https://github.com/harshpatel44/classification-on-reconstructed-images

The project was about classifying MNIST data of low dimensions. After de-noising the reconstructed images using auto-encoders, I classified them using convolutional network and evaluated the performance. The images were reconstructed using PCA.
https://github.com/harshpatel44/classification-on-reconstructed-images

Last synced: 2 months ago
JSON representation

The project was about classifying MNIST data of low dimensions. After de-noising the reconstructed images using auto-encoders, I classified them using convolutional network and evaluated the performance. The images were reconstructed using PCA.

• Host: GitHub
• URL: https://github.com/harshpatel44/classification-on-reconstructed-images
• Owner: Harshpatel44
• Created: 2020-04-30T07:05:34.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-05-13T20:26:57.000Z (about 5 years ago)
• Last Synced: 2025-01-24T15:41:51.226Z (4 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 90.8 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Classification-on-reconstructed-Images

The project was about classifying MNIST data of low dimensions. After de-noising the reconstructed images using auto-encoders, I classified them using convolutional network and evaluated the performance. The images were reconstructed using PCA.


In this notebook, the algorithm goes as follows:

1. Prepare the MNIST dataset

2. Apply dimensionality reduction on the dataset using PCA ( variance = 0.90 )

3. Reconstruct the data from PCA ( the reconstructed data is noisy images )

4. Denoise the images using autoencoders

5. Train and test the denoised images on CNN model and evaluate the results.

6. Now, again apply dimensionality reduction using PCA with variance=0.50 and evaluate the resuls after training with CNN model.


Results:

Training Accuracy on PCA (variance = 0.90) = 98% 

Training Accuracy on PCA (variance = 0.50) = 95% 


Developers

Harsh Patel