371a08011f
* Add MODNet for portrait matting * Minor fixes * Move assets to home directory * Add colormap * ci * Update README.md |
||
|---|---|---|
| .. | ||
| README.md | ||
| main.rs | ||
README.md
This demo shows how to use BLIP to do conditional or unconditional image captioning.
Quick Start
cargo run -r --example blip
BLIP ONNX Model
Results
[Unconditional image captioning]: a group of people walking around a bus
[Conditional image captioning]: 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