This project is highly inspired from the tensorflow tutorial on Image Captioning. To learn more on how to build the model, check out the tutorial here
The model was trained using more than half a million captions from MS-COCO dataset.
Predicted Caption: a man riding a dirt bike on a dirt path <end>
- Download the notebook.py and checkpoints folder.
- Place the target image in the root directory and change the image name in the code (line 370) in notebook.py.
- Open Command Prompt or Terminal and change directory to project root directory.
- Execute below statement.
python notebook.py
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.