Add Mobilenet v4 (#2325)

* Support different resolutions in load_image()

* Added MobilenetV4 model.

* Add MobileNetv4 to README
This commit is contained in:
Jani Monoses
2024-07-09 14:52:20 +03:00
committed by GitHub
parent 25960676ca
commit a226a9736b
6 changed files with 939 additions and 18 deletions

View File

@ -0,0 +1,18 @@
# candle-mobilenetv4
[MobileNetV4 - Universal Models for the Mobile Ecosystem](https://arxiv.org/abs/2404.10518)
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%
```