https://github.com/aneripatel28/imagecaptiongenerator
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: AneriPatel28
- Language: Python
- Default Branch: main
- Size: 2.87 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Image Caption Generator
This project implements an Image Caption Generator that combines Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to generate descriptive captions for images. The model is trained on the Flickr8k dataset and utilizes the Xception architecture for feature extraction.
Features
- Image Feature Extraction: Uses the Xception model to extract features from images.
- Caption Generation: Employs an RNN to generate captions based on extracted image features.
- Graphical User Interface: Provides a user-friendly interface for uploading images and displaying generated captions.
Installation
- Clone the Repository:
bash
git clone https://github.com/AneriPatel28/ImageCaptionGenerator.git
- Navigate to the Project Directory:
bash
cd ImageCaptionGenerator
- Install Dependencies:
Ensure you have Python 3.x installed. Install the required packages using pip:
bash
pip install -r requirements.txt
Usage
- Download the Flickr8k Dataset:
Download the dataset from Kaggle and place the images in the Flicker8k_Dataset directory and the captions file in the Flickr8k_text directory.
- Preprocess the Data:
Run the preprocess_data.py script to preprocess the images and captions:
bash
python preprocess_data.py
- Train the Model:
Execute the train_model.py script to train the caption generator:
bash
python train_model.py
- Generate Captions:
After training, use the generate_caption.py script to generate captions for new images:
bash
python generate_caption.py --image_path path_to_image
- Launch the GUI:
Run the app.py script to start the graphical user interface:
bash
python app.py
Upload an image through the GUI to view the generated caption.
Dependencies
- Python 3.x
- TensorFlow
- Keras
- Flask
- Pillow
- NumPy
- Matplotlib
Install all dependencies using the requirements.txt file:
bash
pip install -r requirements.txt
Acknowledgments
This project is inspired by various image captioning research and implementations. Special thanks to the contributors of the Flickr8k dataset.
License
This project is licensed under the MIT License.
Owner
- Login: AneriPatel28
- Kind: user
- Repositories: 1
- Profile: https://github.com/AneriPatel28
GitHub Events
Total
- Push event: 2
Last Year
- Push event: 2