41 | # Distribution / packaging 42 | .Python 43 | env/ 44 | build/ 45 | develop-eggs/ 46 | dist/ 47 | downloads/ 48 | eggs/ 49 | .eggs/ 50 | lib/ 51 | lib64/ 52 | parts/ 53 | sdist/ 54 | var/ 55 | wheels/ 56 | *.egg-info/ 57 | wandb/ 58 | .installed.cfg 59 | *.egg 60 | 61 | # PyInstaller 62 | # Usually these files are written by a python script from a template 63 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 64 | *.manifest 65 | *.spec 66 | 67 | # Installer logs 68 | pip-log.txt 69 | pip-delete-this-directory.txt 70 | 71 | # Unit test / coverage reports 72 | htmlcov/ 73 | .tox/ 74 | .coverage 75 | .coverage.* 76 | .cache 77 | nosetests.xml 78 | coverage.xml 79 | *.cover 80 | .hypothesis/ 81 | 82 | # Translations 83 | *.mo 84 | *.pot 85 | 86 | # Django stuff: 87 | *.log 88 | local_settings.py 89 | 90 | # Flask stuff: 91 | instance/ 92 | .webassets-cache 93 | 94 | # Scrapy stuff: 95 | .scrapy 96 | 97 | # Sphinx documentation 98 | docs/_build/ 99 | 100 | # PyBuilder 101 | target/ 102 | 103 | # Jupyter Notebook 104 | .ipynb_checkpoints 105 | 106 | # pyenv 107 | .python-version 108 | 109 | # celery beat schedule file 110 | celerybeat-schedule 111 | 112 | # SageMath parsed files 113 | *.sage.py 114 | 115 | # dotenv 116 | .env 117 | 118 | # virtualenv 119 | .venv* 120 | venv*/ 121 | ENV*/ 122 | 123 | # Spyder project settings 124 | .spyderproject 125 | .spyproject 126 | 127 | # Rope project settings 128 | .ropeproject 129 | 130 | # mkdocs documentation 131 | /site 132 | 133 | # mypy 134 | .mypy_cache/ 135 | 136 | 137 | # https://github.com/github/gitignore/blob/master/Global/macOS.gitignore ----------------------------------------------- 138 | 139 | # General 140 | .DS_Store 141 | .AppleDouble 142 | .LSOverride 143 | 144 | # Icon must end with two \r 145 | Icon 146 | Icon? 147 | 148 | # Thumbnails 149 | ._* 150 | 151 | # Files that might appear in the root of a volume 152 | .DocumentRevisions-V100 153 | .fseventsd 154 | .Spotlight-V100 155 | .TemporaryItems 156 | .Trashes 157 | .VolumeIcon.icns 158 | .com.apple.timemachine.donotpresent 159 | 160 | # Directories potentially created on remote AFP share 161 | .AppleDB 162 | .AppleDesktop 163 | Network Trash Folder 164 | Temporary Items 165 | .apdisk 166 | 167 | 168 | # https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore 169 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 170 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 171 | 172 | # User-specific stuff: 173 | .idea/* 174 | .idea/**/workspace.xml 175 | .idea/**/tasks.xml 176 | .idea/dictionaries 177 | .html # Bokeh Plots 178 | .pg # TensorFlow Frozen Graphs 179 | .avi # videos 180 | 181 | # Sensitive or high-churn files: 182 | .idea/**/dataSources/ 183 | .idea/**/dataSources.ids 184 | .idea/**/dataSources.local.xml 185 | .idea/**/sqlDataSources.xml 186 | .idea/**/dynamic.xml 187 | .idea/**/uiDesigner.xml 188 | 189 | # Gradle: 190 | .idea/**/gradle.xml 191 | .idea/**/libraries 192 | 193 | # CMake 194 | cmake-build-debug/ 195 | cmake-build-release/ 196 | 197 | # Mongo Explorer plugin: 198 | .idea/**/mongoSettings.xml 199 | 200 | ## File-based project format: 201 | *.iws 202 | 203 | ## Plugin-specific files: 204 | 205 | # IntelliJ 206 | out/ 207 | 208 | # mpeltonen/sbt-idea plugin 209 | .idea_modules/ 210 | 211 | # JIRA plugin 212 | atlassian-ide-plugin.xml 213 | 214 | # Cursive Clojure plugin 215 | .idea/replstate.xml 216 | 217 | # Crashlytics plugin (for Android Studio and IntelliJ) 218 | com_crashlytics_export_strings.xml 219 | crashlytics.properties 220 | crashlytics-build.properties 221 | fabric.properties 222 | -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | # this drop notebooks from GitHub language stats 2 | *.ipynb linguist-vendored 3 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug-report.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: "🐛 Bug report" 3 | about: Create a report to help us improve 4 | title: '' 5 | labels: bug 6 | assignees: '' 7 | 8 | --- 9 | 10 | Before submitting a bug report, please be aware that your issue **must be reproducible** with all of the following, otherwise it is non-actionable, and we can not help you: 11 | - **Current repo**: run `git fetch && git status -uno` to check and `git pull` to update repo 12 | - **Common dataset**: coco.yaml or coco128.yaml 13 | - **Common environment**: Colab, Google Cloud, or Docker image. See https://github.com/ultralytics/yolov5#environments 14 | 15 | If this is a custom dataset/training question you **must include** your `train*.jpg`, `test*.jpg` and `results.png` figures, or we can not help you. You can generate these with `utils.plot_results()`. 16 | 17 | 18 | ## 🐛 Bug 19 | A clear and concise description of what the bug is. 20 | 21 | 22 | ## To Reproduce (REQUIRED) 23 | 24 | Input: 25 | ``` 26 | import torch 27 | 28 | a = torch.tensor([5]) 29 | c = a / 0 30 | ``` 31 | 32 | Output: 33 | ``` 34 | Traceback (most recent call last): 35 | File "/Users/glennjocher/opt/anaconda3/envs/env1/lib/python3.7/site-packages/IPython/core/interactiveshell.py", line 3331, in run_code 36 | exec(code_obj, self.user_global_ns, self.user_ns) 37 | File "", line 5, in 38 | c = a / 0 39 | RuntimeError: ZeroDivisionError 40 | ``` 41 | 42 | 43 | ## Expected behavior 44 | A clear and concise description of what you expected to happen. 45 | 46 | 47 | ## Environment 48 | If applicable, add screenshots to help explain your problem. 49 | 50 | - OS: [e.g. Ubuntu] 51 | - GPU [e.g. 2080 Ti] 52 | 53 | 54 | ## Additional context 55 | Add any other context about the problem here. 56 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature-request.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: "🚀 Feature request" 3 | about: Suggest an idea for this project 4 | title: '' 5 | labels: enhancement 6 | assignees: '' 7 | 8 | --- 9 | 10 | ## 🚀 Feature 11 | 12 | 13 | ## Motivation 14 | 15 | 16 | 17 | ## Pitch 18 | 19 | 20 | 21 | ## Alternatives 22 | 23 | 24 | 25 | ## Additional context 26 | 27 | 28 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/question.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: "❓Question" 3 | about: Ask a general question 4 | title: '' 5 | labels: question 6 | assignees: '' 7 | 8 | --- 9 | 10 | ## ❔Question 11 | 12 | 13 | ## Additional context 14 | -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- 1 | version: 2 2 | updates: 3 | - package-ecosystem: pip 4 | directory: "/" 5 | schedule: 6 | interval: weekly 7 | time: "04:00" 8 | open-pull-requests-limit: 10 9 | reviewers: 10 | - glenn-jocher 11 | labels: 12 | - dependencies 13 | -------------------------------------------------------------------------------- /.github/workflows/ci-testing.yml: -------------------------------------------------------------------------------- 1 | name: CI CPU testing 2 | 3 | on: # https://help.github.com/en/actions/reference/events-that-trigger-workflows 4 | push: 5 | branches: [ master ] 6 | pull_request: 7 | # The branches below must be a subset of the branches above 8 | branches: [ master ] 9 | schedule: 10 | - cron: '0 0 * * *' # Runs at 00:00 UTC every day 11 | 12 | jobs: 13 | cpu-tests: 14 | 15 | runs-on: ${{ matrix.os }} 16 | strategy: 17 | fail-fast: false 18 | matrix: 19 | os: [ubuntu-latest, macos-latest, windows-latest] 20 | python-version: [3.8] 21 | model: ['yolov5s'] # models to test 22 | 23 | # Timeout: https://stackoverflow.com/a/59076067/4521646 24 | timeout-minutes: 50 25 | steps: 26 | - uses: actions/checkout@v2 27 | - name: Set up Python ${{ matrix.python-version }} 28 | uses: actions/setup-python@v2 29 | with: 30 | python-version: ${{ matrix.python-version }} 31 | 32 | # Note: This uses an internal pip API and may not always work 33 | # https://github.com/actions/cache/blob/master/examples.md#multiple-oss-in-a-workflow 34 | - name: Get pip cache 35 | id: pip-cache 36 | run: | 37 | python -c "from pip._internal.locations import USER_CACHE_DIR; print('::set-output name=dir::' + USER_CACHE_DIR)" 38 | 39 | - name: Cache pip 40 | uses: actions/cache@v1 41 | with: 42 | path: ${{ steps.pip-cache.outputs.dir }} 43 | key: ${{ runner.os }}-${{ matrix.python-version }}-pip-${{ hashFiles('requirements.txt') }} 44 | restore-keys: | 45 | ${{ runner.os }}-${{ matrix.python-version }}-pip- 46 | 47 | - name: Install dependencies 48 | run: | 49 | python -m pip install --upgrade pip 50 | pip install -qr requirements.txt -f https://download.pytorch.org/whl/cpu/torch_stable.html 51 | pip install -q onnx 52 | python --version 53 | pip --version 54 | pip list 55 | shell: bash 56 | 57 | - name: Download data 58 | run: | 59 | # curl -L -o tmp.zip https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip 60 | # unzip -q tmp.zip -d ../ 61 | # rm tmp.zip 62 | 63 | - name: Tests workflow 64 | run: | 65 | # export PYTHONPATH="$PWD" # to run '$ python *.py' files in subdirectories 66 | di=cpu # inference devices # define device 67 | 68 | # train 69 | python train.py --img 128 --batch 16 --weights weights/${{ matrix.model }}.pt --cfg models/${{ matrix.model }}.yaml --epochs 1 --device $di 70 | # detect 71 | python detect.py --weights weights/${{ matrix.model }}.pt --device $di 72 | python detect.py --weights runs/train/exp/weights/last.pt --device $di 73 | # test 74 | python test.py --img 128 --batch 16 --weights weights/${{ matrix.model }}.pt --device $di 75 | python test.py --img 128 --batch 16 --weights runs/train/exp/weights/last.pt --device $di 76 | 77 | python hubconf.py # hub 78 | python models/yolo.py --cfg models/${{ matrix.model }}.yaml # inspect 79 | python models/export.py --img 128 --batch 1 --weights weights/${{ matrix.model }}.pt # export 80 | shell: bash 81 | -------------------------------------------------------------------------------- /.github/workflows/codeql-analysis.yml: -------------------------------------------------------------------------------- 1 | # This action runs GitHub's industry-leading static analysis engine, CodeQL, against a repository's source code to find security vulnerabilities. 2 | # https://github.com/github/codeql-action 3 | 4 | name: "CodeQL" 5 | 6 | on: 7 | schedule: 8 | - cron: '0 0 1 * *' # Runs at 00:00 UTC on the 1st of every month 9 | 10 | jobs: 11 | analyze: 12 | name: Analyze 13 | runs-on: ubuntu-latest 14 | 15 | strategy: 16 | fail-fast: false 17 | matrix: 18 | language: [ 'python' ] 19 | # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ] 20 | # Learn more: 21 | # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed 22 | 23 | steps: 24 | - name: Checkout repository 25 | uses: actions/checkout@v2 26 | 27 | # Initializes the CodeQL tools for scanning. 28 | - name: Initialize CodeQL 29 | uses: github/codeql-action/init@v1 30 | with: 31 | languages: ${{ matrix.language }} 32 | # If you wish to specify custom queries, you can do so here or in a config file. 33 | # By default, queries listed here will override any specified in a config file. 34 | # Prefix the list here with "+" to use these queries and those in the config file. 35 | # queries: ./path/to/local/query, your-org/your-repo/queries@main 36 | 37 | # Autobuild attempts to build any compiled languages (C/C++, C#, or Java). 38 | # If this step fails, then you should remove it and run the build manually (see below) 39 | - name: Autobuild 40 | uses: github/codeql-action/autobuild@v1 41 | 42 | # ℹ️ Command-line programs to run using the OS shell. 43 | # 📚 https://git.io/JvXDl 44 | 45 | # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines 46 | # and modify them (or add more) to build your code if your project 47 | # uses a compiled language 48 | 49 | #- run: | 50 | # make bootstrap 51 | # make release 52 | 53 | - name: Perform CodeQL Analysis 54 | uses: github/codeql-action/analyze@v1 55 | -------------------------------------------------------------------------------- /.github/workflows/greetings.yml: -------------------------------------------------------------------------------- 1 | name: Greetings 2 | 3 | on: [pull_request_target, issues] 4 | 5 | jobs: 6 | greeting: 7 | runs-on: ubuntu-latest 8 | steps: 9 | - uses: actions/first-interaction@v1 10 | with: 11 | repo-token: ${{ secrets.GITHUB_TOKEN }} 12 | pr-message: | 13 | 👋 Hello @${{ github.actor }}, thank you for submitting a 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to: 14 | - ✅ Verify your PR is **up-to-date with origin/master.** If your PR is behind origin/master an automatic [GitHub actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) rebase may be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature' with the name of your local branch: 15 | ```bash 16 | git remote add upstream https://github.com/ultralytics/yolov5.git 17 | git fetch upstream 18 | git checkout feature # <----- replace 'feature' with local branch name 19 | git rebase upstream/master 20 | git push -u origin -f 21 | ``` 22 | - ✅ Verify all Continuous Integration (CI) **checks are passing**. 23 | - ✅ Reduce changes to the absolute **minimum** required for your bug fix or feature addition. _"It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is."_ -Bruce Lee 24 | 25 | issue-message: | 26 | 👋 Hello @${{ github.actor }}, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ [Tutorials](https://github.com/ultralytics/yolov5/wiki#tutorials) to get started, where you can find quickstart guides for simple tasks like [Custom Data Training](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data) all the way to advanced concepts like [Hyperparameter Evolution](https://github.com/ultralytics/yolov5/issues/607). 27 | 28 | If this is a 🐛 Bug Report, please provide screenshots and **minimum viable code to reproduce your issue**, otherwise we can not help you. 29 | 30 | If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online [W&B logging](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data#visualize) if available. 31 | 32 | For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com. 33 | 34 | ## Requirements 35 | 36 | Python 3.8 or later with all [requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) dependencies installed, including `torch>=1.7`. To install run: 37 | ```bash 38 | $ pip install -r requirements.txt 39 | ``` 40 | 41 | ## Environments 42 | 43 | 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): 44 | 45 | - **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle 46 | - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 47 | - **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) 48 | - **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls 49 | 50 | 51 | ## Status 52 | 53 | ![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) 54 | 55 | 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)), testing ([test.py](https://github.com/ultralytics/yolov5/blob/master/test.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/models/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit. 56 | 57 | -------------------------------------------------------------------------------- /.github/workflows/rebase.yml: -------------------------------------------------------------------------------- 1 | name: Automatic Rebase 2 | # https://github.com/marketplace/actions/automatic-rebase 3 | 4 | on: 5 | issue_comment: 6 | types: [created] 7 | 8 | jobs: 9 | rebase: 10 | name: Rebase 11 | if: github.event.issue.pull_request != '' && contains(github.event.comment.body, '/rebase') 12 | runs-on: ubuntu-latest 13 | steps: 14 | - name: Checkout the latest code 15 | uses: actions/checkout@v2 16 | with: 17 | fetch-depth: 0 18 | - name: Automatic Rebase 19 | uses: cirrus-actions/rebase@1.3.1 20 | env: 21 | GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} 22 | -------------------------------------------------------------------------------- /.github/workflows/stale.yml: -------------------------------------------------------------------------------- 1 | name: Close stale issues 2 | on: 3 | schedule: 4 | - cron: "0 0 * * *" 5 | 6 | jobs: 7 | stale: 8 | runs-on: ubuntu-latest 9 | steps: 10 | - uses: actions/stale@v3 11 | with: 12 | repo-token: ${{ secrets.GITHUB_TOKEN }} 13 | stale-issue-message: 'This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.' 14 | stale-pr-message: 'This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.' 15 | days-before-stale: 30 16 | days-before-close: 5 17 | exempt-issue-labels: 'documentation,tutorial' 18 | operations-per-run: 100 # The maximum number of operations per run, used to control rate limiting. 19 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Repo-specific GitIgnore ---------------------------------------------------------------------------------------------- 2 | *.tif 3 | *.tiff 4 | *.heic 5 | *.TIF 6 | *.TIFF 7 | *.HEIC 8 | *.mp4 9 | *.mov 10 | *.MOV 11 | *.avi 12 | *.data 13 | *.json 14 | *.cfg 15 | !setup.cfg 16 | !cfg/yolov3*.cfg 17 | 18 | storage.googleapis.com 19 | runs/* 20 | data/* 21 | !data/images 22 | !data/*.yaml 23 | !data/hyps 24 | !data/scripts 25 | !data/images 26 | !data/images/zidane.jpg 27 | !data/images/bus.jpg 28 | !data/*.sh 29 | 30 | results*.csv 31 | 32 | # Datasets ------------------------------------------------------------------------------------------------------------- 33 | coco/ 34 | coco128/ 35 | VOC/ 36 | 37 | # MATLAB GitIgnore ----------------------------------------------------------------------------------------------------- 38 | *.m~ 39 | *.mat 40 | !targets*.mat 41 | 42 | # Neural Network weights ----------------------------------------------------------------------------------------------- 43 | *.weights 44 | *.pt 45 | *.pb 46 | *.onnx 47 | *.engine 48 | *.mlmodel 49 | *.torchscript 50 | *.tflite 51 | *.h5 52 | *_saved_model/ 53 | *_web_model/ 54 | darknet53.conv.74 55 | yolov3-tiny.conv.15 56 | 57 | # GitHub Python GitIgnore ---------------------------------------------------------------------------------------------- 58 | # Byte-compiled / optimized / DLL files 59 | __pycache__/ 60 | *.py[cod] 61 | *$py.class 62 | 63 | # C extensions 64 | *.so 65 | 66 | # Distribution / packaging 67 | .Python 68 | env/ 69 | build/ 70 | develop-eggs/ 71 | dist/ 72 | downloads/ 73 | eggs/ 74 | .eggs/ 75 | lib/ 76 | lib64/ 77 | parts/ 78 | sdist/ 79 | var/ 80 | wheels/ 81 | *.egg-info/ 82 | /wandb/ 83 | .installed.cfg 84 | *.egg 85 | 86 | 87 | # PyInstaller 88 | # Usually these files are written by a python script from a template 89 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 90 | *.manifest 91 | *.spec 92 | 93 | # Installer logs 94 | pip-log.txt 95 | pip-delete-this-directory.txt 96 | 97 | # Unit test / coverage reports 98 | htmlcov/ 99 | .tox/ 100 | .coverage 101 | .coverage.* 102 | .cache 103 | nosetests.xml 104 | coverage.xml 105 | *.cover 106 | .hypothesis/ 107 | 108 | # Translations 109 | *.mo 110 | *.pot 111 | 112 | # Django stuff: 113 | *.log 114 | local_settings.py 115 | 116 | # Flask stuff: 117 | instance/ 118 | .webassets-cache 119 | 120 | # Scrapy stuff: 121 | .scrapy 122 | 123 | # Sphinx documentation 124 | docs/_build/ 125 | 126 | # PyBuilder 127 | target/ 128 | 129 | # Jupyter Notebook 130 | .ipynb_checkpoints 131 | 132 | # pyenv 133 | .python-version 134 | 135 | # celery beat schedule file 136 | celerybeat-schedule 137 | 138 | # SageMath parsed files 139 | *.sage.py 140 | 141 | # dotenv 142 | .env 143 | 144 | # virtualenv 145 | .venv* 146 | venv*/ 147 | ENV*/ 148 | 149 | # Spyder project settings 150 | .spyderproject 151 | .spyproject 152 | 153 | # Rope project settings 154 | .ropeproject 155 | 156 | # mkdocs documentation 157 | /site 158 | 159 | # mypy 160 | .mypy_cache/ 161 | 162 | 163 | # https://github.com/github/gitignore/blob/master/Global/macOS.gitignore ----------------------------------------------- 164 | 165 | # General 166 | .DS_Store 167 | .AppleDouble 168 | .LSOverride 169 | 170 | # Icon must end with two \r 171 | Icon 172 | Icon? 173 | 174 | # Thumbnails 175 | ._* 176 | 177 | # Files that might appear in the root of a volume 178 | .DocumentRevisions-V100 179 | .fseventsd 180 | .Spotlight-V100 181 | .TemporaryItems 182 | .Trashes 183 | .VolumeIcon.icns 184 | .com.apple.timemachine.donotpresent 185 | 186 | # Directories potentially created on remote AFP share 187 | .AppleDB 188 | .AppleDesktop 189 | Network Trash Folder 190 | Temporary Items 191 | .apdisk 192 | 193 | 194 | # https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore 195 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm 196 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 197 | 198 | # User-specific stuff: 199 | .idea/* 200 | .idea/**/workspace.xml 201 | .idea/**/tasks.xml 202 | .idea/dictionaries 203 | .html # Bokeh Plots 204 | .pg # TensorFlow Frozen Graphs 205 | .avi # videos 206 | 207 | # Sensitive or high-churn files: 208 | .idea/**/dataSources/ 209 | .idea/**/dataSources.ids 210 | .idea/**/dataSources.local.xml 211 | .idea/**/sqlDataSources.xml 212 | .idea/**/dynamic.xml 213 | .idea/**/uiDesigner.xml 214 | 215 | # Gradle: 216 | .idea/**/gradle.xml 217 | .idea/**/libraries 218 | 219 | # CMake 220 | cmake-build-debug/ 221 | cmake-build-release/ 222 | 223 | # Mongo Explorer plugin: 224 | .idea/**/mongoSettings.xml 225 | 226 | ## File-based project format: 227 | *.iws 228 | 229 | ## Plugin-specific files: 230 | 231 | # IntelliJ 232 | out/ 233 | 234 | # mpeltonen/sbt-idea plugin 235 | .idea_modules/ 236 | 237 | # JIRA plugin 238 | atlassian-ide-plugin.xml 239 | 240 | # Cursive Clojure plugin 241 | .idea/replstate.xml 242 | 243 | # Crashlytics plugin (for Android Studio and IntelliJ) 244 | com_crashlytics_export_strings.xml 245 | crashlytics.properties 246 | crashlytics-build.properties 247 | fabric.properties 248 | -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- 1 | # Define hooks for code formations 2 | # Will be applied on any updated commit files if a user has installed and linked commit hook 3 | 4 | default_language_version: 5 | python: python3.8 6 | 7 | # Define bot property if installed via https://github.com/marketplace/pre-commit-ci 8 | ci: 9 | autofix_prs: true 10 | autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions' 11 | autoupdate_schedule: quarterly 12 | # submodules: true 13 | 14 | repos: 15 | - repo: https://github.com/pre-commit/pre-commit-hooks 16 | rev: v4.0.1 17 | hooks: 18 | - id: end-of-file-fixer 19 | - id: trailing-whitespace 20 | - id: check-case-conflict 21 | - id: check-yaml 22 | - id: check-toml 23 | - id: pretty-format-json 24 | - id: check-docstring-first 25 | 26 | - repo: https://github.com/asottile/pyupgrade 27 | rev: v2.23.1 28 | hooks: 29 | - id: pyupgrade 30 | args: [--py36-plus] 31 | name: Upgrade code 32 | 33 | - repo: https://github.com/PyCQA/isort 34 | rev: 5.9.3 35 | hooks: 36 | - id: isort 37 | name: Sort imports 38 | 39 | # TODO 40 | #- repo: https://github.com/pre-commit/mirrors-yapf 41 | # rev: v0.31.0 42 | # hooks: 43 | # - id: yapf 44 | # name: formatting 45 | 46 | # TODO 47 | #- repo: https://github.com/executablebooks/mdformat 48 | # rev: 0.7.7 49 | # hooks: 50 | # - id: mdformat 51 | # additional_dependencies: 52 | # - mdformat-gfm 53 | # - mdformat-black 54 | # - mdformat_frontmatter 55 | 56 | # TODO 57 | #- repo: https://github.com/asottile/yesqa 58 | # rev: v1.2.3 59 | # hooks: 60 | # - id: yesqa 61 | 62 | - repo: https://github.com/PyCQA/flake8 63 | rev: 3.9.2 64 | hooks: 65 | - id: flake8 66 | name: PEP8 67 | -------------------------------------------------------------------------------- /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 upstream/master.** If your PR is behind upstream/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 possible 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:21.10-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 wandb>=0.12.2 14 | RUN pip install --no-cache -U torch torchvision numpy Pillow 15 | # RUN pip install --no-cache torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/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 | # Downloads to user config dir 25 | ADD https://ultralytics.com/assets/Arial.ttf /root/.config/Ultralytics/ 26 | 27 | # Set environment variables 28 | # ENV HOME=/usr/src/app 29 | 30 | 31 | # Usage Examples ------------------------------------------------------------------------------------------------------- 32 | 33 | # Build and Push 34 | # t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t 35 | 36 | # Pull and Run 37 | # t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t 38 | 39 | # Pull and Run with local directory access 40 | # t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t 41 | 42 | # Kill all 43 | # sudo docker kill $(sudo docker ps -q) 44 | 45 | # Kill all image-based 46 | # sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest) 47 | 48 | # Bash into running container 49 | # sudo docker exec -it 5a9b5863d93d bash 50 | 51 | # Bash into stopped container 52 | # id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash 53 | 54 | # Clean up 55 | # docker system prune -a --volumes 56 | 57 | # Update Ubuntu drivers 58 | # https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/ 59 | 60 | # DDP test 61 | # python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3 62 | 63 | # GCP VM from Image 64 | # docker.io/ultralytics/yolov5:latest 65 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## 仓库说明： 2 | 3 | 本仓库是针对基于EASY-EAI-Nano(RV1126)从PC端模型训练、模型单步测试、pytorch模型转换为onnx模型的流程说明，并以口罩检测为例子说明。而模型如何部署到硬件主板上，完整的在线文档教程可以查看以下在线文档的链接： 4 | 5 | ## 环境说明： 6 | 7 | python version >= 3.6 8 | 9 | pytorch version >= 1.7 10 | 11 | onnx verison >= 1.11 12 | 13 | ## 准备数据 14 | 口罩检测数据百度链接：https://pan.baidu.com/s/1vtxWurn1Mqu-wJ017eaQrw 提取码：6666 15 | 16 | 数据集解压后(脚本在数据集里面)，执行以下脚本生成train.txt和valid.txt： 17 | ```python 18 | python list_dataset_file.py 19 | ``` 20 | 21 | 22 | ## 训练模型 23 | 训练一个口罩检测模型，需要修改"data/mask.yaml"里面的train.txt和valid.txt的路径。训练脚本如下所示： 24 | ```python 25 | python train.py --data mask.yaml --cfg yolov5s.yaml --weights "" --batch-size 64 26 | yolov5m 40 27 | yolov5l 24 28 | yolov5x 16 29 | ``` 30 | 训练完成后会在 31 | 32 | ## 模型预测 33 | 测试训练好的模型： 34 | ```python 35 | python detect.py --source data/images --weights ./runs/train/exp/weights/best.pt --conf 0.5 36 | ``` 37 | 测试结果会在"runs/detect"生成： 38 | 39 | 40 | 41 | ## 模型导出 42 | 执行以下指令把pt模型转换为onnx模型，同时会生成best.anchors.txt： 43 | ```python 44 | python export.py --include onnx --rknpu RV1126 --weights ./runs/train/exp/weights/best.pt 45 | ``` 46 | 47 | 48 | ### EASY-EAI-Nano基于NPU运行速度测试(单位:ms)： 49 | 50 | | 模型(640x640输入)         | EASY-EAI-Nano(RV1126) | 51 | | :---------------------- | :-----------------------------------------: | 52 | | yolov5s int8量化 |   52    | 53 | | yolov5m int8量化 |   93    | 54 | 55 | 56 | 57 | ## 参考库： 58 | 59 | https://github.com/ultralytics/yolov5 60 | 61 | https://github.com/soloIife/yolov5_for_rknn 62 | 63 | 64 | ## 技术交流群： 65 | 66 | QQ群：810456486 67 | 68 | 69 | 70 | -------------------------------------------------------------------------------- /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') 80000 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 Path, download, np, xyxy2xywhn 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 | # Train, Val Splits 76 | for split, patches in [('train', 50 + 1), ('val', 43 + 1)]: 77 | print(f"Processing {split} in {patches} patches ...") 78 | images, labels = dir / 'images' / split, dir / 'labels' / split 79 | 80 | # Download 81 | url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/" 82 | if split == 'train': 83 | download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False) # annotations json 84 | download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8) 85 | elif split == 'val': 86 | download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json 87 | download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8) 88 | download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8) 89 | 90 | # Move 91 | for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'): 92 | f.rename(images / f.name) # move to /images/{split} 93 | 94 | # Labels 95 | coco = COCO(dir / f'zhiyuan_objv2_{split}.json') 96 | names = [x["name"] for x in coco.loadCats(coco.getCatIds())] 97 | for cid, cat in enumerate(names): 98 | catIds = coco.getCatIds(catNms=[cat]) 99 | imgIds = coco.getImgIds(catIds=catIds) 100 | for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'): 101 | width, height = im["width"], im["height"] 102 | path = Path(im["file_name"]) # image filename 103 | try: 104 | with open(labels / path.with_suffix('.txt').name, 'a') as file: 105 | annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None) 106 | for a in coco.loadAnns(annIds): 107 | x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner) 108 | xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4) 109 | x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped 110 | file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n") 111 | except Exception as e: 112 | print(e) 113 | -------------------------------------------------------------------------------- /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/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/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 | train: D:/ai_project/coco/coco2017labels/coco/train2017.txt # 118287 images 12 | val: D:/ai_project/coco/coco2017labels/coco/val2017.txt # 5000 images 13 | test: D:/ai_project/coco/coco2017labels/coco/test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794 14 | 15 | # Classes 16 | nc: 80 # number of classes 17 | names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 18 | 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 19 | 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 20 | 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 21 | 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 22 | 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 23 | 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 24 | 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 25 | 'hair drier', 'toothbrush'] # class names 26 | 27 | 28 | # Download script/URL (optional) 29 | -------------------------------------------------------------------------------- /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://ultralytics.com/assets/coco128.zip 31 | -------------------------------------------------------------------------------- /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-high.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for high-augmentation 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: 0.1 # image mixup (probability) 34 | copy_paste: 0.1 # segment copy-paste (probability) 35 | -------------------------------------------------------------------------------- /data/hyps/hyp.scratch-low.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for low-augmentation COCO training from scratch 3 | # python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear 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: 0.01 # 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/hyps/hyp.scratch-med.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # Hyperparameters for medium-augmentation 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: 0.1 # 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: 0.1 # 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: 0.1 # 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/test-1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/data/images/test-1.jpg -------------------------------------------------------------------------------- /data/images/test-2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/data/images/test-2.jpg -------------------------------------------------------------------------------- /data/mask.yaml: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | # COCO 2017 dataset http://cocodataset.org 3 | # Example usage: python train.py --data mask.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 | train: E:/dataset/mask/train.txt 12 | val: E:/dataset/mask/valid.txt 13 | test: E:/dataset/mask/valid.txt 14 | 15 | # Classes 16 | nc: 2 # number of classes 17 | names: ['head', 'mask'] # class names 18 | 19 | 20 | # Download script/URL (optional) 21 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /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 | model = torch.hub.load('ultralytics/yolov5:master', 'custom', 'path/to/yolov5s.onnx') # file from branch 9 | """ 10 | 11 | import torch 12 | 13 | 14 | def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 15 | """Creates a specified YOLOv5 model 16 | 17 | Arguments: 18 | name (str): name of model, i.e. 'yolov5s' 19 | pretrained (bool): load pretrained weights into the model 20 | channels (int): number of input channels 21 | classes (int): number of model classes 22 | autoshape (bool): apply YOLOv5 .autoshape() wrapper to model 23 | verbose (bool): print all information to screen 24 | device (str, torch.device, None): device to use for model parameters 25 | 26 | Returns: 27 | YOLOv5 pytorch model 28 | """ 29 | from pathlib import Path 30 | 31 | from models.common import AutoShape, DetectMultiBackend 32 | from models.yolo import Model 33 | from utils.downloads import attempt_download 34 | from utils.general import check_requirements, intersect_dicts, set_logging 35 | from utils.torch_utils import select_device 36 | 37 | check_requirements(exclude=('tensorboard', 'thop', 'opencv-python')) 38 | set_logging(verbose=verbose) 39 | 40 | name = Path(name) 41 | path = name.with_suffix('.pt') if name.suffix == '' else name # 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 = DetectMultiBackend(path, device=device) # download/load FP32 model 47 | # model = models.experimental.attempt_load(path, map_location=device) # download/load FP32 model 48 | else: 49 | cfg = list((Path(__file__).parent / 'models').rglob(f'{path.stem}.yaml'))[0] # model.yaml path 50 | model = Model(cfg, channels, classes) # create model 51 | if pretrained: 52 | ckpt = torch.load(attempt_download(path), map_location=device) # load 53 | csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 54 | csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors']) # intersect 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 = AutoShape(model) # 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 yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 74 | # YOLOv5-nano model https://github.com/ultralytics/yolov5 75 | return _create('yolov5n', pretrained, channels, classes, autoshape, verbose, device) 76 | 77 | 78 | def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 79 | # YOLOv5-small model https://github.com/ultralytics/yolov5 80 | return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device) 81 | 82 | 83 | def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 84 | # YOLOv5-medium model https://github.com/ultralytics/yolov5 85 | return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device) 86 | 87 | 88 | def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 89 | # YOLOv5-large model https://github.com/ultralytics/yolov5 90 | return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device) 91 | 92 | 93 | def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 94 | # YOLOv5-xlarge model https://github.com/ultralytics/yolov5 95 | return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device) 96 | 97 | 98 | def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 99 | # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5 100 | return _create('yolov5n6', pretrained, channels, classes, autoshape, verbose, device) 101 | 102 | 103 | def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 104 | # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5 105 | return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device) 106 | 107 | 108 | def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 109 | # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5 110 | return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device) 111 | 112 | 113 | def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 114 | # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5 115 | return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device) 116 | 117 | 118 | def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None): 119 | # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5 120 | return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device) 121 | 122 | 123 | if __name__ == '__main__': 124 | model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True) # pretrained 125 | # model = custom(path='path/to/model.pt') # custom 126 | 127 | # Verify inference 128 | from pathlib import Path 129 | 130 | import cv2 131 | import numpy as np 132 | from PIL import Image 133 | 134 | imgs = ['data/images/zidane.jpg', # filename 135 | Path('data/images/zidane.jpg'), # Path 136 | 'https://ultralytics.com/images/zidane.jpg', # URI 137 | cv2.imread('data/images/bus.jpg')[:, :, ::-1], # OpenCV 138 | Image.open('data/images/bus.jpg'), # PIL 139 | np.zeros((320, 640, 3))] # numpy 140 | 141 | results = model(imgs, size=320) # batched inference 142 | results.print() 143 | results.save() 144 | -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/models/__init__.py -------------------------------------------------------------------------------- /models/common_rk_plug_in.py: -------------------------------------------------------------------------------- 1 | # This file contains modules common to various models 2 | 3 | import torch 4 | import torch.nn as nn 5 | from models.common import Conv 6 | 7 | 8 | class surrogate_focus(nn.Module): 9 | # surrogate_focus wh information into c-space 10 | def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups 11 | super(surrogate_focus, self).__init__() 12 | self.conv = Conv(c1 * 4, c2, k, s, p, g, act) 13 | 14 | with torch.no_grad(): 15 | self.conv1 = nn.Conv2d(3, 3, (2, 2), groups=3, bias=False, stride=(2, 2)) 16 | self.conv1.weight[:, :, 0, 0] = 1 17 | self.conv1.weight[:, :, 0, 1] = 0 18 | self.conv1.weight[:, :, 1, 0] = 0 19 | self.conv1.weight[:, :, 1, 1] = 0 20 | 21 | self.conv2 = nn.Conv2d(3, 3, (2, 2), groups=3, bias=False, stride=(2, 2)) 22 | self.conv2.weight[:, :, 0, 0] = 0 23 | self.conv2.weight[:, :, 0, 1] = 0 24 | self.conv2.weight[:, :, 1, 0] = 1 25 | self.conv2.weight[:, :, 1, 1] = 0 26 | 27 | self.conv3 = nn.Conv2d(3, 3, (2, 2), groups=3, bias=False, stride=(2, 2)) 28 | self.conv3.weight[:, :, 0, 0] = 0 29 | self.conv3.weight[:, :, 0, 1] = 1 30 | self.conv3.weight[:, :, 1, 0] = 0 31 | self.conv3.weight[:, :, 1, 1] = 0 32 | 33 | self.conv4 = nn.Conv2d(3, 3, (2, 2), groups=3, bias=False, stride=(2, 2)) 34 | self.conv4.weight[:, :, 0, 0] = 0 35 | self.conv4.weight[:, :, 0, 1] = 0 36 | self.conv4.weight[:, :, 1, 0] = 0 37 | self.conv4.weight[:, :, 1, 1] = 1 38 | 39 | def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2) 40 | return self.conv(torch.cat([self.conv1(x), self.conv2(x), self.conv3(x), self.conv4(x)], 1)) 41 | 42 | 43 | class preprocess_conv_layer(nn.Module): 44 | """docstring for preprocess_conv_layer""" 45 | # input_module 为输入模型，即为想要导出模型 46 | # mean_value 的值可以是 [m1, m2, m3] 或 常数m 47 | # std_value 的值可以是 [s1, s2, s3] 或 常数s 48 | # BGR2RGB的操作默认为首先执行，既替代的原有操作顺序为 49 | # BGR2RGB -> minus mean -> minus std (与rknn config 设置保持一致) -> nhwc2nchw 50 | # 51 | # 使用示例-伪代码： 52 | # from add_preprocess_conv_layer import preprocess_conv_layer 53 | # model_A = create_model() 54 | # model_output = preprocess_co_nv_layer(model_A, mean_value, std_value, BGR2RGB) 55 | # onnx_export(model_output) 56 | # 57 | # 量化时： 58 | # rknn.config的中 channel_mean_value 、reorder_channel 均不赋值。 59 | # 60 | # 部署代码： 61 | # rknn_input 的属性 62 | # pass_through = 1 63 | # 64 | # 另外： 65 | # 由于加入permute操作，c端输入为opencv mat(hwc格式)即可，无需在外部将hwc改成chw格式。 66 | # 67 | 68 | def __init__(self, input_module, mean_value, std_value, BGR2RGB=False): 69 | super(preprocess_conv_layer, self).__init__() 70 | if isinstance(mean_value, int): 71 | mean_value = [mean_value for i in range(3)] 72 | if isinstance(std_value, int): 73 | std_value = [std_value for i in range(3)] 74 | 75 | assert len(mean_value) <= 3, 'mean_value should be int, or list with 3 element' 76 | assert len(std_value) <= 3, 'std_value should be int, or list with 3 element' 77 | 78 | self.input_module = input_module 79 | 80 | with torch.no_grad(): 81 | self.conv1 = nn.Conv2d(3, 3, (1, 1), groups=1, bias=True, stride=(1, 1)) 82 | 83 | if BGR2RGB is False: 84 | self.conv1.weight[:, :, :, :] = 0 85 | self.conv1.weight[0, 0, :, :] = 1/std_value[0] 86 | self.conv1.weight[1, 1, :, :] = 1/std_value[1] 87 | self.conv1.weight[2, 2, :, :] = 1/std_value[2] 88 | elif BGR2RGB is True: 89 | self.conv1.weight[:, :, :, :] = 0 90 | self.conv1.weight[0, 2, :, :] = 1/std_value[0] 91 | self.conv1.weight[1, 1, :, :] = 1/std_value[1] 92 | self.conv1.weight[2, 0, :, :] = 1/std_value[2] 93 | 94 | self.conv1.bias[0] = -mean_value[0]/std_value[0] 95 | self.conv1.bias[1] = -mean_value[1]/std_value[1] 96 | self.conv1.bias[2] = -mean_value[2]/std_value[2] 97 | 98 | self.conv1.eval() 99 | 100 | def forward(self, x): 101 | x = x.permute(0, 3, 1, 2) # NHWC -> NCHW, apply for rknn_pass_through 102 | x = self.conv1(x) 103 | return self.input_module(x) -------------------------------------------------------------------------------- /models/experimental.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Experimental modules 4 | """ 5 | import math 6 | 7 | import numpy as np 8 | import torch 9 | import torch.nn as nn 10 | 11 | from models.common import Conv 12 | from utils.downloads import attempt_download 13 | 14 | 15 | class CrossConv(nn.Module): 16 | # Cross Convolution Downsample 17 | def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False): 18 | # ch_in, ch_out, kernel, stride, groups, expansion, shortcut 19 | super().__init__() 20 | c_ = int(c2 * e) # hidden channels 21 | self.cv1 = Conv(c1, c_, (1, k), (1, s)) 22 | self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g) 23 | self.add = shortcut and c1 == c2 24 | 25 | def forward(self, x): 26 | return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) 27 | 28 | 29 | class Sum(nn.Module): 30 | # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070 31 | def __init__(self, n, weight=False): # n: number of inputs 32 | super().__init__() 33 | self.weight = weight # apply weights boolean 34 | self.iter = range(n - 1) # iter object 35 | if weight: 36 | self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights 37 | 38 | def forward(self, x): 39 | y = x[0] # no weight 40 | if self.weight: 41 | w = torch.sigmoid(self.w) * 2 42 | for i in self.iter: 43 | y = y + x[i + 1] * w[i] 44 | else: 45 | for i in self.iter: 46 | y = y + x[i + 1] 47 | return y 48 | 49 | 50 | class MixConv2d(nn.Module): 51 | # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595 52 | def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy 53 | super().__init__() 54 | n = len(k) # number of convolutions 55 | if equal_ch: # equal c_ per group 56 | i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices 57 | c_ = [(i == g).sum() for g in range(n)] # intermediate channels 58 | else: # equal weight.numel() per group 59 | b = [c2] + [0] * n 60 | a = np.eye(n + 1, n, k=-1) 61 | a -= np.roll(a, 1, axis=1) 62 | a *= np.array(k) ** 2 63 | a[0] = 1 64 | c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b 65 | 66 | self.m = nn.ModuleList( 67 | [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)]) 68 | self.bn = nn.BatchNorm2d(c2) 69 | self.act = nn.ReLU() 70 | 71 | def forward(self, x): 72 | return self.act(self.bn(torch.cat([m(x) for m in self.m], 1))) 73 | 74 | 75 | class Ensemble(nn.ModuleList): 76 | # Ensemble of models 77 | def __init__(self): 78 | super().__init__() 79 | 80 | def forward(self, x, augment=False, profile=False, visualize=False): 81 | y = [] 82 | for module in self: 83 | y.append(module(x, augment, profile, visualize)[0]) 84 | # y = torch.stack(y).max(0)[0] # max ensemble 85 | # y = torch.stack(y).mean(0) # mean ensemble 86 | y = torch.cat(y, 1) # nms ensemble 87 | return y, None # inference, train output 88 | 89 | 90 | def attempt_load(weights, map_location=None, inplace=True, fuse=True): 91 | from models.yolo import Detect, Model 92 | 93 | # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a 94 | model = Ensemble() 95 | for w in weights if isinstance(weights, list) else [weights]: 96 | ckpt = torch.load(attempt_download(w), map_location=map_location) # load 97 | if fuse: 98 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model 99 | else: 100 | model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval()) # without layer fuse 101 | 102 | # Compatibility updates 103 | for m in model.modules(): 104 | if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]: 105 | m.inplace = inplace # pytorch 1.7.0 compatibility 106 | if type(m) is Detect: 107 | if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility 108 | delattr(m, 'anchor_grid') 109 | setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl) 110 | elif type(m) is Conv: 111 | m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility 112 | 113 | if len(model) == 1: 114 | return model[-1] # return model 115 | else: 116 | print(f'Ensemble created with {weights}\n') 117 | for k in ['names']: 118 | setattr(model, k, getattr(model[-1], k)) 119 | model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride 120 | return model # return ensemble 121 | -------------------------------------------------------------------------------- /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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 <--- BiFPN change 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 FPN head 28 | head: 29 | [[-1, 3, C3, [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, C3, [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, C3, [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 # auto-anchor evolves 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 21 | [-1, 1, SPPF, [1024, 5]], # 9 22 | ] 23 | 24 | # YOLOv5 v6.0 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 # auto-anchor 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, SPPF, [1024, 5]], # 11 24 | ] 25 | 26 | # YOLOv5 v6.0 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 (P6/64-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 # auto-anchor 3 anchors per P output layer 8 | 9 | # YOLOv5 v6.0 backbone 10 | backbone: 11 | # [from, number, module, args] 12 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1280]], 25 | [-1, 1, SPPF, [1280, 5]], # 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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, 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/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 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 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 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 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/yolov5n6.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: 0.25 # 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 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3Ghost, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3TR, [1024]], # 9 <--- C3TR() Transformer module 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 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 v6.0 backbone 14 | backbone: 15 | # [from, number, module, args] 16 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 27 | [-1, 1, SPPF, [1024, 5]], # 11 28 | ] 29 | 30 | # YOLOv5 v6.0 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/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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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/yolov5n.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: 0.25 # 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 v6.0 backbone 13 | backbone: 14 | # [from, number, module, args] 15 | [[-1, 1, Conv, [64, 6, 2, 2]], # 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, 6, 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, 3, C3, [1024]], 24 | [-1, 1, SPPF, [1024, 5]], # 9 25 | ] 26 | 27 | # YOLOv5 v6.0 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 | -------------------------------------------------------------------------------- /photo/image.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/photo/image.jpg -------------------------------------------------------------------------------- /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>=7.1.2 8 | PyYAML>=5.3.1 9 | requests>=2.23.0 10 | scipy>=1.4.1 11 | torch>=1.7.0 12 | torchvision>=0.8.1 13 | tqdm>=4.41.0 14 | 15 | # Logging ------------------------------------- 16 | tensorboard>=2.4.1 17 | # wandb 18 | 19 | # Plotting ------------------------------------ 20 | pandas>=1.1.4 21 | seaborn>=0.11.0 22 | 23 | # Export -------------------------------------- 24 | # coremltools>=4.1 # CoreML export 25 | # onnx>=1.9.0 # ONNX export 26 | # onnx-simplifier>=0.3.6 # ONNX simplifier 27 | # scikit-learn==0.19.2 # CoreML quantization 28 | # tensorflow>=2.4.1 # TFLite export 29 | # tensorflowjs>=3.9.0 # TF.js export 30 | 31 | # Extras -------------------------------------- 32 | # albumentations>=1.0.3 33 | # Cython # for pycocotools https://github.com/cocodataset/cocoapi/issues/172 34 | # pycocotools>=2.0 # COCO mAP 35 | # roboflow 36 | thop # FLOPs computation 37 | -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | # Project-wide configuration file, can be used for package metadata and other toll configurations 2 | # Example usage: global configuration for PEP8 (via flake8) setting or default pytest arguments 3 | 4 | [metadata] 5 | license_file = LICENSE 6 | description-file = README.md 7 | 8 | 9 | [tool:pytest] 10 | norecursedirs = 11 | .git 12 | dist 13 | build 14 | addopts = 15 | --doctest-modules 16 | --durations=25 17 | --color=yes 18 | 19 | 20 | [flake8] 21 | max-line-length = 120 22 | exclude = .tox,*.egg,build,temp 23 | select = E,W,F 24 | doctests = True 25 | verbose = 2 26 | # https://pep8.readthedocs.io/en/latest/intro.html#error-codes 27 | format = pylint 28 | # see: https://www.flake8rules.com/ 29 | ignore = 30 | E731 # Do not assign a lambda expression, use a def 31 | F405 32 | E402 33 | F841 34 | E741 35 | F821 36 | E722 37 | F401 38 | W504 39 | E127 40 | W504 41 | E231 42 | E501 43 | F403 44 | E302 45 | F541 46 | 47 | 48 | [isort] 49 | # https://pycqa.github.io/isort/docs/configuration/options.html 50 | line_length = 120 51 | multi_line_output = 0 52 | -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | utils/initialization 4 | """ 5 | 6 | 7 | def notebook_init(verbose=True): 8 | # Check system software and hardware 9 | print('Checking setup...') 10 | 11 | import os 12 | import shutil 13 | 14 | from utils.general import check_requirements, emojis, is_colab 15 | from utils.torch_utils import select_device # imports 16 | 17 | check_requirements(('psutil', 'IPython')) 18 | import psutil 19 | from IPython import display # to display images and clear console output 20 | 21 | if is_colab(): 22 | shutil.rmtree('/content/sample_data', ignore_errors=True) # remove colab /sample_data directory 23 | 24 | if verbose: 25 | # System info 26 | # gb = 1 / 1000 ** 3 # bytes to GB 27 | gib = 1 / 1024 ** 3 # bytes to GiB 28 | ram = psutil.virtual_memory().total 29 | total, used, free = shutil.disk_usage("/") 30 | display.clear_output() 31 | s = f'({os.cpu_count()} CPUs, {ram * gib:.1f} GB RAM, {(total - free) * gib:.1f}/{total * gib:.1f} GB disk)' 32 | else: 33 | s = '' 34 | 35 | select_device(newline=False) 36 | print(emojis(f'Setup complete ✅ {s}')) 37 | return display 38 | -------------------------------------------------------------------------------- /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, 0.0, 6.0) / 6.0 # 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 math 7 | import random 8 | 9 | import cv2 10 | import numpy as np 11 | 12 | from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box 13 | from utils.metrics import bbox_ioa 14 | 15 | 16 | class Albumentations: 17 | # YOLOv5 Albumentations class (optional, only used if package is installed) 18 | def __init__(self): 19 | self.transform = None 20 | try: 21 | import albumentations as A 22 | check_version(A.__version__, '1.0.3', hard=True) # version requirement 23 | 24 | self.transform = A.Compose([ 25 | A.Blur(p=0.01), 26 | A.MedianBlur(p=0.01), 27 | A.ToGray(p=0.01), 28 | A.CLAHE(p=0.01), 29 | A.RandomBrightnessContrast(p=0.0), 30 | A.RandomGamma(p=0.0), 31 | A.ImageCompression(quality_lower=75, p=0.0)], 32 | bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels'])) 33 | 34 | LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p)) 35 | except ImportError: # package not installed, skip 36 | pass 37 | except Exception as e: 38 | LOGGER.info(colorstr('albumentations: ') + f'{e}') 39 | 40 | def __call__(self, im, labels, p=1.0): 41 | if self.transform and random.random() < p: 42 | new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed 43 | im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) 44 | return im, labels 45 | 46 | 47 | def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5): 48 | # HSV color-space augmentation 49 | if hgain or sgain or vgain: 50 | r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains 51 | hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV)) 52 | dtype = im.dtype # uint8 53 | 54 | x = np.arange(0, 256, dtype=r.dtype) 55 | lut_hue = ((x * r[0]) % 180).astype(dtype) 56 | lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) 57 | lut_val = np.clip(x * r[2], 0, 255).astype(dtype) 58 | 59 | im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))) 60 | cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed 61 | 62 | 63 | def hist_equalize(im, clahe=True, bgr=False): 64 | # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255 65 | yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) 66 | if clahe: 67 | c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) 68 | yuv[:, :, 0] = c.apply(yuv[:, :, 0]) 69 | else: 70 | yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram 71 | return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB 72 | 73 | 74 | def replicate(im, labels): 75 | # Replicate labels 76 | h, w = im.shape[:2] 77 | boxes = labels[:, 1:].astype(int) 78 | x1, y1, x2, y2 = boxes.T 79 | s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) 80 | for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices 81 | x1b, y1b, x2b, y2b = boxes[i] 82 | bh, bw = y2b - y1b, x2b - x1b 83 | yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y 84 | x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] 85 | im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax] 86 | labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) 87 | 88 | return im, labels 89 | 90 | 91 | def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): 92 | # Resize and pad image while meeting stride-multiple constraints 93 | shape = im.shape[:2] # current shape [height, width] 94 | if isinstance(new_shape, int): 95 | new_shape = (new_shape, new_shape) 96 | 97 | # Scale ratio (new / old) 98 | r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) 99 | if not scaleup: # only scale down, do not scale up (for better val mAP) 100 | r = min(r, 1.0) 101 | 102 | # Compute padding 103 | ratio = r, r # width, height ratios 104 | new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) 105 | dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding 106 | if auto: # minimum rectangle 107 | dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding 108 | elif scaleFill: # stretch 109 | dw, dh = 0.0, 0.0 110 | new_unpad = (new_shape[1], new_shape[0]) 111 | ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios 112 | 113 | dw /= 2 # divide padding into 2 sides 114 | dh /= 2 115 | 116 | if shape[::-1] != new_unpad: # resize 117 | im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR) 118 | top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) 119 | left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) 120 | im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border 121 | return im, ratio, (dw, dh) 122 | 123 | 124 | def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, 125 | border=(0, 0)): 126 | # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10)) 127 | # targets = [cls, xyxy] 128 | 129 | height = im.shape[0] + border[0] * 2 # shape(h,w,c) 130 | width = im.shape[1] + border[1] * 2 131 | 132 | # Center 133 | C = np.eye(3) 134 | C[0, 2] = -im.shape[1] / 2 # x translation (pixels) 135 | C[1, 2] = -im.shape[0] / 2 # y translation (pixels) 136 | 137 | # Perspective 138 | P = np.eye(3) 139 | P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) 140 | P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) 141 | 142 | # Rotation and Scale 143 | R = np.eye(3) 144 | a = random.uniform(-degrees, degrees) 145 | # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations 146 | s = random.uniform(1 - scale, 1 + scale) 147 | # s = 2 ** random.uniform(-scale, scale) 148 | R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) 149 | 150 | # Shear 151 | S = np.eye(3) 152 | S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) 153 | S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) 154 | 155 | # Translation 156 | T = np.eye(3) 157 | T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) 158 | T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) 159 | 160 | # Combined rotation matrix 161 | M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT 162 | if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed 163 | if perspective: 164 | im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114)) 165 | else: # affine 166 | im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) 167 | 168 | # Visualize 169 | # import matplotlib.pyplot as plt 170 | # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() 171 | # ax[0].imshow(im[:, :, ::-1]) # base 172 | # ax[1].imshow(im2[:, :, ::-1]) # warped 173 | 174 | # Transform label coordinates 175 | n = len(targets) 176 | if n: 177 | use_segments = any(x.any() for x in segments) 178 | new = np.zeros((n, 4)) 179 | if use_segments: # warp segments 180 | segments = resample_segments(segments) # upsample 181 | for i, segment in enumerate(segments): 182 | xy = np.ones((len(segment), 3)) 183 | xy[:, :2] = segment 184 | xy = xy @ M.T # transform 185 | xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine 186 | 187 | # clip 188 | new[i] = segment2box(xy, width, height) 189 | 190 | else: # warp boxes 191 | xy = np.ones((n * 4, 3)) 192 | xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 193 | xy = xy @ M.T # transform 194 | xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine 195 | 196 | # create new boxes 197 | x = xy[:, [0, 2, 4, 6]] 198 | y = xy[:, [1, 3, 5, 7]] 199 | new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T 200 | 201 | # clip 202 | new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) 203 | new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) 204 | 205 | # filter candidates 206 | i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) 207 | targets = targets[i] 208 | targets[:, 1:5] = new[i] 209 | 210 | return im, targets 211 | 212 | 213 | def copy_paste(im, labels, segments, p=0.5): 214 | # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) 215 | n = len(segments) 216 | if p and n: 217 | h, w, c = im.shape # height, width, channels 218 | im_new = np.zeros(im.shape, np.uint8) 219 | for j in random.sample(range(n), k=round(p * n)): 220 | l, s = labels[j], segments[j] 221 | box = w - l[3], l[2], w - l[1], l[4] 222 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 223 | if (ioa < 0.30).all(): # allow 30% obscuration of existing labels 224 | labels = np.concatenate((labels, [[l[0], *box]]), 0) 225 | segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) 226 | cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) 227 | 228 | result = cv2.bitwise_and(src1=im, src2=im_new) 229 | result = cv2.flip(result, 1) # augment segments (flip left-right) 230 | i = result > 0 # pixels to replace 231 | # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch 232 | im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug 233 | 234 | return im, labels, segments 235 | 236 | 237 | def cutout(im, labels, p=0.5): 238 | # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 239 | if random.random() < p: 240 | h, w = im.shape[:2] 241 | scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction 242 | for s in scales: 243 | mask_h = random.randint(1, int(h * s)) # create random masks 244 | mask_w = random.randint(1, int(w * s)) 245 | 246 | # box 247 | xmin = max(0, random.randint(0, w) - mask_w // 2) 248 | ymin = max(0, random.randint(0, h) - mask_h // 2) 249 | xmax = min(w, xmin + mask_w) 250 | ymax = min(h, ymin + mask_h) 251 | 252 | # apply random color mask 253 | im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] 254 | 255 | # return unobscured labels 256 | if len(labels) and s > 0.03: 257 | box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) 258 | ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area 259 | labels = labels[ioa < 0.60] # remove >60% obscured labels 260 | 261 | return labels 262 | 263 | 264 | def mixup(im, labels, im2, labels2): 265 | # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf 266 | r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0 267 | im = (im * r + im2 * (1 - r)).astype(np.uint8) 268 | labels = np.concatenate((labels, labels2), 0) 269 | return im, labels 270 | 271 | 272 | def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) 273 | # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio 274 | w1, h1 = box1[2] - box1[0], box1[3] - box1[1] 275 | w2, h2 = box2[2] - box2[0], box2[3] - box2[1] 276 | ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio 277 | return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates 278 | -------------------------------------------------------------------------------- /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 LOGGER, colorstr, emojis 14 | 15 | PREFIX = colorstr('AutoAnchor: ') 16 | 17 | 18 | def check_anchor_order(m): 19 | # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary 20 | a = m.anchors.prod(-1).view(-1) # anchor area 21 | da = a[-1] - a[0] # delta a 22 | ds = m.stride[-1] - m.stride[0] # delta s 23 | if da.sign() != ds.sign(): # same order 24 | LOGGER.info(f'{PREFIX}Reversing anchor order') 25 | m.anchors[:] = m.anchors.flip(0) 26 | 27 | 28 | def check_anchors(dataset, model, thr=4.0, imgsz=640): 29 | # Check anchor fit to data, recompute if necessary 30 | m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect() 31 | shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True) 32 | scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale 33 | wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh 34 | 35 | def metric(k): # compute metric 36 | r = wh[:, None] / k[None] 37 | x = torch.min(r, 1 / r).min(2)[0] # ratio metric 38 | best = x.max(1)[0] # best_x 39 | aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold 40 | bpr = (best > 1 / thr).float().mean() # best possible recall 41 | return bpr, aat 42 | 43 | anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors 44 | bpr, aat = metric(anchors.cpu().view(-1, 2)) 45 | s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). ' 46 | if bpr > 0.98: # threshold to recompute 47 | LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅')) 48 | else: 49 | LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...')) 50 | na = m.anchors.numel() // 2 # number of anchors 51 | try: 52 | anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False) 53 | except Exception as e: 54 | LOGGER.info(f'{PREFIX}ERROR: {e}') 55 | new_bpr = metric(anchors)[0] 56 | if new_bpr > bpr: # replace anchors 57 | anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors) 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 | LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.') 61 | else: 62 | LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.') 63 | 64 | 65 | def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True): 66 | """ Creates kmeans-evolved anchors from training dataset 67 | 68 | Arguments: 69 | dataset: path to data.yaml, or a loaded dataset 70 | n: number of anchors 71 | img_size: image size used for training 72 | thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0 73 | gen: generations to evolve anchors using genetic algorithm 74 | verbose: print all results 75 | 76 | Return: 77 | k: kmeans evolved anchors 78 | 79 | Usage: 80 | from utils.autoanchor import *; _ = kmean_anchors() 81 | """ 82 | from scipy.cluster.vq import kmeans 83 | 84 | thr = 1 / thr 85 | 86 | def metric(k, wh): # compute metrics 87 | r = wh[:, None] / k[None] 88 | x = torch.min(r, 1 / r).min(2)[0] # ratio metric 89 | # x = wh_iou(wh, torch.tensor(k)) # iou metric 90 | return x, x.max(1)[0] # x, best_x 91 | 92 | def anchor_fitness(k): # mutation fitness 93 | _, best = metric(torch.tensor(k, dtype=torch.float32), wh) 94 | return (best * (best > thr).float()).mean() # fitness 95 | 96 | def print_results(k, verbose=True): 97 | k = k[np.argsort(k.prod(1))] # sort small to large 98 | x, best = metric(k, wh0) 99 | bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr 100 | s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \ 101 | f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \ 102 | f'past_thr={x[x > thr].mean():.3f}-mean: ' 103 | for i, x in enumerate(k): 104 | s += '%i,%i, ' % (round(x[0]), round(x[1])) 105 | if verbose: 106 | LOGGER.info(s[:-2]) 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 | LOGGER.info(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 | LOGGER.info(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, 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, verbose=False) 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, verbose) 163 | 164 | return print_results(k) 165 | -------------------------------------------------------------------------------- /utils/autobatch.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Auto-batch utils 4 | """ 5 | 6 | from copy import deepcopy 7 | 8 | import numpy as np 9 | import torch 10 | from torch.cuda import amp 11 | 12 | from utils.general import LOGGER, colorstr 13 | from utils.torch_utils import profile 14 | 15 | 16 | def check_train_batch_size(model, imgsz=640): 17 | # Check YOLOv5 training batch size 18 | with amp.autocast(): 19 | return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size 20 | 21 | 22 | def autobatch(model, imgsz=640, fraction=0.9, batch_size=16): 23 | # Automatically estimate best batch size to use `fraction` of available CUDA memory 24 | # Usage: 25 | # import torch 26 | # from utils.autobatch import autobatch 27 | # model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False) 28 | # print(autobatch(model)) 29 | 30 | prefix = colorstr('AutoBatch: ') 31 | LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}') 32 | device = next(model.parameters()).device # get model device 33 | if device.type == 'cpu': 34 | LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}') 35 | return batch_size 36 | 37 | d = str(device).upper() # 'CUDA:0' 38 | properties = torch.cuda.get_device_properties(device) # device properties 39 | t = properties.total_memory / 1024 ** 3 # (GiB) 40 | r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GiB) 41 | a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GiB) 42 | f = t - (r + a) # free inside reserved 43 | LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free') 44 | 45 | batch_sizes = [1, 2, 4, 8, 16] 46 | try: 47 | img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes] 48 | y = profile(img, model, n=3, device=device) 49 | except Exception as e: 50 | LOGGER.warning(f'{prefix}{e}') 51 | 52 | y = [x[2] for x in y if x] # memory [2] 53 | batch_sizes = batch_sizes[:len(y)] 54 | p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit 55 | b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size) 56 | LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)') 57 | return b 58 | -------------------------------------------------------------------------------- /utils/aws/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/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 | FILE = Path(__file__).resolve() 12 | ROOT = FILE.parents[2] # YOLOv5 root directory 13 | if str(ROOT) not in sys.path: 14 | sys.path.append(str(ROOT)) # add ROOT to PATH 15 | 16 | port = 0 # --master_port 17 | path = Path('').resolve() 18 | for last in path.rglob('*/**/last.pt'): 19 | ckpt = torch.load(last) 20 | if ckpt['optimizer'] is None: 21 | continue 22 | 23 | # Load opt.yaml 24 | with open(last.parent.parent / 'opt.yaml', errors='ignore') as f: 25 | opt = yaml.safe_load(f) 26 | 27 | # Get device count 28 | d = opt['device'].split(',') # devices 29 | nd = len(d) # number of devices 30 | ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel 31 | 32 | if ddp: # multi-GPU 33 | port += 1 34 | cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}' 35 | else: # single-GPU 36 | cmd = f'python train.py --resume {last}' 37 | 38 | cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread 39 | print(cmd) 40 | os.system(cmd) 41 | -------------------------------------------------------------------------------- /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 | def __init__(self): 13 | # Define the available callbacks 14 | self._callbacks = { 15 | 'on_pretrain_routine_start': [], 16 | 'on_pretrain_routine_end': [], 17 | 18 | 'on_train_start': [], 19 | 'on_train_epoch_start': [], 20 | 'on_train_batch_start': [], 21 | 'optimizer_step': [], 22 | 'on_before_zero_grad': [], 23 | 'on_train_batch_end': [], 24 | 'on_train_epoch_end': [], 25 | 26 | 'on_val_start': [], 27 | 'on_val_batch_start': [], 28 | 'on_val_image_end': [], 29 | 'on_val_batch_end': [], 30 | 'on_val_end': [], 31 | 32 | 'on_fit_epoch_end': [], # fit = train + val 33 | 'on_model_save': [], 34 | 'on_train_end': [], 35 | 36 | 'teardown': [], 37 | } 38 | 39 | def register_action(self, hook, name='', callback=None): 40 | """ 41 | Register a new action to a callback hook 42 | 43 | Args: 44 | hook The callback hook name to register the action to 45 | name The name of the action for later reference 46 | callback The callback to fire 47 | """ 48 | assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" 49 | assert callable(callback), f"callback '{callback}' is not callable" 50 | self._callbacks[hook].append({'name': name, 'callback': callback}) 51 | 52 | def get_registered_actions(self, hook=None): 53 | """" 54 | Returns all the registered actions by callback hook 55 | 56 | Args: 57 | hook The name of the hook to check, defaults to all 58 | """ 59 | if hook: 60 | return self._callbacks[hook] 61 | else: 62 | return self._callbacks 63 | 64 | def run(self, hook, *args, **kwargs): 65 | """ 66 | Loop through the registered actions and fire all callbacks 67 | 68 | Args: 69 | hook The name of the hook to check, defaults to all 70 | args Arguments to receive from YOLOv5 71 | kwargs Keyword Arguments to receive from YOLOv5 72 | """ 73 | 74 | assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}" 75 | 76 | for logger in self._callbacks[hook]: 77 | logger['callback'](*args, **kwargs) 78 | -------------------------------------------------------------------------------- /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 | from zipfile import ZipFile 13 | 14 | import requests 15 | import torch 16 | 17 | 18 | def gsutil_getsize(url=''): 19 | # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du 20 | s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') 21 | return eval(s.split(' ')[0]) if len(s) else 0 # bytes 22 | 23 | 24 | def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): 25 | # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes 26 | file = Path(file) 27 | assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}" 28 | try: # url1 29 | print(f'Downloading {url} to {file}...') 30 | torch.hub.download_url_to_file(url, str(file)) 31 | assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check 32 | except Exception as e: # url2 33 | file.unlink(missing_ok=True) # remove partial downloads 34 | print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') 35 | os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail 36 | finally: 37 | if not file.exists() or file.stat().st_size < min_bytes: # check 38 | file.unlink(missing_ok=True) # remove partial downloads 39 | print(f"ERROR: {assert_msg}\n{error_msg}") 40 | print('') 41 | 42 | 43 | def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads import *; attempt_download() 44 | # Attempt file download if does not exist 45 | file = Path(str(file).strip().replace("'", '')) 46 | 47 | if not file.exists(): 48 | # URL specified 49 | name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc. 50 | if str(file).startswith(('http:/', 'https:/')): # download 51 | url = str(file).replace(':/', '://') # Pathlib turns :// -> :/ 52 | name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth... 53 | safe_download(file=name, url=url, min_bytes=1E5) 54 | return name 55 | 56 | # GitHub assets 57 | file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) 58 | try: 59 | response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api 60 | assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...] 61 | tag = response['tag_name'] # i.e. 'v1.0' 62 | except: # fallback plan 63 | assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 64 | 'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt'] 65 | try: 66 | tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1] 67 | except: 68 | tag = 'v6.0' # current release 69 | 70 | if name in assets: 71 | safe_download(file, 72 | url=f'https://github.com/{repo}/releases/download/{tag}/{name}', 73 | # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional) 74 | min_bytes=1E5, 75 | error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/') 76 | 77 | return str(file) 78 | 79 | 80 | def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'): 81 | # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download() 82 | t = time.time() 83 | file = Path(file) 84 | cookie = Path('cookie') # gdrive cookie 85 | print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='') 86 | file.unlink(missing_ok=True) # remove existing file 87 | cookie.unlink(missing_ok=True) # remove existing cookie 88 | 89 | # Attempt file download 90 | out = "NUL" if platform.system() == "Windows" else "/dev/null" 91 | os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}') 92 | if os.path.exists('cookie'): # large file 93 | s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}' 94 | else: # small file 95 | s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"' 96 | r = os.system(s) # execute, capture return 97 | cookie.unlink(missing_ok=True) # remove existing cookie 98 | 99 | # Error check 100 | if r != 0: 101 | file.unlink(missing_ok=True) # remove partial 102 | print('Download error ') # raise Exception('Download error') 103 | return r 104 | 105 | # Unzip if archive 106 | if file.suffix == '.zip': 107 | print('unzipping... ', end='') 108 | ZipFile(file).extractall(path=file.parent) # unzip 109 | file.unlink() # remove zip 110 | 111 | print(f'Done ({time.time() - t:.1f}s)') 112 | return r 113 | 114 | 115 | def get_token(cookie="./cookie"): 116 | with open(cookie) as f: 117 | for line in f: 118 | if "download" in line: 119 | return line.split()[-1] 120 | return "" 121 | 122 | # Google utils: https://cloud.google.com/storage/docs/reference/libraries ---------------------------------------------- 123 | # 124 | # 125 | # def upload_blob(bucket_name, source_file_name, destination_blob_name): 126 | # # Uploads a file to a bucket 127 | # # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python 128 | # 129 | # storage_client = storage.Client() 130 | # bucket = storage_client.get_bucket(bucket_name) 131 | # blob = bucket.blob(destination_blob_name) 132 | # 133 | # blob.upload_from_filename(source_file_name) 134 | # 135 | # print('File {} uploaded to {}.'.format( 136 | # source_file_name, 137 | # destination_blob_name)) 138 | # 139 | # 140 | # def download_blob(bucket_name, source_blob_name, destination_file_name): 141 | # # Uploads a blob from a bucket 142 | # storage_client = storage.Client() 143 | # bucket = storage_client.get_bucket(bucket_name) 144 | # blob = bucket.blob(source_blob_name) 145 | # 146 | # blob.download_to_filename(destination_file_name) 147 | # 148 | # print('Blob {} downloaded to {}.'.format( 149 | # source_blob_name, 150 | # destination_file_name)) 151 | -------------------------------------------------------------------------------- /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 flask import Flask, request 9 | from PIL import Image 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==21.1 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 15 | -------------------------------------------------------------------------------- /utils/loggers/__init__.py: -------------------------------------------------------------------------------- 1 | # YOLOv5 🚀 by Ultralytics, GPL-3.0 license 2 | """ 3 | Logging utils 4 | """ 5 | 6 | import os 7 | import warnings 8 | from threading import Thread 9 | 10 | import pkg_resources as pkg 11 | import torch 12 | from torch.utils.tensorboard import SummaryWriter 13 | 14 | from utils.general import colorstr, emojis 15 | from utils.loggers.wandb.wandb_utils import WandbLogger 16 | from utils.plots import plot_images, plot_results 17 | from utils.torch_utils import de_parallel 18 | 19 | LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases 20 | RANK = int(os.getenv('RANK', -1)) 21 | 22 | try: 23 | import wandb 24 | 25 | assert hasattr(wandb, '__version__') # verify package import not local dir 26 | if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]: 27 | try: 28 | wandb_login_success = wandb.login(timeout=30) 29 | except wandb.errors.UsageError: # known non-TTY terminal issue 30 | wandb_login_success = False 31 | if not wandb_login_success: 32 | wandb = None 33 | except (ImportError, AssertionError): 34 | wandb = None 35 | 36 | 37 | class Loggers(): 38 | # YOLOv5 Loggers class 39 | def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS): 40 | self.save_dir = save_dir 41 | self.weights = weights 42 | self.opt = opt 43 | self.hyp = hyp 44 | self.logger = logger # for printing results to console 45 | self.include = include 46 | self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss 47 | 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics 48 | 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss 49 | 'x/lr0', 'x/lr1', 'x/lr2'] # params 50 | for k in LOGGERS: 51 | setattr(self, k, None) # init empty logger dictionary 52 | self.csv = True # always log to csv 53 | 54 | # Message 55 | if not wandb: 56 | prefix = colorstr('Weights & Biases: ') 57 | s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)" 58 | print(emojis(s)) 59 | 60 | # TensorBoard 61 | s = self.save_dir 62 | if 'tb' in self.include and not self.opt.evolve: 63 | prefix = colorstr('TensorBoard: ') 64 | self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/") 65 | self.tb = SummaryWriter(str(s)) 66 | 67 | # W&B 68 | if wandb and 'wandb' in self.include: 69 | wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') 70 | run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None 71 | self.opt.hyp = self.hyp # add hyperparameters 72 | self.wandb = WandbLogger(self.opt, run_id) 73 | else: 74 | self.wandb = None 75 | 76 | def on_pretrain_routine_end(self): 77 | # Callback runs on pre-train routine end 78 | paths = self.save_dir.glob('*labels*.jpg') # training labels 79 | if self.wandb: 80 | self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) 81 | 82 | def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn): 83 | # Callback runs on train batch end 84 | if plots: 85 | if ni == 0: 86 | if not sync_bn: # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754 87 | with warnings.catch_warnings(): 88 | warnings.simplefilter('ignore') # suppress jit trace warning 89 | self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), []) 90 | if ni < 3: 91 | f = self.save_dir / f'train_batch{ni}.jpg' # filename 92 | Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start() 93 | if self.wandb and ni == 10: 94 | files = sorted(self.save_dir.glob('train*.jpg')) 95 | self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]}) 96 | 97 | def on_train_epoch_end(self, epoch): 98 | # Callback runs on train epoch end 99 | if self.wandb: 100 | self.wandb.current_epoch = epoch + 1 101 | 102 | def on_val_image_end(self, pred, predn, path, names, im): 103 | # Callback runs on val image end 104 | if self.wandb: 105 | self.wandb.val_one_image(pred, predn, path, names, im) 106 | 107 | def on_val_end(self): 108 | # Callback runs on val end 109 | if self.wandb: 110 | files = sorted(self.save_dir.glob('val*.jpg')) 111 | self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) 112 | 113 | def on_fit_epoch_end(self, vals, epoch, best_fitness, fi): 114 | # Callback runs at the end of each fit (train+val) epoch 115 | x = {k: v for k, v in zip(self.keys, vals)} # dict 116 | if self.csv: 117 | file = self.save_dir / 'results.csv' 118 | n = len(x) + 1 # number of cols 119 | s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header 120 | with open(file, 'a') as f: 121 | f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n') 122 | 123 | if self.tb: 124 | for k, v in x.items(): 125 | self.tb.add_scalar(k, v, epoch) 126 | 127 | if self.wandb: 128 | self.wandb.log(x) 129 | self.wandb.end_epoch(best_result=best_fitness == fi) 130 | 131 | def on_model_save(self, last, epoch, final_epoch, best_fitness, fi): 132 | # Callback runs on model save event 133 | if self.wandb: 134 | if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1: 135 | self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi) 136 | 137 | def on_train_end(self, last, best, plots, epoch, results): 138 | # Callback runs on training end 139 | if plots: 140 | plot_results(file=self.save_dir / 'results.csv') # save results.png 141 | files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))] 142 | files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter 143 | 144 | if self.tb: 145 | import cv2 146 | for f in files: 147 | self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC') 148 | 149 | if self.wandb: 150 | self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) 151 | # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model 152 | if not self.opt.evolve: 153 | wandb.log_artifact(str(best if best.exists() else last), type='model', 154 | name='run_' + self.wandb.wandb_run.id + '_model', 155 | aliases=['latest', 'best', 'stripped']) 156 | self.wandb.finish_run() 157 | else: 158 | self.wandb.finish_run() 159 | self.wandb = WandbLogger(self.opt) 160 | -------------------------------------------------------------------------------- /utils/loggers/wandb/README.md: -------------------------------------------------------------------------------- 1 | 📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 🚀. UPDATED 29 September 2021. 2 | * [About Weights & Biases](#about-weights-&-biases) 3 | * [First-Time Setup](#first-time-setup) 4 | * [Viewing runs](#viewing-runs) 5 | * [Disabling wandb](#disabling-wandb) 6 | * [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) 7 | * [Reports: Share your work with the world!](#reports) 8 | 9 | ## About Weights & Biases 10 | 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. 11 | 12 | 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: 13 | 14 | * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time 15 | * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically 16 | * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization 17 | * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators 18 | * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently 19 | * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models 20 | 21 | ## First-Time Setup 22 |
23 | Toggle Details 24 | 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. 25 | 26 | 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: 27 | 28 | ```shell 29 | $ python train.py --project ... --name ... 30 | ``` 31 | 32 | YOLOv5 notebook example: Open In Colab Open In Kaggle 33 | Screen Shot 2021-09-29 at 10 23 13 PM 34 | 35 | 36 |
37 | 38 | ## Viewing Runs 39 |
40 | Toggle Details 41 | 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: 42 | 43 | * Training & Validation losses 44 | * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 45 | * Learning Rate over time 46 | * A bounding box debugging panel, showing the training progress over time 47 | * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** 48 | * System: Disk I/0, CPU utilization, RAM memory usage 49 | * Your trained model as W&B Artifact 50 | * Environment: OS and Python types, Git repository and state, **training command** 51 | 52 |

Weights & Biases dashboard

53 |
54 | 55 | ## Disabling wandb 56 | * training after running `wandb disabled` inside that directory creates no wandb run 57 | ![Screenshot (84)](https://user-images.githubusercontent.com/15766192/143441777-c780bdd7-7cb4-4404-9559-b4316030a985.png) 58 | 59 | * To enable wandb again, run `wandb online` 60 | ![Screenshot (85)](https://user-images.githubusercontent.com/15766192/143441866-7191b2cb-22f0-4e0f-ae64-2dc47dc13078.png) 61 | 62 | ## Advanced Usage 63 | 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. 64 |
65 |

1: Train and Log Evaluation simultaneousy

66 | This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table 67 | Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, 68 | so no images will be uploaded from your system more than once. 69 |
70 | Usage 71 | Code $ python train.py --upload_data val 72 | 73 | ![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png) 74 |
75 | 76 |

2. Visualize and Version Datasets

77 | 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. 78 |
79 | Usage 80 | Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. 81 | 82 | ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) 83 |
84 | 85 |

3: Train using dataset artifact

86 | 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 87 | can be used to train a model directly from the dataset artifact. This also logs evaluation 88 |
89 | Usage 90 | Code $ python train.py --data {data}_wandb.yaml 91 | 92 | ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) 93 |
94 | 95 |

4: Save model checkpoints as artifacts

96 | To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. 97 | You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged 98 | 99 |
100 | Usage 101 | Code $ python train.py --save_period 1 102 | 103 | ![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) 104 |
105 | 106 |
107 | 108 |

5: Resume runs from checkpoint artifacts.

109 | 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. 110 | 111 |
112 | Usage 113 | Code $ python train.py --resume wandb-artifact://{run_path} 114 | 115 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 116 |
117 | 118 |

6: Resume runs from dataset artifact & checkpoint artifacts.

119 | Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device 120 | 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 121 | train from _wandb.yaml file and set --save_period 122 | 123 |
124 | Usage 125 | Code $ python train.py --resume wandb-artifact://{run_path} 126 | 127 | ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) 128 |
129 | 130 | 131 | 132 |

Reports

133 | 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)). 134 | 135 | Weights & Biases Reports 136 | 137 | 138 | ## Environments 139 | 140 | 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): 141 | 142 | - **Google Colab and Kaggle** notebooks with free GPU: Open In Colab Open In Kaggle 143 | - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 144 | - **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart) 145 | - **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) Docker Pulls 146 | 147 | 148 | ## Status 149 | 150 | ![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg) 151 | 152 | 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. 153 | -------------------------------------------------------------------------------- /utils/loggers/wandb/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/EASY-EAI/yolov5/4e14e074579f9902496b61a0c91ab629c40519f1/utils/loggers/wandb/__init__.py -------------------------------------------------------------------------------- /utils/loggers/wandb/log_dataset.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | from wandb_utils import WandbLogger 4 | 5 | from utils.general import LOGGER 6 | 7 | WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' 8 | 9 | 10 | def create_dataset_artifact(opt): 11 | logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused 12 | if not logger.wandb: 13 | LOGGER.info("install wandb using `pip install wandb` to log the dataset") 14 | 15 | 16 | if __name__ == '__main__': 17 | parser = argparse.ArgumentParser() 18 | parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path') 19 | parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset') 20 | parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project') 21 | parser.add_argument('--entity', default=None, help='W&B entity') 22 | parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run') 23 | 24 | opt = parser.parse_args() 25 | opt.resume = False # Explicitly disallow resume check for dataset upload job 26 | 27 | create_dataset_artifact(opt) 28 | -------------------------------------------------------------------------------- /utils/loggers/wandb/sweep.py: -------------------------------------------------------------------------------- 1 | import sys 2 | from pathlib import Path 3 | 4 | import wandb 5 | 6 | FILE = Path(__file__).resolve() 7 | ROOT = FILE.parents[3] # YOLOv5 root directory 8 | if str(ROOT) not in sys.path: 9 | sys.path.append(str(ROOT)) # add ROOT to PATH 10 | 11 | from train import parse_opt, train 12 | from utils.callbacks import Callbacks 13 | from utils.general import increment_path 14 | from utils.torch_utils import select_device 15 | 16 | 17 | def sweep(): 18 | wandb.init() 19 | # Get hyp dict from sweep agent 20 | hyp_dict = vars(wandb.config).get("_items") 21 | 22 | # Workaround: get necessary opt args 23 | opt = parse_opt(known=True) 24 | opt.batch_size = hyp_dict.get("batch_size") 25 | opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) 26 | opt.epochs = hyp_dict.get("epochs") 27 | opt.nosave = True 28 | opt.data = hyp_dict.get("data") 29 | opt.weights = str(opt.weights) 30 | opt.cfg = str(opt.cfg) 31 | opt.data = str(opt.data) 32 | opt.hyp = str(opt.hyp) 33 | opt.project = str(opt.project) 34 | device = select_device(opt.device, batch_size=opt.batch_size) 35 | 36 | # train 37 | train(hyp_dict, opt, device, callbacks=Callbacks()) 38 | 39 | 40 | if __name__ == "__main__": 41 | sweep() 42 | -------------------------------------------------------------------------------- /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().__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().__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().__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 | self.sort_obj_iou = False 95 | device = next(model.parameters()).device # get model device 96 | h = model.hyp # hyperparameters 97 | 98 | # Define criteria 99 | BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) 100 | BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device)) 101 | 102 | # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3 103 | self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets 104 | 105 | # Focal loss 106 | g = h['fl_gamma'] # focal loss gamma 107 | if g > 0: 108 | BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g) 109 | 110 | det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module 111 | self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7 112 | self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index 113 | self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance 114 | for k in 'na', 'nc', 'nl', 'anchors': 115 | setattr(self, k, getattr(det, k)) 116 | 117 | def __call__(self, p, targets): # predictions, targets, model 118 | device = targets.device 119 | lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device) 120 | tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets 121 | 122 | # Losses 123 | for i, pi in enumerate(p): # layer index, layer predictions 124 | b, a, gj, gi = indices[i] # image, anchor, gridy, gridx 125 | tobj = torch.zeros_like(pi[..., 0], device=device) # target obj 126 | 127 | n = b.shape[0] # number of targets 128 | if n: 129 | ps = pi[b, a, gj, gi] # prediction subset corresponding to targets 130 | 131 | # Regression 132 | pxy = ps[:, :2].sigmoid() * 2 - 0.5 133 | pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i] 134 | pbox = torch.cat((pxy, pwh), 1) # predicted box 135 | iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) 136 | lbox += (1.0 - iou).mean() # iou loss 137 | 138 | # Objectness 139 | score_iou = iou.detach().clamp(0).type(tobj.dtype) 140 | if self.sort_obj_iou: 141 | sort_id = torch.argsort(score_iou) 142 | b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[sort_id], gi[sort_id], score_iou[sort_id] 143 | tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio 144 | 145 | # Classification 146 | if self.nc > 1: # cls loss (only if multiple classes) 147 | t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets 148 | t[range(n), tcls[i]] = self.cp 149 | lcls += self.BCEcls(ps[:, 5:], t) # BCE 150 | 151 | # Append targets to text file 152 | # with open('targets.txt', 'a') as file: 153 | # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] 154 | 155 | obji = self.BCEobj(pi[..., 4], tobj) 156 | lobj += obji * self.balance[i] # obj loss 157 | if self.autobalance: 158 | self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() 159 | 160 | if self.autobalance: 161 | self.balance = [x / self.balance[self.ssi] for x in self.balance] 162 | lbox *= self.hyp['box'] 163 | lobj *= self.hyp['obj'] 164 | lcls *= self.hyp['cls'] 165 | bs = tobj.shape[0] # batch size 166 | 167 | return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach() 168 | 169 | def build_targets(self, p, targets): 170 | # Build targets for compute_loss(), input targets(image,class,x,y,w,h) 171 | na, nt = self.na, targets.shape[0] # number of anchors, targets 172 | tcls, tbox, indices, anch = [], [], [], [] 173 | gain = torch.ones(7, device=targets.device) # normalized to gridspace gain 174 | ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt) 175 | targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices 176 | 177 | g = 0.5 # bias 178 | off = torch.tensor([[0, 0], 179 | [1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m 180 | # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm 181 | ], device=targets.device).float() * g # offsets 182 | 183 | for i in range(self.nl): 184 | anchors = self.anchors[i] 185 | gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain 186 | 187 | # Match targets to anchors 188 | t = targets * gain 189 | if nt: 190 | # Matches 191 | r = t[:, :, 4:6] / anchors[:, None] # wh ratio 192 | j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare 193 | # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2)) 194 | t = t[j] # filter 195 | 196 | # Offsets 197 | gxy = t[:, 2:4] # grid xy 198 | gxi = gain[[2, 3]] - gxy # inverse 199 | j, k = ((gxy % 1 < g) & (gxy > 1)).T 200 | l, m = ((gxi % 1 < g) & (gxi > 1)).T 201 | j = torch.stack((torch.ones_like(j), j, k, l, m)) 202 | t = t.repeat((5, 1, 1))[j] 203 | offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j] 204 | else: 205 | t = targets[0] 206 | offsets = 0 207 | 208 | # Define 209 | b, c = t[:, :2].long().T # image, class 210 | gxy = t[:, 2:4] # grid xy 211 | gwh = t[:, 4:6] # grid wh 212 | gij = (gxy - offsets).long() 213 | gi, gj = gij.T # grid xy indices 214 | 215 | # Append 216 | a = t[:, 6].long() # anchor indices 217 | indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices 218 | tbox.append(torch.cat((gxy - gij, gwh), 1)) # box 219 | anch.append(anchors[a]) # anchors 220 | tcls.append(c) # class 221 | 222 | return tcls, tbox, indices, anch 223 | --------------------------------------------------------------------------------