虛擬環(huán)境搭建

首先在PC的ubuntu系統(tǒng)安裝虛擬環(huán)境：
我的服務(wù)器是ubuntu18.04版本，所以安裝python3.6
conda create -n ok3588 python=3.6
需要鍵盤輸入y，然后完成虛擬環(huán)境安裝。
其他系統(tǒng)的對(duì)應(yīng)關(guān)系：
Ubuntu 18.04 python 3.6 / Ubuntu 20.04 python 3.8 / Ubuntu 22.04 python 3.10

軟件包安裝

進(jìn)入虛擬環(huán)境
conda activate ok3588
首先安裝正確的pip版本
curl https://bootstrap.pypa.io/pip/3.6/get-pip.py | python -
下載github 項(xiàng)目
git clone https://github.com/rockchip-linux/rknn-toolkit2
cd rknn-toolkit2/doc
pip install -r requirements_cp36-1.5.0.txt -i https://mirror.baidu.com/pypi/simple
cd rknn-toolkit2/packages
pip install rknn_toolkit2-1.5.0+1fa95b5c-cp36-cp36m-linux_x86_64.whl

在PC機(jī)上運(yùn)行yolov5目標(biāo)檢測(cè)

cd rknn-toolkit2/examples/onnx/yolov5
python test.py
截圖如下

推理前的圖片：

推理后加上box的圖片：

推理代碼和注釋：文章來源地址http://www.zghlxwxcb.cn/news/detail-601441.html

if __name__ == '__main__':

    # Create RKNN object
    rknn = RKNN(verbose=True)

    # pre-process config  配置數(shù)據(jù)參數(shù)
    print('--> Config model')
    rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]])
    print('done')

    # Load ONNX model 導(dǎo)入模型
    print('--> Loading model')
    ret = rknn.load_onnx(model=ONNX_MODEL)
    if ret != 0:
        print('Load model failed!')
        exit(ret)
    print('done')

    # Build model 創(chuàng)建模型
    print('--> Building model')
    ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET)
    if ret != 0:
        print('Build model failed!')
        exit(ret)
    print('done')

    # Export RKNN model 導(dǎo)出RKNN模型
    print('--> Export rknn model')
    ret = rknn.export_rknn(RKNN_MODEL)
    if ret != 0:
        print('Export rknn model failed!')
        exit(ret)
    print('done')

    # Init runtime environment 初始化runtime環(huán)境
    print('--> Init runtime environment')
    ret = rknn.init_runtime()
    # ret = rknn.init_runtime('rk3588')
    if ret != 0:
        print('Init runtime environment failed!')
        exit(ret)
    print('done')

    # Set inputs
    img = cv2.imread(IMG_PATH)
    # img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))

    # Inference 模型推理
    print('--> Running model')
    outputs = rknn.inference(inputs=[img])
    np.save('./onnx_yolov5_0.npy', outputs[0])
    np.save('./onnx_yolov5_1.npy', outputs[1])
    np.save('./onnx_yolov5_2.npy', outputs[2])
    print('done')

    # post process
    input0_data = outputs[0]
    input1_data = outputs[1]
    input2_data = outputs[2]

    input0_data = input0_data.reshape([3, -1]+list(input0_data.shape[-2:]))
    input1_data = input1_data.reshape([3, -1]+list(input1_data.shape[-2:]))
    input2_data = input2_data.reshape([3, -1]+list(input2_data.shape[-2:]))

    input_data = list()
    input_data.append(np.transpose(input0_data, (2, 3, 0, 1)))
    input_data.append(np.transpose(input1_data, (2, 3, 0, 1)))
    input_data.append(np.transpose(input2_data, (2, 3, 0, 1)))

    boxes, classes, scores = yolov5_post_process(input_data)#識(shí)別結(jié)果后處理

    img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
    if boxes is not None:
        draw(img_1, boxes, scores, classes)
        cv2.imwrite('result.jpg', img_1)

    rknn.release()

到了這里，關(guān)于使用rknn-toolkit2把YOLOV5部署到OK3588上的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！