facebook-sam-vit-base · azureml v1

The Segment Anything Model (SAM) is an innovative image segmentation tool capable of creating high-quality object masks from simple input prompts. Trained on a massive dataset comprising 11 million i…

azureFoundry/azureml/facebook-sam-vit-base@1

The Segment Anything Model (SAM) is an innovative image segmentation tool capable of creating high-quality object masks from simple input prompts. Trained on a massive dataset comprising 11 million images and 1.1 billion masks, SAM demonstrates strong zero-shot capabilities, effectively adapting to new image segmentation tasks without prior specific training. The model's impressive performance matches or exceeds prior models that operated under full supervision.

The above summary was generated using ChatGPT. Review the original-model-card to understand the data used to train the model, evaluation metrics, license, intended uses, limitations and bias before using the model.

Inference samples

Inference typePython sample (Notebook)CLI with YAML
Real timemask-generation-online-endpoint.ipynb<a href="https://aka.ms/

Specifications & capabilities

Provider specifications & access

1–1 / 1

facebook-sam-vit-base · azureml v1 ↗

source model id
azureml/facebook-sam-vit-base@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
    output_modalities
      capabilities

        Original sources

        1–3 / 3

        Microsoft Foundry · Model page ↗

        Microsoft Foundry · Model documentation ↗

        Microsoft Foundry · Catalog ↗

        Source links

        1–1 / 1

        Explore more models

        Models

        Loading
        EVIDENCE / COMPARISON

        Benchmarks

        Explore every benchmark

        Loading

        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.

        Install TensorTrace