Saltar al contenido

Ultralytics API de inferencia HUB

La API de inferencia Ultralytics HUB te permite ejecutar la inferencia a trav茅s de nuestra API REST sin necesidad de instalar y configurar localmente el entorno Ultralytics YOLO .

Ultralytics Captura de pantalla HUB de la pesta帽a Despliegue dentro de la p谩gina Modelo con una flecha apuntando a la tarjeta API de inferencia Ultralytics


Observa: Ultralytics Paseo por la API de Inferencia HUB

Python

Para acceder a la API de inferencia Ultralytics HUB utilizando Python, utiliza el siguiente c贸digo:

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

Nota

Sustituye MODEL_ID con el ID del modelo deseado, API_KEY con tu clave API real, y path/to/image.jpg con la ruta a la imagen sobre la que quieres ejecutar la inferencia.

cURL

Para acceder a la API de inferencia Ultralytics HUB utilizando cURL, utiliza el siguiente c贸digo:

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

Nota

Sustituye MODEL_ID con el ID del modelo deseado, API_KEY con tu clave API real, y path/to/image.jpg con la ruta a la imagen sobre la que quieres ejecutar la inferencia.

Argumentos

Consulta la tabla siguiente para ver una lista completa de los argumentos de inferencia disponibles.

Argumento Por defecto Tipo Descripci贸n
image image Archivo de imagen que se utilizar谩 para la inferencia.
url str URL de la imagen si no pasa un archivo.
size 640 int Tama帽o de la imagen de entrada, el rango v谩lido es 32 - 1280 P铆xeles.
confidence 0.25 float Umbral de confianza para predicciones, rango v谩lido 0.01 - 1.0.
iou 0.45 float Intersecci贸n sobre el umbral de Uni贸n (IoU), rango v谩lido 0.0 - 0.95.

Respuesta

La API de inferencia Ultralytics HUB devuelve una respuesta JSON.

Clasificaci贸n

Modelo de clasificaci贸n

from ultralytics import YOLO

# Load model
model = YOLO("yolov8n-cls.pt")

# Run inference
results = model("image.jpg")

# Print image.jpg results in JSON format
print(results[0].tojson())

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

{
  success: true,
  message: "Inference complete.",
  data: [
    {
      class: 0,
      name: "person",
      confidence: 0.92
    }
  ]
}

Detecci贸n

Modelo de detecci贸n

from ultralytics import YOLO

# Load model
model = YOLO("yolov8n.pt")

# Run inference
results = model("image.jpg")

# Print image.jpg results in JSON format
print(results[0].tojson())

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

{
  success: true,
  message: "Inference complete.",
  data: [
    {
      class: 0,
      name: "person",
      confidence: 0.92,
      width: 0.4893378019332886,
      height: 0.7437513470649719,
      xcenter: 0.4434437155723572,
      ycenter: 0.5198975801467896
    }
  ]
}

OBB

Modelo OBB

from ultralytics import YOLO

# Load model
model = YOLO("yolov8n-obb.pt")

# Run inference
results = model("image.jpg")

# Print image.jpg results in JSON format
print(results[0].tojson())

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

{
  success: true,
  message: "Inference complete.",
  data: [
    {
      class: 0,
      name: "person",
      confidence: 0.92,
      obb: [
        0.669310450553894,
        0.6247171759605408,
        0.9847468137741089,
        ...
      ]
    }
  ]
}

Segmentaci贸n

Modelo de segmentaci贸n

from ultralytics import YOLO

# Load model
model = YOLO("yolov8n-seg.pt")

# Run inference
results = model("image.jpg")

# Print image.jpg results in JSON format
print(results[0].tojson())

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

{
  success: true,
  message: "Inference complete.",
  data: [
    {
      class: 0,
      name: "person",
      confidence: 0.92,
      segment: [0.44140625, 0.15625, 0.439453125, ...]
    }
  ]
}

Pose

Modelo de pose

from ultralytics import YOLO

# Load model
model = YOLO("yolov8n-pose.pt")

# Run inference
results = model("image.jpg")

# Print image.jpg results in JSON format
print(results[0].tojson())

curl -X POST "https://api.ultralytics.com/v1/predict/MODEL_ID" \
    -H "x-api-key: API_KEY" \
    -F "image=@/path/to/image.jpg" \
    -F "size=640" \
    -F "confidence=0.25" \
    -F "iou=0.45"

import requests

# API URL, use actual MODEL_ID
url = "https://api.ultralytics.com/v1/predict/MODEL_ID"

# Headers, use actual API_KEY
headers = {"x-api-key": "API_KEY"}

# Inference arguments (optional)
data = {"size": 640, "confidence": 0.25, "iou": 0.45}

# Load image and send request
with open("path/to/image.jpg", "rb") as image_file:
    files = {"image": image_file}
    response = requests.post(url, headers=headers, files=files, data=data)

print(response.json())

{
  success: true,
  message: "Inference complete.",
  data: [
    {
      class: 0,
      name: "person",
      confidence: 0.92,
      keypoints: [
        0.5290805697441101,
        0.20698919892311096,
        1.0,
        0.5263055562973022,
        0.19584226608276367,
        1.0,
        0.5094948410987854,
        0.19120082259178162,
        1.0,
        ...
      ]
    }
  ]
}


Creado 2024-01-23, Actualizado 2024-06-22
Autores: glenn-jocher (9), sergiuwaxmann (2), RizwanMunawar (1), priytosh-tripathi (1)

Comentarios