[Project Addition] Facial Keypoint Detection using DL

[Arihant-Bhandari]

Pull Request for DL-Simplified 💡

Issue Title : #780 Facial Keypoint Detection using DL

• Info about the related issue (Aim of the project): Detecting Facial Keypoints using images of faces.
• Name: Arihant Bhandari
• GitHub ID: https://github.com/Arihant-Bhandari
• Email ID: [email protected]
• Identify yourself: GSSoC 2024 Contributor

Closes: #780 Facial Keypoint Detection using DL

Describe the add-ons or changes you've made 📃

Wrote code for preprocessing and loading images from dataset, used labels to lock onto features from CSV file, created models including custom CNN as well as pre-trained models, like ResNet50, VGG16 and so on.

Type of change ☑️

What sort of change have you made:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

Models	Validation MSE	Validation MAE	Test MSE	Test MAE
ResNet-50	0.0022	0.0221	0.0020	0.0218
InceptionV3	0.0023	0.0277	0.0021	0.0273
CNN	0.0015	0.0213	0.0013	0.0214
VGG16	0.0022	0.0262	0.0019	0.0253
MobileNet	0.0023	0.0278	0.0022	0.0280
DenseNet-121	0.0019	0.0245	0.0017	0.0240
Xception	0.0019	0.0240	0.0018	0.0239

Checklist: ☑️

• My code follows the guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added things that prove my fix is effective or that my feature works.
• Any dependent changes have been merged and published in downstream modules.

[github-actions]

Our team will soon review your PR. Thanks @Arihant-Bhandari :)