hamed-hosseini / ggcnn

Improving the Successful Robotic GraspDetection on Convolutional Neural Networks

Improving the Successful Robotic GraspDetection on Convolutional Neural Networks

This repository contains the implementation of the Improving the Successful Robotic GraspDetection on Convolutional Neural Networks from the paper:

Improving the Successful Robotic GraspDetection on Convolutional Neural Networks

*Hamed Hosseini, Mehdi Tale Masouleh, Ahmad Kalhor

Contact

Any questions or comments contact Hamed Hosseini.

Installation

⚠️ This code was developed with Python 3.6 on Ubuntu 16.04. Python requirements can installed by:

pip install -r requirements.txt

Datasets

Currently, both the Cornell Grasping Dataset and Jacquard Dataset are supported.

Cornell Grasping Dataset

1. Download the and extract Cornell Grasping Dataset.
2. Convert the PCD files to depth images by running python -m utils.dataset_processing.generate_cornell_depth <Path To Dataset>

Jacquard Dataset

1. Download and extract the Jacquard Dataset.

Pre-trained Models

Coming Soon

Training

Training is done by the train_ggcnn.py script. Run train_ggcnn.py --help to see a full list of options, such as dataset augmentation and validation options.

Training Figures:

Evaluation/Visualisation

Predictions are:

Running on a Robot

comming soon!