CeLuigi / Grid-Anchor-based-Image-Cropping-Pytorch

PyTorch implementation of "Grid anchor based image cropping"

Grid-Anchor-based-Image-Cropping-Pytorch

This code includes several extensions we have made to our conference version. Please read the paper for details.

Requirements

python 2.7, pytorch 0.4.1, numpy, cv2, scipy.

Usage

1. Download the source code, the dataset and the pretrained model.

2. Run TrainModel.py to train a new model on our dataset or Run demo_eval.py to test the pretrained model on any images.

3. To change the aspect ratio of generated crops, please change the generate_bboxes function in croppingDataset.py (line 115).

Annotation software

The executable annotation software can be found here.

Other implementation

1. PyTorch 1.0 or later
2. Matlab (conference version)