Vai al contenuto

Ultralytics API di inferenza HUB

L'API di inferenza di Ultralytics HUB ti permette di eseguire l'inferenza attraverso la nostra API REST senza la necessità di installare e configurare l'ambiente Ultralytics YOLO localmente.

Ultralytics Schermata HUB della scheda Deploy all'interno della pagina Model con una freccia che punta alla scheda Ultralytics Inference API


Guarda: Ultralytics Passaggio all'API di inferenza HUB

Python

Per accedere all'API di inferenza di Ultralytics HUB utilizzando Python, usa il seguente codice:

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

Sostituisci MODEL_ID con l'ID del modello desiderato, API_KEY con la tua chiave API attuale e path/to/image.jpg con il percorso dell'immagine su cui vuoi eseguire l'inferenza.

cURL

Per accedere all'API di inferenza di Ultralytics HUB utilizzando cURL, usa il seguente codice:

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

Sostituisci MODEL_ID con l'ID del modello desiderato, API_KEY con la tua chiave API attuale e path/to/image.jpg con il percorso dell'immagine su cui vuoi eseguire l'inferenza.

Argomenti

Vedi la tabella sottostante per un elenco completo degli argomenti di inferenza disponibili.

Argomento Predefinito Tipo Descrizione
image image File di immagine da utilizzare per l'inferenza.
url str URL dell'immagine se non si passa un file.
size 640 int Dimensione dell'immagine di input, l'intervallo valido è 32 - 1280 Pixel.
confidence 0.25 float Soglia di confidenza per le stime, intervallo valido 0.01 - 1.0.
iou 0.45 float Intersezione oltre la soglia dell'Unione (IoU), intervallo valido 0.0 - 0.95.

Risposta

L'API di inferenza di Ultralytics HUB restituisce una risposta JSON.

Classificazione

Modello di classificazione

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
    }
  ]
}

Rilevamento

Modello di rilevamento

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

Modello 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,
        ...
      ]
    }
  ]
}

Segmentazione

Modello di segmentazione

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

Modello di posa

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,
        ...
      ]
    }
  ]
}


Creato 2024-01-23, Aggiornato 2024-06-22
Autori: glenn-jocher (9), sergiuwaxmann (2), RizwanMunawar (1), priytosh-tripathi (1)

Commenti