{"id":13642604,"url":"https://github.com/sicara/tf2-yolov4","last_synced_at":"2025-04-05T16:10:29.446Z","repository":{"id":37658850,"uuid":"259558900","full_name":"sicara/tf2-yolov4","owner":"sicara","description":"A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection","archived":false,"fork":false,"pushed_at":"2024-03-20T15:33:12.000Z","size":3421,"stargazers_count":207,"open_issues_count":24,"forks_count":51,"subscribers_count":13,"default_branch":"master","last_synced_at":"2025-03-29T15:08:21.767Z","etag":null,"topics":["keras","object-detection","tensorflow","yolo","yolov4"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sicara.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-28T07:06:28.000Z","updated_at":"2025-02-18T13:13:32.000Z","dependencies_parsed_at":"2024-08-02T01:16:15.979Z","dependency_job_id":"32672977-0ce0-4f09-90dd-8eaa1ac3e9af","html_url":"https://github.com/sicara/tf2-yolov4","commit_stats":{"total_commits":123,"total_committers":5,"mean_commits":24.6,"dds":0.5934959349593496,"last_synced_commit":"85bc3bfc85e719297d221a2f4835213ecfdec65a"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sicara%2Ftf2-yolov4","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sicara%2Ftf2-yolov4/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sicara%2Ftf2-yolov4/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sicara%2Ftf2-yolov4/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sicara","download_url":"https://codeload.github.com/sicara/tf2-yolov4/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247361695,"owners_count":20926643,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["keras","object-detection","tensorflow","yolo","yolov4"],"created_at":"2024-08-02T01:01:33.763Z","updated_at":"2025-04-05T16:10:29.416Z","avatar_url":"https://github.com/sicara.png","language":"Python","funding_links":[],"categories":["Other Versions of YOLO"],"sub_categories":[],"readme":"# YOLOv4\n\n\u003e A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection\n\n[![Pypi Version](https://img.shields.io/pypi/v/tf2-yolov4.svg)](https://pypi.org/project/tf2-yolov4/)\n![Python Versions](https://img.shields.io/badge/python-3.6%20|%203.7%20|%203.8-%23EBBD68.svg)\n![Tensorflow Versions](https://img.shields.io/badge/TensorFlow-2.x-blue.svg)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)\n[![Python package](https://github.com/sicara/tf2-yolov4/workflows/Python%20package/badge.svg?branch=master)](https://github.com/sicara/tf2-yolov4/actions?query=workflow%3A%22Python+package%22)\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sicara/tf2-yolov4/blob/master/notebooks/YoloV4_Dectection_Example.ipynb)\n\nThis implementation runs (for now) inference with the original Darknet weights from [AlexeyAB](https://www.github.com/AlexeyAB/darknet).\nSee the roadmap section to see what's next.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"./assets/banner.jpeg\" width=\"940\" /\u003e\n\u003c/p\u003e\n\n## Installation\n\nTo install this package, you can run:\n\n```bash\npip install tf2_yolov4\npip install tensorflow\n# Check that tf2_yolov4 is installed properly\npython -c \"from tf2_yolov4.model import YOLOv4; print(YOLOv4)\"\n```\n\nRequirements:\n\n- MacOs \u003e= 10.15 since tensorflow-addons is not available for older release of MacOs\n- Python \u003e= 3.6\n- Compatible versions between TensorFlow and TensorFlow Addons: check the [compatibility matrix](https://github.com/tensorflow/addons#python-op-compatibility-matrix)\n\n## Examples in Colab\n\n- [Run detection on a single image](./notebooks/YoloV4_Dectection_Example.ipynb) / [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sicara/tf2-yolov4/blob/master/notebooks/YoloV4_Dectection_Example.ipynb)\n\n## Pretrained weights\n\nOur YOLOv4 implementation supports the `weights` argument similarly to Keras applications. To load a model with pretrained\nweights, you can simply call:\n\n```python\n# Loads Darknet weights trained on COCO\nmodel = YOLOv4(\n    input_shape,\n    num_classes,\n    anchors,\n    weights=\"darknet\",\n)\n```\n\nIf weights are available locally, they will be used. Otherwise, they will be automatically downloaded.\n\n## Roadmap\n\n- [x] Inference\n    - [x] CSPDarknet53 backbone with Mish activations\n    - [x] SPP Neck\n    - [x] YOLOv3 Head\n    - [x] Load Darknet Weights\n    - [x] Image loading and preprocessing\n    - [x] YOLOv3 box postprocessing\n    - [x] Handling non-square images\n- [ ] Training\n    - [ ] Training loop with YOLOv3 loss\n    - [ ] CIoU loss\n    - [ ] Cross mini-Batch Normalization\n    - [ ] Self-adversarial Training\n    - [ ] Mosaic Data Augmentation\n    - [ ] DropBlock\n- [ ] Enhancements\n    - [x] Automatic download of pretrained weights (like Keras applications)\n\n## References\n\n- [yolov3-tf2](https://github.com/zzh8829/yolov3-tf2)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsicara%2Ftf2-yolov4","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsicara%2Ftf2-yolov4","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsicara%2Ftf2-yolov4/lists"}