YOLO-World

YOLO-World एक ज़ीरो-शॉट ऑब्जेक्ट डिटेक्शन मॉडल है जो आपको किसी भी प्रशिक्षण के बिना, केवल उन आइटमों का वर्णन करके ऑब्जेक्ट डिटेक्शन करने की अनुमति देता है जिन्हें आप डिटेक्ट करना चाहते हैं।

आप लोकली YOLO-World को चलाने के लिए भी चला सकते हैं Inference, हमारा open-source inference server।

inferencejs के साथ एज inference

हमारे होस्टेड API का बेस URL है https://infer.roboflow.com.

YOLO-World को Inference के साथ, Python SDK या self-hosted API के माध्यम से उपयोग करने पर अधिक जानकारी के लिए देखें YOLO-World Inference docs पृष्ठ.

YOLO-World inference.

post

Run the YOLO-World zero-shot object detection model.

Query parameters

api_keyany ofOptional

Roboflow API Key that will be passed to the model during initialization for artifact retrieval

stringOptional

or

nullOptional

countinferenceany ofOptional

booleanOptional

or

nullOptional

service_secretany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request for Grounding DINO zero-shot predictions.

Attributes: text (List[str]): A list of strings.

idstringRequired

api_keyany ofOptional

Roboflow API Key that will be passed to the model during initialization for artifact retrieval

stringOptional

or

nullOptional

usage_billablebooleanOptionalDefault: true

startany ofOptional

numberOptional

or

nullOptional

sourceany ofOptional

stringOptional

or

nullOptional

source_infoany ofOptional

stringOptional

or

nullOptional

disable_model_monitoringany ofOptional

If true, disables model monitoring for this request

Default: false

booleanOptional

or

nullOptional

model_idany ofOptional

stringOptional

or

nullOptional

model_typeany ofOptional

The type of the model, usually referring to what task the model performs

Example: object-detection

stringOptional

or

nullOptional

imageany ofRequired

or

disable_preproc_auto_orientany ofOptional

If true, the auto orient preprocessing step is disabled for this call.

Default: false

booleanOptional

or

nullOptional

disable_preproc_contrastany ofOptional

If true, the auto contrast preprocessing step is disabled for this call.

Default: false

booleanOptional

or

nullOptional

disable_preproc_grayscaleany ofOptional

If true, the grayscale preprocessing step is disabled for this call.

Default: false

booleanOptional

or

nullOptional

disable_preproc_static_cropany ofOptional

If true, the static crop preprocessing step is disabled for this call.

Default: false

booleanOptional

or

nullOptional

textstring[]Required

A list of strings

Example: ["person","dog","cat"]

yolo_world_version_idany ofOptionalDefault: l

stringOptional

or

nullOptional

confidenceany ofOptionalDefault: 0.4

numberOptional

or

nullOptional

Responses

200

Successful Response

application/json

Object Detection inference response.

Attributes: predictions (List[inference.core.entities.responses.inference.ObjectDetectionPrediction]): List of object detection predictions.

visualizationany ofOptional

Base64 encoded string containing prediction visualization image data

stringOptional

or

nullOptional

inference_idany ofOptional

Unique identifier of inference

stringOptional

or

nullOptional

frame_idany ofOptional

The frame id of the image used in inference if the input was a video

integerOptional

or

nullOptional

timeany ofOptional

The time in seconds it took to produce the predictions including image preprocessing

numberOptional

or

nullOptional

imageany ofRequired

or

422

Validation Error

application/json

post

/yolo_world/infer

HTTPcURLJavaScriptPython

POST /yolo_world/infer HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 464

{
  "id": "text",
  "api_key": "text",
  "usage_billable": true,
  "start": 1,
  "source": "text",
  "source_info": "text",
  "disable_model_monitoring": false,
  "model_id": "text",
  "model_type": "object-detection",
  "image": [
    {
      "type": "url",
      "value": "http://www.example-image-url.com"
    }
  ],
  "disable_preproc_auto_orient": false,
  "disable_preproc_contrast": false,
  "disable_preproc_grayscale": false,
  "disable_preproc_static_crop": false,
  "text": [
    "person",
    "dog",
    "cat"
  ],
  "yolo_world_version_id": "l",
  "confidence": 0.4
}

{
  "visualization": "text",
  "inference_id": "text",
  "frame_id": 1,
  "time": 1,
  "image": [
    {
      "width": 1,
      "height": 1
    }
  ],
  "predictions": [
    {
      "x": 1,
      "y": 1,
      "width": 1,
      "height": 1,
      "confidence": 1,
      "class": "text",
      "class_confidence": 1,
      "class_id": 1,
      "tracker_id": 1,
      "detection_id": "text",
      "parent_id": "text"
    }
  ]
}