Deepstream-test3 deepstream-5.0

2678236133 · March 23, 2021, 1:06pm

Please provide complete information as applicable to your setup.

•Hardware Platform ( GPU) ：GeForce GTX 1660
•DeepStream Version ：deepstream-5.0_5.0.0-1_amd64.deb
•TensorRT Version： trt7.0.0.11
•NVIDIA GPU Driver Version ：NVIDIA-SMI 440.33.01
•CUDA Version：10.2
• CUDNN Version：7.6.5
• Issue Type( questions, new requirements, bugs)： questions
• 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)
command used is as below.

cd /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3/
make
./deepstream-test3-app file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4

Hi Guys,

I am trying to run deepstream-test3-app with video. I can not get it to work normally. The output of demo is shown as below.

./deepstream-test3-app file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
Now playing: file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4,
libEGL warning: DRI2: failed to authenticate
WARNING: …/nvdsinfer/nvdsinfer_func_utils.cpp:34 [TRT]: Current optimization profile is: 0. Please ensure there are no enqueued operations pending in this context prior to switching profiles
0:00:01.023123404 31307 0x556eff8c5100 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1577> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:685 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

0:00:01.023162946 31307 0x556eff8c5100 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1681> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:01.023631034 31307 0x556eff8c5100 INFO nvinfer gstnvinfer_impl.cpp:311:notifyLoadModelStatus: [UID 1]: Load new model:dstest3_pgie_config.txt sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Running…
Decodebin child added: qtdemux0
Decodebin child added: multiqueue0
Decodebin child added: h264parse0
Decodebin child added: capsfilter0
Decodebin child added: aacparse0
Decodebin child added: avdec_aac0
Decodebin child added: nvv4l2decoder0
In cb_newpad
In cb_newpad
cuGraphicsGLRegisterBuffer failed with error(304) gst_eglglessink_cuda_init texture = 1
Frame Number = 0 Number of objects = 6 Vehicle Count = 4 Person Count = 2
0:00:01.234093157 31307 0x556eff3f8ca0 WARN nvinfer gstnvinfer.cpp:1946:gst_nvinfer_output_loop: error: Internal data stream error.
0:00:01.234101349 31307 0x556eff3f8ca0 WARN nvinfer gstnvinfer.cpp:1946:gst_nvinfer_output_loop: error: streaming stopped, reason not-negotiated (-4)
ERROR from element primary-nvinference-engine: Internal data stream error.
Error details: gstnvinfer.cpp(1946): gst_nvinfer_output_loop (): /GstPipeline:dstest3-pipeline/GstNvInfer:primary-nvinference-engine:
streaming stopped, reason not-negotiated (-4)
Returned, stopping playback
Frame Number = 1 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 2 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Frame Number = 3 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 4 Number of objects = 7 Vehicle Count = 4 Person Count = 3
Frame Number = 5 Number of objects = 6 Vehicle Count = 4 Person Count = 2
Frame Number = 6 Number of objects = 5 Vehicle Count = 3 Person Count = 2
Deleting pipeline

Before this, I have run sucessfully this demo in jetson nano with deepstrem 5.0. However, curious about how to use deepstream5.0 in x86 platform with gpu.

Please help me out.

Thanks.

amycao · March 25, 2021, 2:00am

HI,
Sorry for the delay.
You need to use nvidia GPU as display.

2678236133 · March 25, 2021, 2:30am

Sorry for not understanding what you say. GeForce GTX 1660 can not use deepstream? However, I find that gtx 1660 can work in this post Why the fps is not crossing 35 even though free GPU space available - #6 by Fiona.Chen. Can you show available gpu list？

Thanks!

amycao · March 25, 2021, 3:07am

I mean you use another non nvidia GPU as display. you can use geforce 1660 for deepstream, but you may use non nvidia GPU as display. please check your setup.

2678236133 · March 25, 2021, 3:23am

I have just one gpu, and there is not integrated gpu in intel cpu. how to check my setup.
Thank you for your help

amycao · March 25, 2021, 3:55am

Oh, ok. can you login to desktop? or you can export the display from remote terminal.
export DISPLAY=:0 or 1 // xrandr to check if export success
please let me know if this works. if still not work, should be your display driver installation issue.

2678236133 · March 25, 2021, 5:27am

it still does not work. command and output is shown below.

root@pysoft:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3# export DISPLAY=:0
root@pysoft:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3# echo $DISPLAY
:0
root@pysoft:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3# xrandr
Invalid MIT-MAGIC-COOKIE-1 keyCan’t open display :0
root@pysoft:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3# export DISPLAY=:1
root@pysoft:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test3# xrandr
Screen 0: minimum 8 x 8, current 1440 x 900, maximum 32767 x 32767
DVI-D-0 disconnected (normal left inverted right x axis y axis)
HDMI-0 connected primary 1440x900+0+0 (normal left inverted right x axis y axis) 410mm x 260mm
1440x900 59.89*+ 74.98
1920x1080 59.94
1280x1024 75.02 60.02
1280x960 60.00
1280x720 59.94
1152x864 75.00
1024x768 75.03 70.07 60.00
800x600 75.00 60.32 56.25
720x480 59.94 59.94
640x480 75.00 59.94
DP-0 disconnected (normal left inverted right x axis y axis)
DP-1 disconnected (normal left inverted right x axis y axis)

amycao · March 25, 2021, 5:44am

Can you share how you install the display driver?

2678236133 · March 25, 2021, 6:11am

step1: install display driver
NVIDIA-Linux-x86_64-450.51.run is installed.
sudo ./NVIDIA-Linux-x86_64-450.51.run

step2: install cuda
sudo dpkg -i cuda-repo-ubuntu1804-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb
sudo apt-key add /var/cuda-repo-10-2-local-10.2.89-440.33.01/7fa2af80.pub
sudo apt-get update
sudo apt-get install cuda

sudo dpkg -i cuda-repo-ubuntu1804-10-2-local_10.2.1-1_amd64
sudo dpkg -i cuda-repo-ubuntu1804-10-2-local_10.2.2-1_amd64

after step1, nvidia-smi show that verison of display driver is 450.51.
however, after step2, nvidia-smi show that verison of display driver is 440.33.01.

I find post suffix of cuda10.2 is 440.33.01, but I just see the only cuda10.2 version.

amycao · March 25, 2021, 10:29am

please make sure cuda version and display driver version match. try with cuda 11.0.2

wget http://developer.download.nvidia.com/compute/cuda/11.0.2/local_installers/cuda_11.0.2_450.51.05_linux.run
sudo sh cuda_11.0.2_450.51.05_linux.run

2678236133 · March 30, 2021, 3:43am

Thanks for your help. It works. but I still have a question how to save image based on deepstream-test3 with gtx1660.
Before, I use below code to sucess to save opencv Mat with jetson nano. Now, how should I do. Thank you!

GstPadProbeReturn nvosd_src_pad_buffer_probe(GstPad *pad, GstPadProbeInfo *info, gpointer u_data)
{

GstBuffer *buf = (GstBuffer *)info->data;

```
NvDsMetaList *l_frame = NULL;
```
```
NvDsMetaList *l_user_meta = NULL;
```
```
GstMapInfo in_map_info;
```
```
char *src_data = NULL;
```

if (!gst_buffer_map(buf, &in_map_info, GST_MAP_READ))

```
{
```

    g_print("Error: Failed to map gst buffer\n");

    gst_buffer_unmap(buf, &in_map_info);

```
    return GST_PAD_PROBE_OK;
```
```
}
```

NvBufSurface *surface = (NvBufSurface *)in_map_info.data;

NvDsBatchMeta *batch_meta = gst_buffer_get_nvds_batch_meta(buf);

for (l_frame = batch_meta->frame_meta_list; l_frame != NULL; l_frame = l_frame->next)

```
{   
```

    NvDsFrameMeta *frame_meta = (NvDsFrameMeta *)(l_frame->data);

    src_data = (char *)malloc(surface->surfaceList[frame_meta->batch_id].dataSize);

```
    if (src_data == NULL)
```
```
    {
```

        g_print("Error: failed to malloc src_data \n");

```
        continue;
```
```
    }
```

    NvBufSurfaceMap(surface, -1, -1, NVBUF_MAP_READ);

    NvBufSurfacePlaneParams *pParams = &surface->surfaceList[frame_meta->batch_id].planeParams;

```
    unsigned int offset = 0;
```

    for (unsigned int num_planes = 0; num_planes < pParams->num_planes; num_planes++)

```
    {
```
```
        if (num_planes > 0)
```

            offset += pParams->height[num_planes - 1] * (pParams->bytesPerPix[num_planes - 1] * pParams->width[num_planes - 1]);

        for (unsigned int h = 0; h < pParams->height[num_planes]; h++)

```
        {
```

            memcpy((void *)(src_data + offset + h * pParams->bytesPerPix[num_planes] * pParams->width[num_planes]),

                   (void *)((char *)surface->surfaceList[frame_meta->batch_id].mappedAddr.addr[num_planes] + h * pParams->pitch[num_planes]),

                   pParams->bytesPerPix[num_planes] * pParams->width[num_planes]);

```
        }
```
```
    }
```

    NvBufSurfaceSyncForDevice(surface, -1, -1);

    NvBufSurfaceUnMap(surface, -1, -1);

    gint frame_width = (gint)surface->surfaceList[frame_meta->batch_id].width;

    gint frame_height = (gint)surface->surfaceList[frame_meta->batch_id].height;

    gint frame_step = surface->surfaceList[frame_meta->batch_id].pitch;

    cv::Mat frame = cv::Mat(frame_height, frame_width, CV_8UC4, src_data, frame_step);

    cv::Mat out_mat = cv::Mat(cv::Size(frame_width, frame_height), CV_8UC3);

    cv::cvtColor(frame, out_mat, COLOR_RGBA2BGR);

if (src_data != NULL)
```
    {
```
```
        free(src_data);
```
```
        src_data = NULL;
```
```
    }
```
```
}
```
```
gst_buffer_unmap(buf, &in_map_info);
```
```
return GST_PAD_PROBE_OK;
```
}

amycao · April 13, 2021, 2:53am

Hi,
Please refer to this topic, there one workable save image for dGPU.
RTSP camera access frame issue - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums