YOLO Vision 2026:

MNN Export for YOLO26 Models and Deployment#

MNN#

MNN mobile neural network inference framework

MNN is a highly efficient and lightweight deep learning framework. It supports inference and training of deep learning models and has industry-leading performance for inference and training on-device. At present, MNN has been integrated into more than 30 apps of Alibaba Inc, such as Taobao, Tmall, Youku, DingTalk, Xianyu, etc., covering more than 70 usage scenarios such as live broadcast, short video capture, search recommendation, product searching by image, interactive marketing, equity distribution, security risk control. In addition, MNN is also used on embedded devices, such as IoT.



Watch: How to Export Ultralytics YOLO26 to MNN Format | Speed up Inference on Mobile Devices📱

Supported Tasks#

MNN export supports all seven Ultralytics tasks. Semantic segmentation and depth estimation are available only with YOLO26, the only family that ships those heads.

TaskYOLOv8YOLO11YOLO26
Detect✅✅✅
Segment✅✅✅
Semantic❌❌✅
Depth❌❌✅
Classify✅✅✅
Pose✅✅✅
OBB✅✅✅

Export to MNN: Converting Your YOLO26 Model#

You can expand model compatibility and deployment flexibility by converting Ultralytics YOLO models to MNN format. This conversion optimizes your models for mobile and embedded environments, ensuring efficient performance on resource-constrained devices.

Installation#

To install the required packages, run:

Installation
# Install the required package for YOLO26 and MNN
pip install ultralytics
pip install MNN

Usage#

All Ultralytics YOLO26 models are designed to support export out of the box, making it easy to integrate them into your preferred deployment workflow. You can view the full list of supported export formats and configuration options to choose the best setup for your application.

The MNN format supports the Export, Predict, and Validate modes. Export your model, then load the exported model to run inference or validate its accuracy.

Export
from ultralytics import YOLO

# Load a YOLO26 model
model = YOLO("yolo26n.pt")

# Export the model to MNN format
model.export(format="mnn")  # creates 'yolo26n.mnn'
Predict
from ultralytics import YOLO

# Load the exported MNN model
model = YOLO("yolo26n.mnn")

# Run inference
results = model("https://ultralytics.com/images/bus.jpg")
Validate
from ultralytics import YOLO

# Load the exported MNN model
model = YOLO("yolo26n.mnn")

# Validate accuracy on the COCO8 dataset
metrics = model.val(data="coco8.yaml")

Export Arguments#

ArgumentTypeDefaultDescription
formatstr'mnn'Target format for the exported model, defining compatibility with various deployment environments.
imgszint or tuple640Desired image size for the model input. Can be an integer for square images or a tuple (height, width) for specific dimensions.
quantizeint or strNoneQuantization precision: 16 (FP16), 8 (INT8 weight quantization), or 32/unset (FP32). Replaces the deprecated half/int8 flags.
simplifyboolTrueSimplifies the intermediate ONNX graph with onnxslim.
opsetintNoneSpecifies the ONNX opset version for the intermediate ONNX graph. If not set, uses the latest supported version.
batchint1Specifies export model batch inference size or the max number of images the exported model will process concurrently in predict mode.
dynamicboolFalseEnables dynamic input image dimensions. Cannot be combined with nms=True.
nmsboolFalseAdds NMS for detect and pose models. Cannot be combined with dynamic=True.
devicestrNoneSpecifies the device for exporting: GPU (device=0), CPU (device=cpu), MPS for Apple silicon (device=mps).

For more details about the export process, visit the Ultralytics documentation page on exporting.

MNN-Only Inference#

A function that relies solely on MNN for YOLO26 inference and preprocessing is implemented, providing both Python and C++ versions for easy deployment in any scenario.

MNN
import argparse

import MNN
import MNN.cv as cv2
import MNN.numpy as np

def inference(model, img, precision, backend, thread):
    config = {}
    config["precision"] = precision
    config["backend"] = backend
    config["numThread"] = thread
    rt = MNN.nn.create_runtime_manager((config,))
    # net = MNN.nn.load_module_from_file(model, ['images'], ['output0'], runtime_manager=rt)
    net = MNN.nn.load_module_from_file(model, [], [], runtime_manager=rt)
    original_image = cv2.imread(img)
    ih, iw, _ = original_image.shape
    length = max((ih, iw))
    scale = length / 640
    image = np.pad(original_image, [[0, length - ih], [0, length - iw], [0, 0]], "constant")
    image = cv2.resize(
        image, (640, 640), 0.0, 0.0, cv2.INTER_LINEAR, -1, [0.0, 0.0, 0.0], [1.0 / 255.0, 1.0 / 255.0, 1.0 / 255.0]
    )
    image = image[..., ::-1]  # BGR to RGB
    input_var = image[None]
    input_var = MNN.expr.convert(input_var, MNN.expr.NC4HW4)
    output_var = net.forward(input_var)
    output_var = MNN.expr.convert(output_var, MNN.expr.NCHW)
    output_var = output_var.squeeze()
    # output_var shape: [84, 8400]; 84 means: [cx, cy, w, h, prob * 80]
    cx = output_var[0]
    cy = output_var[1]
    w = output_var[2]
    h = output_var[3]
    probs = output_var[4:]
    # [cx, cy, w, h] -> [y0, x0, y1, x1]
    x0 = cx - w * 0.5
    y0 = cy - h * 0.5
    x1 = cx + w * 0.5
    y1 = cy + h * 0.5
    boxes = np.stack([x0, y0, x1, y1], axis=1)
    # ensure ratio is within the valid range [0.0, 1.0]
    boxes = np.clip(boxes, 0, 1)
    # get max prob and idx
    scores = np.max(probs, 0)
    class_ids = np.argmax(probs, 0)
    result_ids = MNN.expr.nms(boxes, scores, 100, 0.45, 0.25)
    print(result_ids.shape)
    # nms result box, score, ids
    result_boxes = boxes[result_ids]
    result_scores = scores[result_ids]
    result_class_ids = class_ids[result_ids]
    for i in range(len(result_boxes)):
        x0, y0, x1, y1 = result_boxes[i].read_as_tuple()
        y0 = int(y0 * scale)
        y1 = int(y1 * scale)
        x0 = int(x0 * scale)
        x1 = int(x1 * scale)
        # clamp to the original image size to handle cases where padding was applied
        x1 = min(iw, x1)
        y1 = min(ih, y1)
        print(result_class_ids[i])
        cv2.rectangle(original_image, (x0, y0), (x1, y1), (0, 0, 255), 2)
    cv2.imwrite("res.jpg", original_image)

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--model", type=str, required=True, help="the yolo26 model path")
    parser.add_argument("--img", type=str, required=True, help="the input image path")
    parser.add_argument("--precision", type=str, default="normal", help="inference precision: normal, low, high, lowBF")
    parser.add_argument(
        "--backend",
        type=str,
        default="CPU",
        help="inference backend: CPU, OPENCL, OPENGL, NN, VULKAN, METAL, TRT, CUDA, HIAI",
    )
    parser.add_argument("--thread", type=int, default=4, help="inference using thread: int")
    args = parser.parse_args()
    inference(args.model, args.img, args.precision, args.backend, args.thread)

Summary#

In this guide, we introduce how to export the Ultralytics YOLO26 model to MNN and use MNN for inference. The MNN format provides excellent performance for edge AI applications, making it ideal for deploying computer vision models on resource-constrained devices.

For more usage, please refer to the MNN documentation.

FAQ#

  • To export your Ultralytics YOLO26 model to MNN format, follow these steps:

    Export
    from ultralytics import YOLO

# Load a YOLO26 model
model = YOLO("yolo26n.pt")

# Export to MNN format
model.export(format="mnn")  # creates 'yolo26n.mnn' with fp32 weight
model.export(format="mnn", quantize=16)  # creates 'yolo26n.mnn' with fp16 weight
model.export(format="mnn", quantize=8)  # creates 'yolo26n.mnn' with int8 weight

    For detailed export options, check the Export page in the documentation.

  • To predict with an exported YOLO26 MNN model, use the predict function from the YOLO class.

    Predict
    from ultralytics import YOLO

# Load the YOLO26 MNN model
model = YOLO("yolo26n.mnn")

# Run inference
results = model("https://ultralytics.com/images/bus.jpg")  # predict with `fp32`
results = model("https://ultralytics.com/images/bus.jpg", quantize=16)  # predict with `fp16` if device support

for result in results:
    result.show()  # display to screen
    result.save(filename="result.jpg")  # save to disk

  • MNN is versatile and supports various platforms:

    • Mobile: Android, iOS, Harmony.
    • Embedded Systems and IoT Devices: Devices like Raspberry Pi and NVIDIA Jetson.
    • Desktop and Servers: Linux, Windows, and macOS.

  • To deploy your YOLO26 models on Mobile devices:

    1. Build for Android: Follow the MNN Android guide.
    2. Build for iOS: Follow the MNN iOS guide.
    3. Build for Harmony: Follow the MNN Harmony guide.
Contributors
GLglenn-jocher13LAlakshanthad3JUjules-ai2AMamanharshx1Y-Y-T-G1ONonuralpszr1LALaughing-q1RIRizwanMunawar1WAwangzhaode1

Comments