• Hardware Platform (Jetson / GPU) GPU RTX 2060
• DeepStream Version 5.0
• TensorRT Version 7.1
• NVIDIA GPU Driver Version (valid for GPU only) 450
I have added dsexample in the pipeline between nvvidconv and nvosd
and its working except
when I tried access 2 videos its giving information of 1 batch at a time in gst_dsexample_transform_ip function
‘’’
static GstFlowReturn
gst_dsexample_transform_ip (GstBaseTransform * btrans, GstBuffer * inbuf)
{
GstDsExample *dsexample = GST_DSEXAMPLE (btrans);
GstMapInfo in_map_info;
GstFlowReturn flow_ret = GST_FLOW_ERROR;
gdouble scale_ratio = 1.0;
DsExampleOutput *output;
NvBufSurface *surface = NULL;
NvDsBatchMeta *batch_meta = NULL;
NvDsFrameMeta *frame_meta = NULL;
NvDsMetaList * l_frame = NULL;
guint i = 0;
batch_meta = gst_buffer_get_nvds_batch_meta (inbuf);
std::cout<<"numbatch inside gst:"<<batch_meta->num_frames_in_batch<<"\n";
‘’’
…
output is
numbatch inside gst:1
I’m developing a custom plugin using DeepStream 5.0 on T4 platform.
Base on gst-dsexample, I’m trying to implement a simple function to add some texts for display on selected video sources.
I’m doing this by changing gst_dsexample_transform_ip function in gstdsexample.cpp:
// Iterating through frames in batched meta from diff. sources
for (l_frame = batch_meta->frame_meta_list; l_frame != NULL;
l_frame = l_frame->next) {
frame_meta = (NvDsFrameMeta *) (l_frame->data);
if (fr…
Similar to this my source_id is always 0 even if I have 2 inputs!!!
My pipeline is queue1, pgie, queue2,nvtracker, queue3, tiler, queue4,
nvvidconv, queue5,dsexample, queue6, nvosd, queue7, sink,
Hi Please someone respond
Can you try with latest DS 6.0?
Is it wont work with 5.0 or 5.1?
Because upgradation will take some time and we need to deploy the device soon
with 5.1 in jetson nano
Setup Info
• Hardware Platform (Jetson / GPU) - GPU
• DeepStream Version - deepstream:5.0-20.07-devel
• TensorRT Version - Haven’t changed the default that comes with container deepstream:5.0-20.07-devel
• NVIDIA GPU Driver Version (valid for GPU only) - 440.33.01
• Sample application and the configuration file content - …/sample_apps/deepstream-nvdsanalytics-test/deepstream_nvdsanalytics_test.cpp
• Reproduce steps
I was trying to save the cropped image being generated after analytics usi…
Mine is similar to this But couldnt understand how she solved it!!
please find attached code
deepstream_test3_app.c (24.0 KB)
gstdsexample.cpp (34.2 KB)
Your pipeline shows you put dsexample after nvmultistreamtiler. The Gst-nvmultistreamtiler plugin composites a 2D tile from batched buffers. Gst-nvmultistreamtiler — DeepStream 6.1.1 Release documentation After nvmultistreamtiler, the batch is a one frame batch. So it is correct to see batch size is 1.
system
Closed
December 13, 2021, 6:43am
14
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.