https://github.com/anujdutt9/cnn-deep-layer-filters-visualization

CNN Deep Layer Filters Visualization using Tensorflow.
https://github.com/anujdutt9/cnn-deep-layer-filters-visualization

convolutional-neural-networks hidden-layers numpy python35 tensorflow visualization

Last synced: 4 days ago
JSON representation

CNN Deep Layer Filters Visualization using Tensorflow.

• Host: GitHub
• URL: https://github.com/anujdutt9/cnn-deep-layer-filters-visualization
• Owner: anujdutt9
• Created: 2017-08-18T00:37:45.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-08-18T14:57:24.000Z (over 7 years ago)
• Last Synced: 2024-11-13T03:34:55.614Z (2 months ago)
• Topics: convolutional-neural-networks, hidden-layers, numpy, python35, tensorflow, visualization
• Language: Python
• Homepage:
• Size: 22.1 MB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# CNN-Hidden-Layer-Filters-Visualization

***This project contains the code for visualizing the Filters in the Hidden Layers of a Convolutional Neural Network. To depict this, I have used the MNIST dataset as Input.***

# Requirements:

1. **Tensorflow v1.2.1**

2. **Numpy 1.13.0 [+ mkl for Windows]**

3. **Python 3.5 64-bit**

# Usage:

```

python3 main.py

```

# Results:

1. *Input Image*

![Output a1](Outputs/InputImage.png?raw=true "Output a1")

2. *First Hidden Layer Filters*

![Output a1](Outputs/FirstHiddenLayer.png?raw=true "Output a1")

3. *Second Hidden Layer Filters*

![Output a1](Outputs/SecondHiddenLayer.png?raw=true "Output a1")

4. *Third Hidden Layer Filters*

![Output a1](Outputs/ThirdHiddenLayer.png?raw=true "Output a1")  

5. *Pooling Layer Visualization*

![Output a1](Outputs/PoolingLayer.png?raw=true "Output a1")