Warning
It's an ongoing project. The result isn't good right now.
Usage
1. Clone the repositories
$ git clone https://github.com/pdollar/coco.git
$ cd coco/PythonAPI/
$ make
$ python setup.py build
$ python setup.py install
$ cd ../../
$ git clone https://github.com/yunjey/pytorch-tutorial.git
$ cd pytorch-tutorial/tutorials/03-advanced/image_captioning/
2. Download the dataset
$ pip install -r requirements.txt
$ chmod +x download.sh
$ ./download.sh
3. Preprocessing
$ python build_vocab.py
$ python resize.py
4. Train the model
$ python train_bin.py
5. Test the model
$ python sample_bin.py --image='png/example.png'
TODO
- ONNX implementation
- TVM implementation
Acknowledge
Specially thank Yunjey Choi for making the image captioning tutorial for PyTorch public. Also thank jiecaoyu for making the XNOR-Net for PyTorch public.