Files
usls/examples/blip
Jamjamjon f0fd4936e8 Add florence2 model
* Add florence2-base model for all tasks

* Update annotator.rs
2024-09-21 20:23:42 +08:00
..
2024-09-21 20:23:42 +08:00

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