https://github.com/ladyamely/densenet-tensorflow

This repository contains an implementation of the DenseNet architecture in TensorFlow
https://github.com/ladyamely/densenet-tensorflow

densenet densenet-tensorflow machine-learning python tensorflow

Last synced: 4 months ago
JSON representation

This repository contains an implementation of the DenseNet architecture in TensorFlow

• Host: GitHub
• URL: https://github.com/ladyamely/densenet-tensorflow
• Owner: LadyAmely
• Created: 2024-12-23T13:05:42.000Z (6 months ago)
• Default Branch: master
• Last Pushed: 2025-01-09T21:01:30.000Z (5 months ago)
• Last Synced: 2025-02-20T00:43:24.313Z (4 months ago)
• Topics: densenet, densenet-tensorflow, machine-learning, python, tensorflow
• Language: Python
• Homepage:
• Size: 507 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# DenseNet Implementation in TensorFlow

---

![](https://komarev.com/ghpvc/?username=LadyAmely&color=green)

This repository contains an implementation of the DenseNet architecture in TensorFlow. DenseNet is a convolutional neural network (CNN) architecture known for its efficiency in parameter usage and performance in image classification tasks.

## Dataset

In this project, VGGNet was trained on the Fashion-MNIST dataset, showcasing its effectiveness even on simpler datasets for classification tasks.

---

## Results

Using Fashion-MNIST dataset, the model achieved the following results:

- **Precision**: **88.57%**

- **Recall**: **88.53%**

- **F1-Score**: **88.50%**

---

![Fashion-MNIST](https://github.com/LadyAmely/DenseNet-tensorflow/blob/master/plots/predictions_visualizations.png)

## References

Original Paper: ["Densely Connected Convolutional Networks (Huang et al., 2017)"](https://arxiv.org/pdf/1608.06993).