How to Use the v3 Detection API

Use this pre-trained v3 computer vision model to retrieve predictions with our hosted API or deploy to the edge. Learn More About Roboflow Inference

Switch Model:
v17
v3-kgfed/17
v17
v3-kgfed/17
Trained On: 2024-04-02-2-50am
v16
v3-kgfed/16
Trained On: 2024-04-01-4-32pm
v15
v3-kgfed/15
Trained On: 2024-04-01-4-20pm
v13
v3-kgfed/13
Trained On: 2024-03-30-5-25pm
v11
v3-kgfed/11
Trained On: 2024-03-30-9-45am
v10
v3-kgfed/10
Trained On: 2024-03-30-4-05am
v9
v3-kgfed/9
Trained On: 2024-03-30-3-21am
v6
v3-kgfed/6
Trained On: 2024-03-27-4-32am
v4
v3-kgfed/4
Trained On: 2024-03-27-4-14am
v3
v3-kgfed/3
Trained On: 2024-03-26-12-38pm
v1
v3-kgfed/1
Trained On: 2024-03-26-12-31pm
Trained On: v3-kgfed 52861 Images
View Version
Model Type: Roboflow 3.0 Instance Segmentation (Fast)
Checkpoint: v3-kgfed/16
mAP
10.4%
View Model Graphs

Samples from Test Set

Upload Image

Drop file here or

Paste Image URL

Try On My Machine

Try this model on images

0
fps
0
objects detected
Label Display Mode:
Copy
Copied
Roboflow Inference

Inference is Roboflow's open source deployment package for developer-friendly vision inference.

How to Deploy the v3 Detection API

Using Roboflow, you can deploy your object detection model to a range of environments, including:

  • Raspberry Pi
  • NVIDIA Jetson
  • A Docker container
  • A web page
  • A Python script using the Roboflow SDK.

Below, we have instructions on how to use our deployment options.

Code Snippets

Hosted API
Utilities
Python
JavaScript
## Infer on Local and Hosted Images To install dependencies, `pip install inference-sdk`. Then, add the following code snippet to a Python script: ```python from inference_sdk import InferenceHTTPClient CLIENT = InferenceHTTPClient( api_url="https://outline.roboflow.com", api_key="API_KEY" ) result = CLIENT.infer(your_image.jpg, model_id="MODEL_ENDPOINT/VERSION") ``` [See the inference-sdk docs](https://inference.roboflow.com/inference_helpers/inference_sdk/)
## Node.js We're using [axios](https://github.com/axios/axios) to perform the POST request in this example so first run npm install axios to install the dependency. ### Inferring on a Local Image ```javascript const axios = require("axios"); const fs = require("fs"); const image = fs.readFileSync("YOUR_IMAGE.jpg", { encoding: "base64" }); axios({ method: "POST", url: "https://outline.roboflow.com/MODEL_ENDPOINT/VERSION", params: { api_key: "API_KEY" }, data: image, headers: { "Content-Type": "application/x-www-form-urlencoded" } }) .then(function (response) { console.log(response.data); }) .catch(function (error) { console.log(error.message); }); ``` ### Inferring on an Image Hosted Elsewhere via URL ```javascript const axios = require("axios"); axios({ method: "POST", url: "https://outline.roboflow.com/MODEL_ENDPOINT/VERSION", params: { api_key: "API_KEY", image: "IMAGE_URL" } }) .then(function (response) { console.log(response.data); }) .catch(function (error) { console.log(error.message); }); ```
More Deployment Resources
Roboflow Documentation

Look through our full documentation for more information and resources on how to utilize this model.
Example Web App

Use this model with a full fledged web application that has all sample code included.
Deploy to NVIDIA Jetson

Perform inference at the edge with a Jetson via our Docker container.
Deploy Mobile iOS

Utilize your model on your mobile device.

Similar Projects

See More