Latency and FPS measurement #3
Conversation
|
i am running the sample video with .264 extension and getting this error.please help me to resolve this issue. sudo ./deepstream-pose-estimation-app sample_qHD.h264 sohail22 0:00:01.348730282 7957 0x563249c1e070 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /home/convsys/deepstream_sdk_v5.0.1_x86_64/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation-master/resnet18.engine |
|
https://forums.developer.nvidia.com/t/nvosd-circle-crash/157368
From: sohail759 <[email protected]>
Sent: Sunday, February 14, 2021 4:35 PM
To: NVIDIA-AI-IOT/deepstream_pose_estimation <[email protected]>
Cc: Subscribed <[email protected]>
Subject: Re: [NVIDIA-AI-IOT/deepstream_pose_estimation] Latency and FPS measurement (#3)
i am running the sample video with .264 extension and getting this error.please help me to resolve this issue.
sudo ./deepstream-pose-estimation-app sample_qHD.h264 sohail22
Now playing: sample_qHD.h264
0:00:01.348653041 7957 0x563249c1e070 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from :/home/convsys/deepstream_sdk_v5.0.1_x86_64/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation-master/resnet18.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:685 [FullDims Engine Info]: layers num: 4
0 INPUT kFLOAT input 3x224x224 min: 1x3x224x224 opt: 1x3x224x224 Max: 1x3x224x224
1 OUTPUT kFLOAT part_affinity_fields 56x56x42 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT heatmap 56x56x18 min: 0 opt: 0 Max: 0
3 OUTPUT kFLOAT maxpool_heatmap 56x56x18 min: 0 opt: 0 Max: 0
0:00:01.348730282 7957 0x563249c1e070 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /home/convsys/deepstream_sdk_v5.0.1_x86_64/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation-master/resnet18.engine
0:00:01.351122025 7957 0x563249c1e070 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:deepstream_pose_estimation_config.txt sucessfully
Running...
libnvosd (603):(ERROR) : Out of bound radius
0:00:03.876006191 7957 0x563249c60a30 WARN nvinfer gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: Internal data stream error.
0:00:03.876013208 7957 0x563249c60a30 WARN nvinfer gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: streaming stopped, reason error (-5)
ERROR from element nv-onscreendisplay: Unable to draw circles
Error details: gstnvdsosd.c(558): gst_nvds_osd_transform_ip (): /GstPipeline:deepstream-tensorrt-openpose-pipeline/GstNvDsOsd:nv-onscreendisplay
Returned, stopping playback
Deleting pipeline
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#3 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AGZNUYLQQGNWBMQJNRJR5FTS673UNANCNFSM4XQYUS2A>.
|
|
thanks for reply.
can you please suggest me some solution of this.
…On Sun, Feb 14, 2021 at 9:49 PM robbiwu ***@***.***> wrote:
https://forums.developer.nvidia.com/t/nvosd-circle-crash/157368
From: sohail759 ***@***.***>
Sent: Sunday, February 14, 2021 4:35 PM
To: NVIDIA-AI-IOT/deepstream_pose_estimation <
***@***.***>
Cc: Subscribed ***@***.***>
Subject: Re: [NVIDIA-AI-IOT/deepstream_pose_estimation] Latency and FPS
measurement (#3)
i am running the sample video with .264 extension and getting this
error.please help me to resolve this issue.
sudo ./deepstream-pose-estimation-app sample_qHD.h264 sohail22
Now playing: sample_qHD.h264
0:00:01.348653041 7957 0x563249c1e070 INFO nvinfer
gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from
NvDsInferContextImpl::deserializeEngineAndBackend()
<nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from
:/home/convsys/deepstream_sdk_v5.0.1_x86_64/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation-master/resnet18.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:685 [FullDims Engine Info]:
layers num: 4
0 INPUT kFLOAT input 3x224x224 min: 1x3x224x224 opt: 1x3x224x224 Max:
1x3x224x224
1 OUTPUT kFLOAT part_affinity_fields 56x56x42 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT heatmap 56x56x18 min: 0 opt: 0 Max: 0
3 OUTPUT kFLOAT maxpool_heatmap 56x56x18 min: 0 opt: 0 Max: 0
0:00:01.348730282 7957 0x563249c1e070 INFO nvinfer
gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from
NvDsInferContextImpl::generateBackendContext()
<nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model:
/home/convsys/deepstream_sdk_v5.0.1_x86_64/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation-master/resnet18.engine
0:00:01.351122025 7957 0x563249c1e070 INFO nvinfer
gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new
model:deepstream_pose_estimation_config.txt sucessfully
Running...
libnvosd (603):(ERROR) : Out of bound radius
0:00:03.876006191 7957 0x563249c60a30 WARN nvinfer
gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: Internal data stream
error.
0:00:03.876013208 7957 0x563249c60a30 WARN nvinfer
gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: streaming stopped,
reason error (-5)
ERROR from element nv-onscreendisplay: Unable to draw circles
Error details: gstnvdsosd.c(558): gst_nvds_osd_transform_ip ():
/GstPipeline:deepstream-tensorrt-openpose-pipeline/GstNvDsOsd:nv-onscreendisplay
Returned, stopping playback
Deleting pipeline
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<
#3 (comment)>,
or unsubscribe<
https://github.com/notifications/unsubscribe-auth/AGZNUYLQQGNWBMQJNRJR5FTS673UNANCNFSM4XQYUS2A>.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#3 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AP6J2JYYPPM6OK6B4NM5TDLS675I3ANCNFSM4XQYUS2A>
.
|
|
Hello,have you solved this problem,I hit the same error,can you give me some advice,thx!!! |
|
Yes I have resolved that problem.i just perform the 3rd step of guide and
then remake the app.
…On Tue, 16 Mar 2021, 12:47 pm yantaixu0120, ***@***.***> wrote:
Hello,have you solved this problem,I hit the same error,can you give me
some advice,thx!!!
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#3 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AP6J2J6OACPVXP55F7X7RNDTD4EHXANCNFSM4XQYUS2A>
.
|
Do you mean " Download the TRTPose model, convert it to ONNX using this export utility, and set its location in the DeepStream configuration file" |
|
*Step 3: Replace the OSD library in the DeepStream install directory.*
*Perform this step and remake the app.this will resolve the problem.*
On Tue, 16 Mar 2021, 12:54 pm yantaixu0120, ***@***.***>
wrote:
… Yes I have resolved that problem.i just perform the 3rd step of guide and
then remake the app.
… <#m_6625076619958295573_m_-741326857377205296_>
On Tue, 16 Mar 2021, 12:47 pm yantaixu0120, *@*.***> wrote: Hello,have
you solved this problem,I hit the same error,can you give me some
advice,thx!!! — You are receiving this because you commented. Reply to this
email directly, view it on GitHub <#3 (comment)
<#3 (comment)>>,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AP6J2J6OACPVXP55F7X7RNDTD4EHXANCNFSM4XQYUS2A
.
Do you mean " Download the TRTPose model, convert it to ONNX using this
export utility, and set its location in the DeepStream configuration file"
this step??
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#3 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AP6J2JYOWHALSBBSNSI742DTD4FCLANCNFSM4XQYUS2A>
.
|
|
Here is a link of detailed steps.
https://developer.nvidia.com/blog/creating-a-human-pose-estimation-application-with-deepstream-sdk/
…On Tue, 16 Mar 2021, 1:12 pm sohail awan, ***@***.***> wrote:
*Step 3: Replace the OSD library in the DeepStream install directory.*
*Perform this step and remake the app.this will resolve the problem.*
On Tue, 16 Mar 2021, 12:54 pm yantaixu0120, ***@***.***>
wrote:
> Yes I have resolved that problem.i just perform the 3rd step of guide and
> then remake the app.
> … <#m_7282932526300136930_m_6625076619958295573_m_-741326857377205296_>
> On Tue, 16 Mar 2021, 12:47 pm yantaixu0120, *@*.***> wrote: Hello,have
> you solved this problem,I hit the same error,can you give me some
> advice,thx!!! — You are receiving this because you commented. Reply to this
> email directly, view it on GitHub <#3 (comment)
> <#3 (comment)>>,
> or unsubscribe
> https://github.com/notifications/unsubscribe-auth/AP6J2J6OACPVXP55F7X7RNDTD4EHXANCNFSM4XQYUS2A
> .
>
> Do you mean " Download the TRTPose model, convert it to ONNX using this
> export utility, and set its location in the DeepStream configuration file"
> this step??
>
> —
> You are receiving this because you commented.
> Reply to this email directly, view it on GitHub
> <#3 (comment)>,
> or unsubscribe
> <https://github.com/notifications/unsubscribe-auth/AP6J2JYOWHALSBBSNSI742DTD4FCLANCNFSM4XQYUS2A>
> .
>
|
thanks， 0:00:00.813945366 24705 0x5599042de4f0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation/human_pose.onnx_b1_gpu0_fp16.engine 0:00:00.813998830 24705 0x5599042de4f0 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream_pose_estimation/human_pose.onnx_b1_gpu0_fp16.engine how can i fixed it?thx |
Hi,
I've added latency and fps calculation to the code if you guys interested. Nothing fancy, just added the same code sections from sample apps without any switch to turn on/off.