Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

Assigning this issue to you @cosmicishan

@abhisheks008 I have sent the proposal for this issue under WOC in devfolio
Pls have a look at it

Proposals are under review. @Rangan2005

For issue #932 (Hair Type Classification Using Deep Learning) my approach involves implementing an ensemble of three deep learning models: ResNet50, MobileNetV2, and VGG16.
The plan is :

1.Train each model individually and evaluate their performance using metrics like accuracy, precision, and recall scores .
2.Combine these models' predictions using a weighted voting mechanism to improve classification accuracy.
3.Compare the ensemble’s results with individual models to demonstrate the advantages of using an ensemble approach.

Assigned @KrishnaChaitanya16

@abhisheks008 Am I required to clone the whole repo or can I create a repo of my own and make that repo a submodule of the main repo

Fork the repository and create a pull request to the main branch.

@abhisheks008 What are the accuracy scores expected for each model and the ensemble .

Accuracy scores should be higher than 90%

@abhisheks008 I have changed my plan slightly , I have used ConvNxt instead of MobileNetV2 and i have achieved the following results

Classification Report for hair-convnext-tiny:

              precision    recall  f1-score   support

    Straight       0.92      0.96      0.94       195

        Wavy       0.87      0.82      0.84       126

       curly       0.89      0.95      0.92       186

  dreadlocks       0.98      0.98      0.98       193

       kinky       0.94      0.80      0.86        95

    accuracy                           0.92       795

   macro avg       0.92      0.90      0.91       795

weighted avg       0.92      0.92      0.92       795

=======================================

Classification Report for hair-vgg16:

              precision    recall  f1-score   support

    Straight       0.88      0.94      0.91       195

        Wavy       0.89      0.83      0.86       126

       curly       0.91      0.92      0.91       186

  dreadlocks       0.98      0.97      0.98       193

       kinky       0.90      0.85      0.88        95

    accuracy                           0.92       795

   macro avg       0.91      0.90      0.91       795

weighted avg       0.92      0.92      0.92       795

=========================================

Classification Report for hair-resnet50:

              precision    recall  f1-score   support

    Straight       0.92      0.92      0.92       195

        Wavy       0.82      0.81      0.82       126

       curly       0.86      0.92      0.89       186

  dreadlocks       0.97      0.99      0.98       193

       kinky       0.91      0.77      0.83        95

    accuracy                           0.90       795

   macro avg       0.90      0.88      0.89       795

weighted avg       0.90      0.90      0.90       795

============================================

Ensemble Model Classification Report:

              precision    recall  f1-score   support

    Straight       0.92      0.94      0.93       195

        Wavy       0.88      0.85      0.86       126

       curly       0.91      0.93      0.92       186

  dreadlocks       1.00      1.00      1.00       193

       kinky       0.90      0.86      0.88        95

    accuracy                           0.93       795

   macro avg       0.92      0.92      0.92       795

weighted avg       0.93      0.93      0.93       795

Is this ok? if yes i will proceed with the ensemble of these models.