# State of art the Head Pose Estimation in Tensorflow2
This repository includes:
- ["WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose" (BMVC 2020).](https://www.bmvc2020-conference.com/assets/papers/0907.pdf) adapted from the [original source code](https://github.com/Ascend-Research/HeadPoseEstimation-WHENet).
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://arxiv.org/abs/1905.00641) adapted from https://github.com/StanislasBertrand/RetinaFace-tf2.
<img src=images/output.png height="220"/>
## Install
You can install this repository with pip (requires python>=3.6);
```
pip install headpose_estimation
```
```bash
pip install git+https://github.com/geekysethi/headpose_estimation
```
You can also install with the `setup.py`
## With Face Detection
To perform detection you can simple use the following lines:
```python
import cv2
from headpose_estimation import Headpose
headpose = Headpose()
img = cv2.imread("path_to_im.jpg")
detections,image = headpose.run(img)
```
This will return a list of dictionary which looks like this `[{'bbox': [xmin, ymin, xmax, ymax], 'yaw': yaw_value, 'pitch': pitch_value, 'roll': roll_value}`
## Without Face Detection
To perform detection you can simple use the following lines:
```python
import cv2
from headpose_estimation import Headpose
headpose = Headpose(face_detection=False)
imgcrop = cv2.imread("path_to_im.jpg")
detections,image = headpose.run(imgcrop)
```
In this case it will return a list of dictionary which looks like this `[{'yaw': yaw_value, 'pitch': pitch_value, 'roll': roll_value}`
## Dependncies
* EfficientNet https://github.com/qubvel/efficientnet
Raw data
{
"_id": null,
"home_page": "https://github.com/geekysethi/headpose_estimation",
"name": "headpose-detection",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "python,image,face detection,headpose estimation,machine learning,computer vision",
"author": "Ashish Sethi",
"author_email": "<ashish18024@iiitd.ac.in>",
"download_url": "https://files.pythonhosted.org/packages/35/e2/c51e37da9136df34485c7d16cf5cf2b6739cb751cad3f6760c956fc9068c/headpose_detection-0.0.4.tar.gz",
"platform": null,
"description": "# State of art the Head Pose Estimation in Tensorflow2 \n\nThis repository includes:\n- [\"WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose\" (BMVC 2020).](https://www.bmvc2020-conference.com/assets/papers/0907.pdf) adapted from the [original source code](https://github.com/Ascend-Research/HeadPoseEstimation-WHENet).\n\n\n- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://arxiv.org/abs/1905.00641) adapted from https://github.com/StanislasBertrand/RetinaFace-tf2.\n\n\n\n\n\n<img src=images/output.png height=\"220\"/> \n\n\n\n## Install\n\nYou can install this repository with pip (requires python>=3.6);\n\n```\npip install headpose_estimation\n```\n\n```bash\npip install git+https://github.com/geekysethi/headpose_estimation\n```\n\nYou can also install with the `setup.py`\n\n## With Face Detection\nTo perform detection you can simple use the following lines:\n\n```python\nimport cv2\nfrom headpose_estimation import Headpose\nheadpose = Headpose()\nimg = cv2.imread(\"path_to_im.jpg\")\ndetections,image = headpose.run(img)\n```\n\nThis will return a list of dictionary which looks like this `[{'bbox': [xmin, ymin, xmax, ymax], 'yaw': yaw_value, 'pitch': pitch_value, 'roll': roll_value}`\n\n\n## Without Face Detection\nTo perform detection you can simple use the following lines:\n\n```python\nimport cv2\nfrom headpose_estimation import Headpose\nheadpose = Headpose(face_detection=False)\nimgcrop = cv2.imread(\"path_to_im.jpg\")\ndetections,image = headpose.run(imgcrop)\n```\n\nIn this case it will return a list of dictionary which looks like this `[{'yaw': yaw_value, 'pitch': pitch_value, 'roll': roll_value}`\n\n## Dependncies\n* EfficientNet https://github.com/qubvel/efficientnet\n",
"bugtrack_url": null,
"license": "",
"summary": "Head pose estimation module",
"version": "0.0.4",
"split_keywords": [
"python",
"image",
"face detection",
"headpose estimation",
"machine learning",
"computer vision"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "b550e9f044ca9d69d0f21612ea4d15ac",
"sha256": "647e9ad232c380419665179d6f3ca1668d949b3f33ba7ff260a2a53a802fc9b6"
},
"downloads": -1,
"filename": "headpose_detection-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b550e9f044ca9d69d0f21612ea4d15ac",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 16309935,
"upload_time": "2022-12-05T14:47:18",
"upload_time_iso_8601": "2022-12-05T14:47:18.215848Z",
"url": "https://files.pythonhosted.org/packages/31/aa/2b359cb464ec91305d496d33a830fd453aeb1f74a5393fa0312d093d42c6/headpose_detection-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "4c748a13e23d5ccf4aa6b51c5bda8191",
"sha256": "978cfbbaa03ce8611dfecc18d3773f4360dfe6d7dbe856abc4f57c997b5d33fc"
},
"downloads": -1,
"filename": "headpose_detection-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "4c748a13e23d5ccf4aa6b51c5bda8191",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 16307006,
"upload_time": "2022-12-05T14:47:24",
"upload_time_iso_8601": "2022-12-05T14:47:24.230022Z",
"url": "https://files.pythonhosted.org/packages/35/e2/c51e37da9136df34485c7d16cf5cf2b6739cb751cad3f6760c956fc9068c/headpose_detection-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-05 14:47:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "geekysethi",
"github_project": "headpose_estimation",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "headpose-detection"
}
JSON
