Vision

On this page, we’ll dive into the different vision tasks you can use.

These tasks are all powered by the huggingface's transformers.js library. You can use any of the pre-trained ONNX models from the huggingface models or use your own.

Headers

  • Name
    x-api-group(optional)
    Type
    string, default 'main'
    Description

    The id of the peer-ai compute group you want to run this compute on.

  • Name
    x-api-key
    Type
    string
    Description

    The API key for your PeerAI account.

Image Classification

Image classification is the process of categorizing an image into different classes or categories. It involves training a model on a dataset of labeled images and then using that model to predict the class of new images.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'image-classification', 'object-detection'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    inputs.0
    Type
    string
    Description

    The URL or file path of the image to classify.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"image-classification\", \"model\": \"Xenova/vit-base-patch16-224\", \"inputs\": [\"https://files.worldwildlife.org/wwfcmsprod/images/Tiger_resting_Bandhavgarh_National_Park_India/hero_small/6aofsvaglm_Medium_WW226365.jpg\"]}"

Response

[
  {
    "label": "tiger, Panthera tigris",
    "score": 0.905
  }
]

Image Segmentation

Image segmentation is the process of dividing an image into multiple segments or regions to simplify the representation of an image into meaningful parts. It is commonly used in computer vision tasks such as object detection and image understanding.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'image-segmentation', 'object-detection'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    inputs.0
    Type
    string
    Description

    The URL of the image to perform segmentation on.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"image-segmentation\", \"inputs\": [\"https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg\"]}"

Response

[
  {
    "score": 0.965,
    "label": "LABEL_198",
    "mask": {
      "data": {
        "0": 255,
        "1": 255,
        "2": 255,
        ...
      },
      "width": 612,
      "height": 408,
      "channels": 1
    }
  }
]

Object Detection

Object detection is the task of identifying and localizing objects in an image or video. It involves drawing bounding boxes around objects and assigning labels to them.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'sentiment-analysis', 'text-classification'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    inputs.0
    Type
    string
    Description

    The image URL or file path to perform object detection on.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"object-detection\", \"inputs\": [\"https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg\"]}"

Response

[
  {
    "score": 0.999,
    "label": "sports ball",
    "box": {
      "xmin": 95,
      "ymin": 446,
      "xmax": 181,
      "ymax": 514
    }
  },
  {
    "score": 0.999,
    "label": "person",
    "box": {
      "xmin": -12,
      "ymin": 45,
      "xmax": 170,
      "ymax": 376
    }
  },
  {
    "score": 0.968,
    "label": "person",
    "box": {
      "xmin": 97,
      "ymin": 11,
      "xmax": 561,
      "ymax": 523
    }
  },
  {
    "score": 0.934,
    "label": "person",
    "box": {
      "xmin": 532,
      "ymin": 28,
      "xmax": 648,
      "ymax": 325
    }
  },
  {
    "score": 0.999,
    "label": "person",
    "box": {
      "xmin": 422,
      "ymin": 69,
      "xmax": 639,
      "ymax": 493
    }
  }
]

Depth Estimation

Depth estimation is the task of estimating the depth of an image or video. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Pose Estimation

Pose estimation is the task of estimating the pose of a person or object in an image or video. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Video Classification

Video classification is the task of classifying a video into one of several categories. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Face Detection

Face detection is the task of detecting faces in an image or video. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Face Recognition

Face recognition is the task of recognizing faces in an image or video. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Face Keypoint Detection

Face keypoint detection is the task of detecting facial keypoints in an image or video. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Image Similarity

Image similarity is the task of finding similar images in a dataset. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon

Image search is the task of finding similar images in a dataset. It is commonly used in computer vision tasks such as object detection and image understanding.

Coming Soon