ggcnn
ggcnn copied to clipboard
Labeling the dataset
Hi Doug, Sorry for my question in advance. How do you labeled the dataset in order to obtain the txt file, did you use a specific tool?Moreover, do you apply some augmentation to your dataset in order to increment it? I've found this grasping-labeling tool for labeling the images (https://github.com/ulaval-damas/grasp-rectangle-labelling )but the format I obtain is different from your txt file.
Bests,
Olivia
Hi Olivia,
I never labelled any of the data myself. I used either the existing Cornell dataset (which has one point of the rectangle per line
x y) or the Jacquard dataset (which has format like
x;y;angle;width;height`).
Yes, the data loader applies random rotate and zoom/crop: https://github.com/dougsm/ggcnn/blob/master/utils/data/grasp_data.py#L51