YOLOv7

Use YOLOv7 instance segmentation through our Serverless Hosted API

We support YOLOv7 instance segmentation inferencing via our Serverless Hosted API. Training YOLOv7 is not supported on Roboflow, but you can upload your own weights and run inference against them.

For self-hosted deployment, see Roboflow Inference.

YOLOv7 input size is set when you train your model outside Roboflow (typical values: 640x640 or 1280x1280).

Default COCO aliases

There are no pretrained YOLOv7 aliases. You must train YOLOv7 instance segmentation outside of Roboflow, upload the weights to a Project, then call your own model_id against the Serverless Hosted API.

Code sample

Install the Inference SDK and supervision for decoding and drawing masks:

pip install inference-sdk supervision opencv-python

Run inference against your own YOLOv7 instance segmentation model, then use supervision to render the predicted masks and labels onto the source image. Replace model_id with your Project's value, and pass your Roboflow API Key via the API_KEY environment variable.

import os
import urllib.request

import cv2
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/bicycle.png"
image_path = "bicycle.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
results = client.infer(image_path, model_id="your-project/1")

detections = sv.Detections.from_inference(results)

mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator()

labels = [
    f"{cls} {conf:.2f}"
    for cls, conf in zip(detections.data.get("class_name", []), detections.confidence)
]

annotated = mask_annotator.annotate(scene=image.copy(), detections=detections)
annotated = label_annotator.annotate(scene=annotated, detections=detections, labels=labels)

cv2.imwrite("annotated.png", annotated)

Set api_url to match your deployment target:

• https://serverless.roboflow.com for the Serverless Hosted API.

• http://localhost:9001 for a local Inference server.

• Your Dedicated Deployment URL for a private endpoint.