flystem-usls

History

Jamjamjon f0fd4936e8 Add florence2 model * Add florence2-base model for all tasks * Update annotator.rs		2024-09-21 20:23:42 +08:00
..
README.md	0.0.14: `DataLoader` now support video and streaming	2024-09-16 10:41:16 +08:00
main.rs	Add florence2 model	2024-09-21 20:23:42 +08:00

README.md

This demo shows how to use BLIP to do conditional or unconditional image captioning.

Quick Start

cargo run -r --example blip

Results

[Unconditional]: a group of people walking around a bus
[Conditional]: three man walking in front of a bus
Some(["three man walking in front of a bus"])

TODO

Multi-batch inference for image caption
VQA
Retrival
TensorRT support for textual model