Xuất MNN cho các Mô hình YOLO11 và triển khai

from ultralytics import YOLO

# Load the YOLO11 model
model = YOLO("yolo11n.pt")

# Export the model to MNN format
model.export(format="mnn")  # creates 'yolo11n.mnn'

# Load the exported MNN model
mnn_model = YOLO("yolo11n.mnn")

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

# Export a YOLO11n PyTorch model to MNN format
yolo export model=yolo11n.pt format=mnn # creates 'yolo11n.mnn'

# Run inference with the exported model
yolo predict model='yolo11n.mnn' source='https://ultralytics.com/images/bus.jpg'

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 = np.expand_dims(image, 0)
    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 yolo11 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)

#include <stdio.h>
#include <MNN/ImageProcess.hpp>
#include <MNN/expr/Module.hpp>
#include <MNN/expr/Executor.hpp>
#include <MNN/expr/ExprCreator.hpp>
#include <MNN/expr/Executor.hpp>

#include <cv/cv.hpp>

using namespace MNN;
using namespace MNN::Express;
using namespace MNN::CV;

int main(int argc, const char* argv[]) {
    if (argc < 3) {
        MNN_PRINT("Usage: ./yolo11_demo.out model.mnn input.jpg [forwardType] [precision] [thread]\n");
        return 0;
    }
    int thread = 4;
    int precision = 0;
    int forwardType = MNN_FORWARD_CPU;
    if (argc >= 4) {
        forwardType = atoi(argv[3]);
    }
    if (argc >= 5) {
        precision = atoi(argv[4]);
    }
    if (argc >= 6) {
        thread = atoi(argv[5]);
    }
    MNN::ScheduleConfig sConfig;
    sConfig.type = static_cast<MNNForwardType>(forwardType);
    sConfig.numThread = thread;
    BackendConfig bConfig;
    bConfig.precision = static_cast<BackendConfig::PrecisionMode>(precision);
    sConfig.backendConfig = &bConfig;
    std::shared_ptr<Executor::RuntimeManager> rtmgr = std::shared_ptr<Executor::RuntimeManager>(Executor::RuntimeManager::createRuntimeManager(sConfig));
    if(rtmgr == nullptr) {
        MNN_ERROR("Empty RuntimeManger\n");
        return 0;
    }
    rtmgr->setCache(".cachefile");

    std::shared_ptr<Module> net(Module::load(std::vector<std::string>{}, std::vector<std::string>{}, argv[1], rtmgr));
    auto original_image = imread(argv[2]);
    auto dims = original_image->getInfo()->dim;
    int ih = dims[0];
    int iw = dims[1];
    int len = ih > iw ? ih : iw;
    float scale = len / 640.0;
    std::vector<int> padvals { 0, len - ih, 0, len - iw, 0, 0 };
    auto pads = _Const(static_cast<void*>(padvals.data()), {3, 2}, NCHW, halide_type_of<int>());
    auto image = _Pad(original_image, pads, CONSTANT);
    image = resize(image, Size(640, 640), 0, 0, INTER_LINEAR, -1, {0., 0., 0.}, {1./255., 1./255., 1./255.});
    image = cvtColor(image, COLOR_BGR2RGB);
    auto input = _Unsqueeze(image, {0});
    input = _Convert(input, NC4HW4);
    auto outputs = net->onForward({input});
    auto output = _Convert(outputs[0], NCHW);
    output = _Squeeze(output);
    // output shape: [84, 8400]; 84 means: [cx, cy, w, h, prob * 80]
    auto cx = _Gather(output, _Scalar<int>(0));
    auto cy = _Gather(output, _Scalar<int>(1));
    auto w = _Gather(output, _Scalar<int>(2));
    auto h = _Gather(output, _Scalar<int>(3));
    std::vector<int> startvals { 4, 0 };
    auto start = _Const(static_cast<void*>(startvals.data()), {2}, NCHW, halide_type_of<int>());
    std::vector<int> sizevals { -1, -1 };
    auto size = _Const(static_cast<void*>(sizevals.data()), {2}, NCHW, halide_type_of<int>());
    auto probs = _Slice(output, start, size);
    // [cx, cy, w, h] -> [y0, x0, y1, x1]
    auto x0 = cx - w * _Const(0.5);
    auto y0 = cy - h * _Const(0.5);
    auto x1 = cx + w * _Const(0.5);
    auto y1 = cy + h * _Const(0.5);
    auto boxes = _Stack({x0, y0, x1, y1}, 1);
    // ensure ratio is within the valid range [0.0, 1.0]
    boxes = _Maximum(boxes, _Scalar<float>(0.0f));
    boxes = _Minimum(boxes, _Scalar<float>(1.0f));
    auto scores = _ReduceMax(probs, {0});
    auto ids = _ArgMax(probs, 0);
    auto result_ids = _Nms(boxes, scores, 100, 0.45, 0.25);
    auto result_ptr = result_ids->readMap<int>();
    auto box_ptr = boxes->readMap<float>();
    auto ids_ptr = ids->readMap<int>();
    auto score_ptr = scores->readMap<float>();
    for (int i = 0; i < 100; i++) {
        auto idx = result_ptr[i];
        if (idx < 0) break;
        auto x0 = box_ptr[idx * 4 + 0] * scale;
        auto y0 = box_ptr[idx * 4 + 1] * scale;
        auto x1 = box_ptr[idx * 4 + 2] * scale;
        auto y1 = box_ptr[idx * 4 + 3] * scale;
        // clamp to the original image size to handle cases where padding was applied
        x1 = std::min(static_cast<float>(iw), x1);
        y1 = std::min(static_cast<float>(ih), y1);
        auto class_idx = ids_ptr[idx];
        auto score = score_ptr[idx];
        rectangle(original_image, {x0, y0}, {x1, y1}, {0, 0, 255}, 2);
    }
    if (imwrite("res.jpg", original_image)) {
        MNN_PRINT("result image write to `res.jpg`.\n");
    }
    rtmgr->updateCache();
    return 0;
}

from ultralytics import YOLO

# Load the YOLO11 model
model = YOLO("yolo11n.pt")

# Export to MNN format
model.export(format="mnn")  # creates 'yolo11n.mnn' with fp32 weight
model.export(format="mnn", half=True)  # creates 'yolo11n.mnn' with fp16 weight
model.export(format="mnn", int8=True)  # creates 'yolo11n.mnn' with int8 weight

yolo export model=yolo11n.pt format=mnn           # creates 'yolo11n.mnn' with fp32 weight
yolo export model=yolo11n.pt format=mnn half=True # creates 'yolo11n.mnn' with fp16 weight
yolo export model=yolo11n.pt format=mnn int8=True # creates 'yolo11n.mnn' with int8 weight

from ultralytics import YOLO

# Load the YOLO11 MNN model
model = YOLO("yolo11n.mnn")

# Export to MNN format
results = model("https://ultralytics.com/images/bus.jpg")  # predict with `fp32`
results = model("https://ultralytics.com/images/bus.jpg", half=True)  # predict with `fp16` if device support

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

yolo predict model='yolo11n.mnn' source='https://ultralytics.com/images/bus.jpg'             # predict with `fp32`
yolo predict model='yolo11n.mnn' source='https://ultralytics.com/images/bus.jpg' --half=True # predict with `fp16` if device support