我们现在有个自己训练的模型,想在发送消息前对收到的消息进行加工,应该如何做?

我们有自己训练好的模型,对其中的输出结果我们都感兴趣,但是怎么从这所有的结果中统计出一个正确可信的值?我需要一个连续记录的过程和统计分析的过程这该如何做呢??举个例子,我们现在就是想要识别到的结果,但是我们每帧都在识别,是否要每帧都发送呢,应该是统计一段时间内的识别结果,把统计后的结果发送。比如统计一秒内的30个结果,发现有28个识别成了13,有两个识别成了18,那我们就把这个13发送出去,18就不要了,就是如何在deepstream中处理数据,再通过Kafka将数据发送出去

1 AI models can’t identify objects with 100% accuracy, you can use threshold to filter that low probability, please find threshold, segmentation-threshold, classifier-threshold in this link: Gst-nvinfer — DeepStream 6.1.1 Release documentation
2 about Kafka, you can refer to deepstream-test4, deepstream-test5.

可以通过Gst-nvinfer来实现对原始识别数据的加工吗??

yes, please set network-type to 100, then you can access original inference output NvDsInferTensorMeta, please refer to the sample deepstream-infer-tensor-meta-test.

这个例子deepstream-infer-tensor-meta-test我该怎么使用呢?

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• 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)

1 please install deepstream SDK, here is the link: Quickstart Guide — DeepStream 6.1.1 Release documentation
2 enter to /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-infer-tensor-meta-test, then refer to deepstream-infer-tensor-meta-test’s readme, which includes detailed steps.

为什么我会出现下面的问题?
ERROR from element h264parse0: No valid frames found before end of stream
Error details: gstbaseparse.c(3625): gst_base_parse_loop (): /GstPipeline:dstensor-pipeline/GstH264Parse:h264parse0
Returned, stopping playback

please share your start command and the whole logs. seemed can’t find h264 frame from the input file.

这是我的开始命令:./deepstream-infer-tensor-meta-app dstensor_sgie1_config.txt sample_720p.h264
这是所有的错误:
Running…
ERROR from element h264parse0: No valid frames found before end of stream
Error details: gstbaseparse.c(3625): gst_base_parse_loop (): /GstPipeline:dstensor-pipeline/GstH264Parse:h264parse0
Returned, stopping playback

(deepstream-infer-tensor-meta-app:1460): GStreamer-CRITICAL **: 08:50:28.683: gst_value_intersect: assertion ‘G_IS_VALUE (value2)’ failed

(deepstream-infer-tensor-meta-app:1460): GStreamer-CRITICAL **: 08:50:28.683: gst_mini_object_unref: assertion ‘GST_MINI_OBJECT_REFCOUNT_VALUE (mini_object) > 0’ failed
Deleting pipeline

please refer to deepstream-infer-tensor-meta-test’s readme, here is how to start:
4. Usage:
$ ./deepstream-infer-tensor-meta-app -t “infer-type” “h264_elementary_stream”

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

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.