Sea Animals Detection using Deep Neural Networks

[PiyushBL45t]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Sea Animals Detection using Deep Learning
:red_circle: Aim : To create a DL Model that will detect the sea animals and creatures
:red_circle: Dataset : https://www.kaggle.com/datasets/vencerlanz09/sea-animals-image-dataste
:red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 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.

---

:red_circle::yellow_circle: 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.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Piyush Bhujbal
• GitHub Profile Link : https://www.github.com/PiyushBL45t
• Email ID : bhujbalpiyush@gmail.com
• Participant ID (if applicable):
• Approach for this Project :
  1. Perform Image preprocessing if required.
  2. Then perform image visualization.
  3. Create training, testing and validation data sets using image data generation.
  4. Create a sample summary of the CNN model.
  5. Use a proper optimizer to construct CNN and optimize the algorithm.
  6. Implement model training using CNN and pre-trained models.
  7. Evaluate each models performance.
  8. Make predictions using test dataset.
  9. Document all the parameters like epochs, training time as well as accuracy and loss functions used.
• What is your participant role? (Mention the Open Source program): Social Summer of Code Participant

---

Happy Contributing 🚀

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

[abhisheks008]

Issue assigned to you @PiyushBL45t

[PiyushBL45t]

Thank you.

On Thu, Jul 20, 2023, 8:32 PM Abhishek Sharma @.***> wrote:

Issue assigned to you @PiyushBL45t https://github.com/PiyushBL45t

— Reply to this email directly, view it on GitHub https://github.com/World-of-ML/DL-Simplified/issues/349#issuecomment-1644091039, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASB2BKOXSIVUVCBWMIIMQDLXRFCBVANCNFSM6AAAAAA2OYDGAY . You are receiving this because you were mentioned.Message ID: @.***>

[abhisheks008]

Is this the one you are talking about? @PiyushBL45t

[PiyushBL45t]

Yes

On Wed, Jul 26, 2023, 9:41 PM Abhishek Sharma @.***> wrote:

Is this the one you are talking about? @PiyushBL45t https://github.com/PiyushBL45t

— Reply to this email directly, view it on GitHub https://github.com/World-of-ML/DL-Simplified/issues/349#issuecomment-1652119526, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASB2BKOKAZVCIFWKSTICKH3XSE6SRANCNFSM6AAAAAA2OYDGAY . You are receiving this because you were mentioned.Message ID: @.***>

[abhisheks008]

You can edit this issue template and start working on it. Make sure you complete it within the deadline.

[PiyushBL45t]

Ok, sounds good. Then shall I say that I will work on Enhancement of the project

On Wed, Jul 26, 2023 at 10:17 PM Abhishek Sharma @.***> wrote:

You can edit this issue template and start working on it. Make sure you complete it within the deadline.

— Reply to this email directly, view it on GitHub https://github.com/World-of-ML/DL-Simplified/issues/349#issuecomment-1652169356, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASB2BKNC6UH6ETEJ6KNSU4DXSFC3VANCNFSM6AAAAAA2OYDGAY . You are receiving this because you were mentioned.Message ID: @.***>

[abhisheks008]

Can you clarify more about it?

[Surya735]

I would like to work on this issue. Can you please clarify what 'detection' encompasses? Does it mean to 'classify sea animals' ?

[abhisheks008]

Yes. Can you please share the approach for solving this issue/project? @Surya735

[Surya735]

Hi @abhisheks008, My initial approach would be using self supervised learning for classification and would consist of the following:

1) A convolutional network to learn features, constrained to allow the features to project data points onto lower dimensional manifolds

2) A second network that focuses on classification of data points on the basis of the manifolds on which the feature vectors obtained from above lie

[abhisheks008]

Hi @Surya735 it is a nice approach for solving this issue. Try to implement 3-4 deep learning methods and make a comparison to find out the best fitted model based on the accuracy scores of the models generated. You can check out the existing projects in this repository to get an idea about the same.

Issue assigned to you under OSEN. Go ahead!

[Surya735]

Thank you for assigning the issue to me @abhisheks008

[abhisheks008]

Hi @Surya735, updates on this issue?

[Surya735]

Hey @abhisheks008 ,

I have finished the necessary literature review and will begin working on the code now. Although I have my end semester exams starting shortly prior to which I have a round of mini project submissions for various subjects. So unfortunately I won't have a lot of time to work on it currently and I really hope that's not an issue because I would genuinely love to contribute to the issue. Are you looking at any deadline on this?

[abhisheks008]

Hi @Surya735, there is no such deadline from my side. But as you are a part of a particular program, I believe following the deadline of OSEN comes under code of conduct, which you should follow.

Anyways take your time and all the best for your semester exams. Good luck!

[Surya735]

Hi @abhisheks008 Thank you so much for understanding. I will definitely be working on it every chance I get and will keep you updated

[abhisheks008]

This issue will not be considered under CollabCode Open Source event organized by OSEN as the program ends on November 20th, 2023.

[aindree-2005]

Full name : Aindree Chatterjee GitHub Profile Link : https://www.github.com/aindree-2005 Email ID : aindree2005@gmail.com Approach for this Project : Using CNNS and data augmentation What is your participant role? CodePeak @abhisheks008 can I work on this?

[abhisheks008]

Issue assigned to you @aindree-2005