Xuất MNN cho các model YOLO26 và triển khai#

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'

from ultralytics import YOLO

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

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

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")

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)