mirror of https://github.com/huggingface/candle.git synced 2025-06-15 02:16:37 +00:00

Files

Jani Monoses 86613c00e2 MobileCLIP models S1 and S2 (#2454 )

* Allow loading images with given std and mean

* OpenCLIP text encoder component

* Two MobileCLIP models

* Clippy fixes.

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>

2024-08-29 15:38:58 +02:00

main.rs

MobileCLIP models S1 and S2 (#2454 )

2024-08-29 15:38:58 +02:00

README.md

Add Mobilenet v4 (#2325 )

2024-07-09 13:52:20 +02:00

README.md

candle-mobilenetv4

MobileNetV4 - Universal Models for the Mobile Ecosystem This candle implementation uses pre-trained MobileNetV4 models from timm for inference. The classification head has been trained on the ImageNet dataset and returns the probabilities for the top-5 classes.

Running an example

$ cargo run --example mobilenetv4 --release  -- --image candle-examples/examples/yolo-v8/assets/bike.jpg --which medium
loaded image Tensor[dims 3, 256, 256; f32]
model built
unicycle, monocycle     : 20.18%
mountain bike, all-terrain bike, off-roader: 19.77%
bicycle-built-for-two, tandem bicycle, tandem: 15.91%
crash helmet            : 1.15%
tricycle, trike, velocipede: 0.67%