SpotLab/MobileViT_DeepLabv3 ↗
- source model id
- HuggingFace/spotlab-mobilevit-deeplabv3@1
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- other
- architecture
- input_modalities
- output_modalities
- capabilities
`SpotLab/MobileViT_DeepLabv3` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/SpotLab/MobileViT_DeepLabv3) - [`image-segmentation` Task on Hugging Face](https…
azureFoundry/HuggingFace/spotlab-mobilevit-deeplabv3@1
`SpotLab/MobileViT_DeepLabv3` powered by Hugging Face Inference Toolkit
- [Original Model Card](https://huggingface.co/SpotLab/MobileViT_DeepLabv3) - [`image-segmentation` Task on Hugging Face](https://huggingface.co/tasks/image-segmentation)
### Send Request
You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.
```bash curl <AZUREML_ENDPOINT_URL> \ -X POST \ -H "Authorization: Bearer <AZUREML_TOKEN>" \ -H "Content-Type: image/jpeg" \ --data-binary @"image.jpg" ```
### Supported Parameters
- **inputs** (string): The input image data as a base64-encoded string. If no parameters are provided, you can also provide the image data as a raw bytes payload. - **parameters** (object): - **mask_threshold** (float): Threshold to use when turning the predicted masks into binary values. - **overlap_mask_area_threshold** (float): Mask overlap threshold to eliminate small, disconnected segments. - **subtask** (enum): Possible values: instance, panoptic, semantic. - **threshold** (float): Probability threshold to filter out predicted masks.
Check the full API Specification at [the Hugging Face Inference documentation](https://huggingface.co/docs/inference-providers/tasks/image-segmentation#api-specification).
1–1 / 1
1–4 / 4
Hugging Face · SpotLab/MobileViT_DeepLabv3 ↗
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.