Does the function in classifier_parser work for each individual object when batch_size > 1?

[yeongjae1]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

hello

I set batch_size = 8 of SGIE and made the parser function below work after classification in SGIE, but only one obj (individual) comes in, can you tell me why?

extern "C" bool NvDsInferClassiferParseCustomFaceRecognition(
    std::vector<NvDsInferLayerInfo> const &outputLayersInfo,
    NvDsInferNetworkInfo const &networkInfo,
    float classifierThreshold,
    std::vector<NvDsInferAttribute> &attrList,
    std::string &descString)
{

[Fiona.Chen]

What is your SGIE?

[yeongjae1]

It is a FaceRecognize model, and TRT was created based on Onnx (Third-party REPO)
I didn’t use Nvidia-Tao separately
But I’m curious, is it possible to enter the custom_parser function in batch units?

[Fiona.Chen]

This custom parse function is just a callback which parse one frame output of the batch.

Please refer to the function InferPostprocessor::postProcessHost() in /opt/nvidia/deepstream/deepstream/sources/libs/nvdsinfer/nvdsinfer_context_impl.cpp

[yeongjae1]

I looked at the line of code you mentioned, and it appears to me that the NvDsInferClassiferParseCustomSoftmax function handles objects one by one.
Am I right??

extern "C"
bool NvDsInferClassiferParseCustomSoftmax (std::vector<NvDsInferLayerInfo> const &outputLayersInfo,
        NvDsInferNetworkInfo  const &networkInfo,
        float classifierThreshold,
        std::vector<NvDsInferAttribute> &attrList,
        std::string &descString)
{
    /* Get the number of attributes supported by the classifier. */
    unsigned int numAttributes = outputLayersInfo.size();

    /* Iterate through all the output coverage layers of the classifier.
    */
    for (unsigned int l = 0; l < numAttributes; l++)
    {
        /* outputCoverageBuffer for classifiers is usually a softmax layer.
         * The layer is an array of probabilities of the object belonging
         * to each class with each probability being in the range [0,1] and
         * sum all probabilities will be 1.
         */
        NvDsInferDimsCHW dims;

        getDimsCHWFromDims(dims, outputLayersInfo[l].inferDims);
        unsigned int numClasses = dims.c;
        float *outputCoverageBuffer = (float *)outputLayersInfo[l].buffer;
        float maxProbability = 0;
        bool attrFound = false;
        NvDsInferAttribute attr;

[Fiona.Chen]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

@yeongjae1

I looked at the line of code you mentioned, and it appears to me that the NvDsInferClassiferParseCustomSoftmax function handles objects one by one.

You can think so.