Pokémon classification using Deep learning

[Pratzybha]

Deep Learning Simplified Repository (Proposing new issue)
🔴 Project Title : Pokémon classification using Deep learning
🔴 Aim : To classify 150 different Pokémon species of gen1 based on 7000+ labelled image dataset
🔴 Dataset : https://www.kaggle.com/datasets/lantian773030/pokemonclassification
🔴 Approach :

Algorithms :-

CNN
VGG16
Inception

📍 Follow the Guidelines to Contribute in the Project :
You need to create a separate folder named as the Project Title.
Inside that folder, there will be four main components.
Images - To store the required images.
Dataset - To store the dataset or, information/source about the dataset.
Model - To store the machine learning model you've created using the dataset.
requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.
🔴🟡 Points to Note :

The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
"Issue Title" and "PR Title should be the same. Include issue number along with it.
Follow Contributing Guidelines & Code of Conduct before start Contributing.
✅ To be Mentioned while taking the issue :

Full name : Pratibha Balgi
GitHub Profile Link : https://github.com/Pratzybha
Email ID : [email protected]
Participant ID (if applicable): -
Approach for this Project : CNN
What is your participant role? (Mention the Open Source program) GSSoC'24 Contributor
Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions]

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

[Pratzybha]

@abhisheks008 Please assign it to me. GSSOC24-EXT

[abhisheks008]

Assigned to you @Pratzybha

[Smritigit1202]

Hey, is the issue still available to resolve?
If yes, could you please assign me?

[abhisheks008]

Hey, is the issue still available to resolve? If yes, could you please assign me?

Can you please mention in which open source event you are participating in?
@Smritigit1202

[Smritigit1202]

Currently participating in KWOC, but I got no issue even if no event is been taken into consideration.
Happy to contribute without the tag as well.

[abhisheks008]

Currently participating in KWOC, but I got no issue even if no event is been taken into consideration. Happy to contribute without the tag as well.

Cool! Can you please share your approach for this problem statement? I'll assign you this issue under KWOC if it fulfills the approach criteria.

@Smritigit1202

[Smritigit1202]

The approach I am thinking to use is - Use CNNs on pokemon dataset by classification then train the augmented dataset diversity(to overcome overfitting) then test from separate dataset, more images on google ofc!
What do u think? Shall I use this approach?

[abhisheks008]

The approach I am thinking to use is - Use CNNs on pokemon dataset by classification then train the augmented dataset diversity(to overcome overfitting) then test from separate dataset, more images on google ofc! What do u think? Shall I use this approach?

Apart from CNN, what other models you are planning for this problem statement? As you know in this project repository we mainly focus on 3-4 models for each problem statement.

[DeXtAr47-oss]

Full name : Pritam Das
GitHub Profile Link : https://github.com/DeXtAr47-oss
Email ID : [email protected]
Approach for this project: I would first load the model from kaggle, next i would be dividing the datasets into training, validaition and test part also i would be doing few preprocessing like resizing, scaling pixel values and performing image processing steps after that i would like to use various models like resnet, mobilenet or any other models and then calculate its performance using various metric based on the performance i would be doing hyperparameter tunning for more better results after that would be using the testing data to finally classify the pokemon.
Participant role: currently participating in WOC4.0

[abhisheks008]

Full name : Pritam Das GitHub Profile Link : https://github.com/DeXtAr47-oss Email ID : [email protected] Approach for this project: I would first load the model from kaggle, next i would be dividing the datasets into training, validaition and test part also i would be doing few preprocessing like resizing, scaling pixel values and performing image processing steps after that i would like to use various models like resnet, mobilenet or any other models and then calculate its performance using various metric based on the performance i would be doing hyperparameter tunning for more better results after that would be using the testing data to finally classify the pokemon. Participant role: currently participating in WOC4.0

Hi @DeXtAr47-oss for this you need to submit the proposals in Devfolio. Please follow the process and submit the same as mentioned by the WOC team.