Releases: BerkeleyAutomation/gqcnn
Releases · BerkeleyAutomation/gqcnn
GQ-CNN 1.3.0
What's Changed
- Updated
autolab_core
/perception
deps to reflect API changes.
Full Changelog: v1.2.0...v1.3.0
GQ-CNN 1.2.0
Release 1.2.0
Python 2 support has been dropped.
GQ-CNN 1.1.1
Release 1.1.1
This will be the final release to support Python 2. Starting from v1.1.2, only Python 3 will be supported.
GQ-CNN 1.1.0
Release 1.1.0
We're excited to announce GQ-CNN version 1.1.0, which brings the GQ-CNN package up to date with support for Python 2 and 3, along with the following changes:
- PEP8 compliant codebase.
- Travis CI integration for linting and installation tests.
GQ-CNN 1.0.0
Release 1.0.0
We're excited to announce GQ-CNN version 1.0.0, which brings the GQ-CNN package up to date with recent research in the Dexterity-Network (Dex-Net) project. v1.0.0 introduces support for:
- Dex-Net 4.0: Composite policies that decide whether to use a suction cup or parallel-jaw gripper.
- Fully Convolutional GQ-CNNs: Fully convolutional architectures that efficiently evaluate millions of grasps faster than prior GQ-CNNs.
Misc
- More robust ROS policy with integrated pre-processing.
- Improved interface for training GQ-CNNs and evaluating policies.
- Faster training due to improved parallelism in data prefetch/pre-processing.
- Easy-to-use shell scripts for replication of published results from Dex-Net {2.0,2.1,3.0,4.0} and FC-GQ-CNN.