Deepstream-bodypose2d-app use int8_calibration_320_448.txt log print (errors invalid input pafmap dimension.)

Accelerated Computing Intelligent Video Analytics TAO Toolkit
,
1

Please provide the following information when requesting support.

• Hardware (Jetson TX2 xavier NX JetPack4.6)
• Network Type (bodypostNet)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
step1:
git clone GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream
step2:
cd deepstream_tao_apps/configs/bodypose2d_tao
vim bodypose2d_pgie_config.txt
…
int8-calib-file=…/…/models/bodypose2d/int8_calibration_320_448.txt
infer-dims=3;320;384
network-mode=1
…
step3:cd deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app
./deepstream-bodypose2d-app 1 …/…/…/configs/bodypose2d_tao/sample_bodypose2d_model_config.txt file:///media/nvidia/SD/src/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app/dance.mp4 ./body2dout
===== NVMEDIA: NVENC =====
NvMMLiteBlockCreate : Block : BlockType = 4
terminate called after throwing an instance of ‘std::runtime_error’
what(): invalid input pafmap dimension.
Aborted (core dumped)

2

Hi,
This looks more related to Deepstream. We are moving this post to the Deepstream forum to get better help.
Thank you.

4

Hi @yezhouyin
Is it still an issue? I saw you submitted another topic (When bodypostNet is from fp16 to int8, the effect is significantly worse) and it seems the program is running already.

5

If you run with the default official model, please keep the original setting.
Please check if you can run with the default setting.

6

Thank you for your attention, these are two problems, 1. It is possible to use the default configuration of 3x288x384 with int8, but the effect is too bad. I want to use a larger size of 3x320x448 on int8, but an error is reported; 2. From fp16 to int8 detection The effect is too bad, I don’t know if there is a problem with the int8 calibration file

7

Thank you for your attention. The default configuration of 3x288x384 can be run with int8, but the effect is too bad. I want to use a larger size of 3x320x448 on int8. The official also gave 3 calibration files for reference: https://catalog.ngc. nvidia.com/orgs/nvidia/teams/tao/models/bodyposenet/files

9

Here is bodypose model doc, BodyPoseNet | NVIDIA NGC

int8-calib-file=…/…/models/bodypose2d/int8_calibration_320_448.txt
infer-dims=3;320;384
network-mode=1
here did you try infer-dims=3;320;448?

10

Sorry, I wrote infer-dims=3;320;384, actually I tried
infer-dims=3;320;448

The log prints invalid input pafmap dimension

13

Can you download tao-converter into your machine and then convert it into a new tensorrt engine?

$ tao-converter model.etlt -k nvidia_tlt -p input_1:0,1x320x448x3,4x320x448x3,16x320x448x3 -t fp16 -m 16 -e fp16.engine

Then config it to “model-engine-file” and retry.

14

Thank you for your attention
command：
tao-converter -k nvidia_tlt -p input_1:0,1x320x448x3,1x320x448x3,1x320x448x3 model.etlt -t int8 -c int8_calibration_320_448.txt -e tao-converter.model_int8_b1_320_448.engine -b 1
the conversion of tao-converter to engine does not report an error, and the same error is printed when running

15

Please share the latest full log again. Thanks.

16

Uploading: tao-converter.model_int8_b1_320_448.engine…
bodynet.log (2.5 KB)
bodypose2d_pgie_config.txt (3.1 KB)

17

Please modify deepstream_bodypose2d_app.cpp(deepstream_tao_apps/deepstream_bodypose2d_app.cpp at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub) and then make clean and make.
$ vim deepstream_bodypose2d_app.cpp

//cvcore::ModelInputParams ModelInputParams = {8, 384, 288, cvcore::RGB_U8};
cvcore::ModelInputParams ModelInputParams = {8, 448, 320, cvcore::RGB_U8};

Then, you can run with infer-dims=3;320;448

18

Thank you for your answer
Problem solved, in network-mode=2 (fp16)

19

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