#Kaolin, #PyTorchOpenSourceLibrary; #3-Ddeeplearningresearch; #NVIDIA; #California
California (U.S.), Dec 4 (Canadian-Media): To address the lack of readily available technological tools such as robots, self-driving vehicles, smartphones, and other devices that currently generate a growing amount of 3-D data, a team of researchers at NVIDIA (California) had recently created Kaolin, a PyTorch open-source library aimed at advancing and facilitating 3-D deep learning research to meet the demands of real-world environments, media reports said.
Kaolin offers valuable tools for both experienced developers of deep learning models as well as for beginners. Several state-of-the-art architectures can be found within the library, as a starting point or as a source of inspiration for their own models.
"While active 3-D deep learning researchers view Kaolin as a means to accelerate their research, newcomers into this field are turning to Kaolin for an idea of where to begin," Krishna Murthy Jatavallabhula, one of the researchers who carried out the study said.
"Currently, there is not a single open-source software library that supports multiple representations of 3-D data, multiple tasks, and evaluation criteria," Jatavallabhula told TechXplore.
"We decided to address this gap in the literature by creating Kaolin, the first comprehensive 3-D deep learning library."
Kaolin includes several graphics modules to edit 3-D images, with functions such as rendering, lighting, shading and view warping. Moreover, it supports a wide range of loss functions and evaluation metrics, allowing researchers to easily evaluate their deep learning algorithms.
Kaolin also contains a variety of tools for constructing deep learning architectures that can analyze 3-D data and allows researchers to load, preprocess, and manipulate 3-D data before it is used to train deep learning algorithms.
"Typically, 3-D deep learning researchers need to write a lot of boilerplate code for their research projects," Jatavallabhula explained. "With Kaolin, however, researchers only need to implement the novel parts of their project, as Kaolin packages a comprehensive set of utilities for data loading, conversion and evaluation."
Meanwhile, Jatavallabhula and his colleagues are planning to work on extending Kaolin and enhancing its capabilities further.
"Our plan is to add more deep learning models to our model zoo (collection of AI models)...in short, we plan on making Kaolin a one-stop platform for 3-D deep learning research," said Jatavallabhula