We present a fine-tuned YOLOs model for license plate detection, which achieved an AP of 47.9 on the test set. Our model was trained for 200 epochs on a single GPU using Google Colab, utilizing the DETR loss and a base-sized YOLOs model. We evaluated our model on various IoU thresholds and obtained an average recall of 0.676 at IoU=0.50:0.95, with location being medium.

You can use cURL or any other http client to run inferences:

```bash
curl -X POST \
    -H "Authorization: bearer $(deepctl auth token)"  \
    -F image=@my_image.jpg  \
    'https://api.deepinfra.com/v1/inference/nickmuchi/yolos-small-rego-plates-detection'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "score": 0.9939407110214233,
      "label": "remote",
      "box": {
        "xmin": 46,
        "ymin": 72,
        "xmax": 181,
        "ymax": 119
      }
    },
    {
      "score": 0.983637809753418,
      "label": "cat",
      "box": {
        "xmin": 12,
        "ymin": 54,
        "xmax": 319,
        "ymax": 470
      }
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


You can use our command-line tool [deepctl](/docs/getting-started) to run
inferences:

```bash
deepctl infer \
    -m 'nickmuchi/yolos-small-rego-plates-detection'  \
    -i image=@my_image.jpg
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "score": 0.9939407110214233,
      "label": "remote",
      "box": {
        "xmin": 46,
        "ymin": 72,
        "xmax": 181,
        "ymax": 119
      }
    },
    {
      "score": 0.983637809753418,
      "label": "cat",
      "box": {
        "xmin": 12,
        "ymin": 54,
        "xmax": 319,
        "ymax": 470
      }
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


image

The webhook to call when inference is done, by default you will get the output in the response of your inference request