Sky-Fleet-classifier-using-CNN-Imagenet-models-

This project is a deep learning image classification model that utilizes Imagenet's pre-trained models to classify a dataset of sky fleet images. The dataset used in this project can be found at this Link.
Sample images of this dataset

The dataset contains 5 different categories of images, and the model has been finetuned to fit these categories using the ResNet152V2 model. The model achieved a training accuracy of 96.96% and a validation accuracy of 87.86%.

In the Resnet.ipynb file, you will find the complete training code for the model. Once the model has been trained, you can use the prediction.ipynb file to predict images using the saved pretrained model. The output of the program will be the predicted category for each image.

Please note that the dataset used in this project is provided for demonstration purposes only and is not intended for commercial use.
Output of program

Getting Started

1. Clone the repository
   

git clone https://github.com/ShubhamSongire/Sky-Fleet-Classifier-using-CNN-Imagenet-models

2. Install the required dependencies

pip install -r requirements.txt

3. Run the Resnet.ipynb file to train the model

4. Run the prediction.ipynb file to predict images using the trained model

File Structure

├── Resnet.ipynb
├── Inception V2.ipynb
├── prediction.ipynb
├── requirements.txt
└── dataset/
├── train/
│ ├── rocket /
│ ├── fighter_jet /
│ ├── helicopter /
│ ├── passenger_plane /
│ └── drone /
├── val/
│ ├── rocket /
│ ├── fighter_jet /
│ ├── helicopter /
│ ├── passenger_plane /
│ └── drone /

Built With

Keras - The deep learning framework used
Imagenet - Pre-trained models used

Authors - ShubhamSongire

Acknowledgments

Imagenet for providing the pre-trained models used in this project
Dataset for providing the dataset used in this project