基于Ascend910+PyTorch1.11.0+CANN6.3.RC2的YoloV5训练推理一体化解决方案

昇腾Pytorch镜像:https://ascendhub.huawei.com/#/detail/ascend-pytorch

代码仓:git clone https://gitee.com/ascend/modelzoo-GPL.git

coco测试验证集:wget https://bj-aicc.obs.cn-north-309.mtgascendic.cn/dataset/coco2017/coco.zip

coco训练集(放images下):wget https://bj-aicc.obs.cn-north-309.mtgascendic.cn/dataset/coco2017/train2017.zip

部分代码

python 复制代码
# import StreamManagerApi.py
from StreamManagerApi import *

if __name__ == '__main__':
    # init stream manager
    streamManagerApi = StreamManagerApi()
    ret = streamManagerApi.InitManager()
    if ret != 0:
        print("Failed to init Stream manager, ret=%s" % str(ret))
        exit()

    # create streams by pipeline config file
    with open("data/pipeline/Sample.pipeline", 'rb') as f:
        pipelineStr = f.read()
    ret = streamManagerApi.CreateMultipleStreams(pipelineStr)
    if ret != 0:
        print("Failed to create Stream, ret=%s" % str(ret))
        exit()

    # Construct the input of the stream
    dataInput = MxDataInput()
    with open("data/test.jpg", 'rb') as f:
        dataInput.data = f.read()

    # The following is how to set the dataInput.roiBoxs
    """
    roiVector = RoiBoxVector()
    roi = RoiBox()
    roi.x0 = 100
    roi.y0 = 100
    roi.x1 = 200
    roi.y1 = 200
    roiVector.push_back(roi)
    dataInput.roiBoxs = roiVector
    """

    # Inputs data to a specified stream based on streamName.
    streamName = b'classification'
    inPluginId = 0
    uniqueId = streamManagerApi.SendDataWithUniqueId(streamName, inPluginId, dataInput)
    if uniqueId < 0:
        print("Failed to send data to stream.")
        exit()

    # Obtain the inference result by specifying streamName and uniqueId.
    inferResult = streamManagerApi.GetResultWithUniqueId(streamName, uniqueId, 3000)
    if inferResult.errorCode != 0:
        print("GetResultWithUniqueId error. errorCode=%d, errorMsg=%s" % (
            inferResult.errorCode, inferResult.data.decode()))
        exit()

    # print the infer result
    print(inferResult.data.decode())

    # destroy streams
    streamManagerApi.DestroyAllStreams()

本来想一次性写完的,奈何装CANN的驱动装了一个礼拜,各种内核版本不匹配,国产AI硬件任重道远...

相关推荐
jay神1 天前
基于 YOLOv8 的传送带异物检测系统(Web 版)
前端·人工智能·深度学习·yolo·计算机视觉·计算机毕业设计
jay神4 天前
基于 YOLOv8 的手势识别系统(Web 版)
前端·人工智能·python·深度学习·yolo·计算机视觉·计算机毕业设计
鱼听禅4 天前
Ubuntu安装YOLOv8进行菌落识别训练
linux·python·yolo·ubuntu
jay神6 天前
基于深度学习的交通流量预测系统(Web 版)
前端·人工智能·深度学习·yolo·计算机毕业设计
带电的小王6 天前
YOLO27:官方预览页放出全部规格,60.5 mAP 破 YOLO 纪录,但权重还没发布
yolo
jay神7 天前
基于 YOLOv8 的轴承缺陷检测(Web 版)
前端·人工智能·yolo
jay神7 天前
基于 YOLOv8 的森林火灾检测系统(Web 版)
前端·yolo
微尘hjx7 天前
【Deep-OC-SORT 06】多轨迹算法Deep-OC-SORT-CMC相机运动补偿
yolo·目标检测·目标跟踪·ultralytics·轨迹算法·deep-oc-sort·车流统计
LongRunning8 天前
【Linux】RK3568-OpenCV+YOLO(八)
linux·opencv·yolo
微尘hjx12 天前
【Deep-OC-SORT 01】多轨迹算法Deep-OC-SORT源码分析
深度学习·yolo·目标跟踪·ultralytics·轨迹算法·deep-oc-sort·车流统计