deepstream yolov5-6.0使用指南

首先修改  Yolov5-6.0的源码  yolo.py,将最后return,改为torch.cat(z, 1)

    def forward(self, x):
        z = []  # inference output
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
                    anchor_grid = (self.anchors[i].clone() * self.stride[i]).view(1, -1, 1, 1, 2)

                y = x[i].sigmoid()
                if self.inplace:
                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh
                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    wh = (y[..., 2:4] * 2) ** 2 * anchor_grid  # wh
                    y = torch.cat((xy, wh, y[..., 4:]), -1)
                z.append(y.view(bs, -1, self.no))

        return torch.cat(z, 1)

export导出的onnx是这样的:只有一个25200*6(1个类别)deepstream yolov5-6.0使用指南_第1张图片

然后在deepstream的/usr/src/tensorrt/bin下执行:onnx转engine

./trtexec --onnx=./personcartruck.onnx --saveEngine=./personcartruck.engine   --fp16

后处理修改:

进入/opt/nvidia/deepstream/deepstream/sources/libs/nvdsinfer_customparser/nvdsinfer_custombboxparser.cpp

覆盖后执行,make install  会生成so到lib下,然后配置在config文件中,文章的最后有例子

/*
 * Copyright (c) 2018-2020, NVIDIA CORPORATION. All rights reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
 * DEALINGS IN THE SOFTWARE.
 */

#include 
#include 
#include "nvdsinfer_custom_impl.h"
#include 
#include 
#include 
#include 

#define MIN(a,b) ((a) < (b) ? (a) : (b))
#define MAX(a,b) ((a) > (b) ? (a) : (b))
#define CLIP(a,min,max) (MAX(MIN(a, max), min))
#define DIVIDE_AND_ROUND_UP(a, b) ((a + b - 1) / b)

struct MrcnnRawDetection {
    float y1, x1, y2, x2, class_id, score;
};

/* This is a sample bounding box parsing function for the sample Resnet10
 * detector model provided with the SDK. */

/* C-linkage to prevent name-mangling */
extern "C"
bool NvDsInferParseYolo (std::vector const &outputLayersInfo,
        NvDsInferNetworkInfo  const &networkInfo,
        NvDsInferParseDetectionParams const &detectionParams,
        std::vector &objectList);

/* This is a sample bounding box parsing function for the tensorflow SSD models
 * detector model provided with the SDK. */


static std::vector
nonMaximumSuppression(const float nmsThresh, std::vector binfo)
{
    auto overlap1D = [](float x1min, float x1max, float x2min, float x2max) -> float {
        if (x1min > x2min)
        {
            std::swap(x1min, x2min);
            std::swap(x1max, x2max);
        }
        return x1max < x2min ? 0 : std::min(x1max, x2max) - x2min;
    };
    auto computeIoU
        = [&overlap1D](NvDsInferParseObjectInfo& bbox1, NvDsInferParseObjectInfo& bbox2) -> float {
        float overlapX
            = overlap1D(bbox1.left, bbox1.left + bbox1.width, bbox2.left, bbox2.left + bbox2.width);
        float overlapY
            = overlap1D(bbox1.top, bbox1.top + bbox1.height, bbox2.top, bbox2.top + bbox2.height);
        float area1 = (bbox1.width) * (bbox1.height);
        float area2 = (bbox2.width) * (bbox2.height);
        float overlap2D = overlapX * overlapY;
        float u = area1 + area2 - overlap2D;
        return u == 0 ? 0 : overlap2D / u;
    };

    std::stable_sort(binfo.begin(), binfo.end(),
                     [](const NvDsInferParseObjectInfo& b1, const NvDsInferParseObjectInfo& b2) {
                         return b1.detectionConfidence > b2.detectionConfidence;
                     });
    std::vector out;
    for (auto i : binfo)
    {
        bool keep = true;
        for (auto j : out)
        {
            if (keep)
            {
                float overlap = computeIoU(i, j);
                keep = overlap <= nmsThresh;
            }
            else
                break;
        }
        if (keep) out.push_back(i);
    }
    return out;
}


float clamp(const float val, const float minVal, const float maxVal)
{
    assert(minVal <= maxVal);
    return std::min(maxVal, std::max(minVal, val));
}

static NvDsInferParseObjectInfo convertBBox(
    const float& bx, const float& by, const float& bw,
    const float& bh, const uint& netW, const uint& netH)
{
    NvDsInferParseObjectInfo b;

    float x1 = bx - bw / 2;
    float y1 = by - bh / 2;
    float x2 = x1 + bw;
    float y2 = y1 + bh;

    x1 = clamp(x1, 0, netW);
    y1 = clamp(y1, 0, netH);
    x2 = clamp(x2, 0, netW);
    y2 = clamp(y2, 0, netH);

    b.left = x1;
    b.width = clamp(x2 - x1, 0, netW);
    b.top = y1;
    b.height = clamp(y2 - y1, 0, netH);

    return b;
}

static void addBBoxProposal(
    const float bx, const float by, const float bw, const float bh,
    const uint& netW, const uint& netH, const int maxIndex,
    const float maxProb, std::vector& binfo)
{
    NvDsInferParseObjectInfo bbi = convertBBox(bx, by, bw, bh, netW, netH);
    if (bbi.width < 1 || bbi.height < 1) return;

    bbi.detectionConfidence = maxProb;
    bbi.classId = maxIndex;
    binfo.push_back(bbi);
}

static std::vector
nmsAllClasses(const float nmsThresh,
        std::vector& binfo,
        const uint numClasses)
{
    std::vector result;
    std::vector> splitBoxes(numClasses);
    for (auto& box : binfo)
    {
        splitBoxes.at(box.classId).push_back(box);
    }

    for (auto& boxes : splitBoxes)
    {
        boxes = nonMaximumSuppression(nmsThresh, boxes);
        result.insert(result.end(), boxes.begin(), boxes.end());
    }
    return result;
}


extern "C" bool NvDsInferParseYolo(
    std::vector const& outputLayersInfo,
    NvDsInferNetworkInfo const& networkInfo,
    NvDsInferParseDetectionParams const& detectionParams,
    std::vector& objectList)
{

    const float kCONF_THRESH = detectionParams.perClassThreshold[0];
    int dimensions  = 5 + detectionParams.numClassesConfigured;
    int confidenceIndex = 4;
    int labelStartIndex = 5;
    const float beta_nms = 0.45;

    std::vector binfo;
    for (unsigned int l = 0; l < 1; l++)
    {
        float* output = (float *)outputLayersInfo[l].buffer;
        const NvDsInferLayerInfo &layer = outputLayersInfo[0];

        //printf("zwh  layer.inferDims.d[0] %d, layer.inferDims.d[1] %d \n", layer.inferDims.d[0],layer.inferDims.d[1]);
        for (int i = 0; i < 25200; ++i) {
            int index = i * dimensions;       // index是5+classnum的倍数,位置是0;
            if(output[index+confidenceIndex] <= 0.4f) continue;

            for (int j = labelStartIndex; j < dimensions; ++j) {
                output[index+j] = output[index+j] * output[index+confidenceIndex];
            }

            for (int k = labelStartIndex; k < dimensions; ++k) {
                if(output[index+k] <= kCONF_THRESH) continue;
                const float bx = output[index];
                const float by = output[index+1];
                const float bw = output[index+2];
                const float bh = output[index+3];

                const float maxProb = output[index+k];
                const int maxIndex = k -5;   // k是5+0的位置,所以类别是k-5
                addBBoxProposal(bx, by, bw, bh, networkInfo.width, networkInfo.height, maxIndex, maxProb, binfo);
                
            }
        }
    }
    objectList.clear();
    objectList = nmsAllClasses(beta_nms, binfo, detectionParams.numClassesConfigured);

    return true;

}

/* Check that the custom function has been defined correctly */
CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE(NvDsInferParseYolo);

 然后在配置文件中配置:

#修改类别数

num-detected-classes=3 
parse-bbox-func-name=NvDsInferParseYolo
custom-lib-path=/opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_infercustomparser.so

你可能感兴趣的:(人工智能)