# Deploy zero shot image classification on sagemaker

**URL:** <https://discuss.huggingface.co/t/deploy-zero-shot-image-classification-on-sagemaker/24931>\
**Category:** Models\
**Created:** [October 25, 2022, 8:39am UTC](https://discuss.huggingface.co/t/deploy-zero-shot-image-classification-on-sagemaker/24931 "2022-10-25T08:39:24Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ABDOU9419](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/abdou9419/32/12225_2.png) [@ABDOU9419](https://discuss.huggingface.co/u/ABDOU9419)\
**Post date:** [October 25, 2022, 8:39am UTC](https://discuss.huggingface.co/t/deploy-zero-shot-image-classification-on-sagemaker/24931/1 "2022-10-25T08:39:24Z")

</div>

I deployed a zero shot model on sagemaker and im trying to test it by sending this request

```auto
predictor.predict({
  "inputs": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png",
    "parameters": {
    "candidate_labels": ['playing music', 'playing sports']
  }
}
)

```

but the following error is shown :

```auto
An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from model with message "{
  "code": 400,
  "type": "InternalServerException",
  "message": "You have to specify pixel_values"
}

```

can you help me guys.