The BEiT model is a Vision Transformer (ViT) pre-trained on ImageNet-21k, a dataset of 14 million images and 21,841 classes, using a self-supervised approach. The model was fine-tuned on the same dataset and achieved state-of-the-art performance on various image classification benchmarks. The BEiT model uses relative position embeddings and mean-pools the final hidden states of the patch embeddings for classification.

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/microsoft/beit-base-patch16-224-pt22k-ft22k'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "label": "Maltese dog, Maltese terrier, Maltese",
      "score": 0.9235488176345825
    },
    {
      "label": "Lhasa, Lhasa apso",
      "score": 0.0298430435359478
    }
  ],
  "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 'microsoft/beit-base-patch16-224-pt22k-ft22k'  \
    -i image=@my_image.jpg
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "label": "Maltese dog, Maltese terrier, Maltese",
      "score": 0.9235488176345825
    },
    {
      "label": "Lhasa, Lhasa apso",
      "score": 0.0298430435359478
    }
  ],
  "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

microsoft/beit-base-patch16-224-pt22k-ft22k

HTTP/cURL API

Input fields

`image`string

`webhook`file

Input Schema

Output Schema