nqanh/affordance-net
AffordanceNet - Multiclass Instance Segmentation Framework - ICRA 2018
This helps robots understand how to interact with objects by identifying what actions can be performed on them. You input images from a camera, and it outputs detected objects along with their 'affordances' (like 'grasp' for a bottle), which can then guide robotic manipulation tasks such as picking up items. Roboticists, automation engineers, or researchers developing intelligent robotic systems would find this useful.
134 stars. No commits in the last 6 months.
Use this if you are developing robotic systems that need to perceive objects in their environment and understand how to interact with them, particularly for tasks like grasping or pouring.
Not ideal if you are looking for a general-purpose object detection tool without the need for detailed interaction capabilities or if you do not have access to GPU hardware.
Stars
134
Forks
52
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 12, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nqanh/affordance-net"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.