Datao Liang's picture

2

Datao Liang

CantonMonkey

·

CantonMonkey

AI & ML interests

multimodel, LLM, computer vision

Organizations

CantonMonkey 's Spaces 4

Text2Image Demo

Generate images from text prompts

Diffusion3D

Generate interactive 3D scenes from text

GeoVision

Images to 3D depth maps, point clouds & camera trajectories

VGG Based Multi Input ASL Recognition

98% accuracy, a multi-input VGG model for ASL recognition