Handwritten Digits Generator - DCGAN (Generative Adversarial Network)

[PradnyaGaitonde]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title :
Handwritten Digits Generator - DCGAN (Generative Adversarial Network)
🔴 Aim :
The goal of this project is to develop a Generative Adversarial Network (GAN) capable of generating realistic images of handwritten digits similar to those in the MNIST dataset.
🔴 Dataset :
A collection of 60,000 training images and 10,000 test images of handwritten digits (0-9).
🔴 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.

---

🔴🟡 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 : Pradnya Gaitonde
• GitHub Profile Link : https://github.com/PradnyaGaitonde
• Email ID : [email protected]
• Participant ID (if applicable):
• Approach for this Project : Libraries Used: TensorFlow, ImageIO, Matplotlib, Numpy, PIL, TensorFlow-Docs.
  Deep Learning Concept: Utilize GANs comprising a generator and a discriminator to create realistic images.

1. Install Dependencies:
   TensorFlow, ImageIO, Matplotlib, Numpy, PIL, TensorFlow-Docs.
2. Load and Prepare Dataset:
   Load MNIST dataset using TensorFlow. Normalize images to the range [-1, 1].
3. Build Models:
   Generator: Neural network to generate images from noise.
   Discriminator: Neural network to distinguish real images from fake ones.
4. Define Loss and Optimizers:
   Use BinaryCrossentropy for loss.
   Use Adam optimizers for both models.
5. Training Loop:
   Train both networks simultaneously.
   Save generated images and model checkpoints periodically.
6. Generate and Save Images:
   Create and save images during training to visualize progress.
7. Create Animated GIF:
   Compile saved images into a GIF to observe training evolution.

• What is your participant role? (Mention the Open Source program) Contributor in GSSOC24.

---

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! 😊

[abhisheks008]

Similar problem statement is already present in this repo.

Closing this issue as not planned.