deepstream-plugins make failed

How to get detection results for image?

kSAVE_DETECTIONS = true

Found

About performance -

batch_size 4 needs 84-120ms on Jetson-TX2

Also can I know if I can use video as input? and get output stream the way it is in deepstream SDK?

Still Getting this error after trying out your steps

TRT-yolo-app: yolov2.cpp:40: YoloV2::YoloV2(uint): Assertion `m_OutputIndex != -1' failed.

and while doing make in gstyoloplugin getting this error:

gstyoloplugin.h:36:25: fatal error: gst-nvquery.h: No such file or directory

I think it’s because of some missing gstreamer installation. Did you install plugins mentioned in Readme on Git repo ?

Facing this error while compiling the libgstyolo in Jetson-TX1, with deep stream-2.0 for running the TRT-yolo app in the Jetson TX-1 device


/usr/bin/ld: skipping incompatible /usr/local/deepstream/libgstnvquery.so when searching for -lgstnvquery
/usr/bin/ld: cannot find -lgstnvquery
/usr/bin/ld: skipping incompatible /usr/local/deepstream/libgstnvdsmeta.so when searching for -lgstnvdsmeta
/usr/bin/ld: cannot find -lgstnvdsmeta
collect2: error: ld returned 1 exit status
Makefile:64: recipe for target ‘libgstnvyolo.so’ failed
make: *** [libgstnvyolo.so] Error 1

Facing this error while compiling the libgstyolo in Jetson-TX1, with deep stream-2.0 for running the TRT-yolo app in the Jetson TX-1 device


/usr/bin/ld: skipping incompatible /usr/local/deepstream/libgstnvquery.so when searching for -lgstnvquery
/usr/bin/ld: cannot find -lgstnvquery
/usr/bin/ld: skipping incompatible /usr/local/deepstream/libgstnvdsmeta.so when searching for -lgstnvdsmeta
/usr/bin/ld: cannot find -lgstnvdsmeta
collect2: error: ld returned 1 exit status
Makefile:64: recipe for target ‘libgstnvyolo.so’ failed
make: *** [libgstnvyolo.so] Error 1

@subhasis.chakraborty
Which tensorRT version are you using ?
Check your TRT-yolo app is building individually.

Deepstream 2.0 for Jetson is not released. There is just Deepstream 1.5. That might be causing the issues.
Only Xavier boards right now support the Deepstream 2.0.

I am using Tensorrt-4.0 as it is supported with Jetpack 3.3, but if i build TRT-yolo app indiviually then there is no detections, so i was trying to build gst-yoloplugin and i ran into this error.

@subhasis.chakraborty
There will be detections in the detection folder.
Check that kSAVE_DETECTIONS = true is present in network_config
The error with the Deepstream states that the .so files are not found. I think the path in Makefile.config should be proper.

@prince15046

No, the deep-stream 2.0 instalation path ie. /usr/local/deepstream/ in given in Makefile.config and that path contains all the .so files still i’m getting this error. Can you please specify which version of deepstream are you using?

Hi,

Due to DeepStream dependency, only standalone application is available for Jetson user.
Thanks

Hi,

Please noticed that only standalone TRT app is available for Jetson user.
You can find this information on our note:
https://github.com/vat-nvidia/deepstream-plugins#note

Thanks.

Hi Prince, how did you sorted this, whatsup with the configuration part? what changes has to be done?

I believe its the yolo.cfg right?

Sorted, check the cfg, its a webpage!

I’m also have this question.

trt-yolo-app
File does not exist : sources/lib/models/yolov3-tiny-kFLOAT-batch1.engine
Unable to find cached TensorRT engine for network : yolov3-tiny precision : kFLOAT and batch size :1
Creating a new TensorRT Engine
Loading pre-trained weights…
Loading complete!
Total Number of weights read : 8858734
layer inp_size out_size weightPtr
(1) conv-bn-leaky 3 x 416 x 416 16 x 416 x 416 496
(2) maxpool 16 x 416 x 416 16 x 208 x 208 496
(3) conv-bn-leaky 16 x 208 x 208 32 x 208 x 208 5232
(4) maxpool 32 x 208 x 208 32 x 104 x 104 5232
(5) conv-bn-leaky 32 x 104 x 104 64 x 104 x 104 23920
(6) maxpool 64 x 104 x 104 64 x 52 x 52 23920
(7) conv-bn-leaky 64 x 52 x 52 128 x 52 x 52 98160
(8) maxpool 128 x 52 x 52 128 x 26 x 26 98160
(9) conv-bn-leaky 128 x 26 x 26 256 x 26 x 26 394096
(10) maxpool 256 x 26 x 26 256 x 13 x 13 394096
(11) conv-bn-leaky 256 x 13 x 13 512 x 13 x 13 1575792
(12) maxpool 512 x 13 x 13 512 x 13 x 13 1575792
(13) conv-bn-leaky 512 x 13 x 13 1024 x 13 x 13 6298480
(14) conv-bn-leaky 1024 x 13 x 13 256 x 13 x 13 6561648
(15) conv-bn-leaky 256 x 13 x 13 512 x 13 x 13 7743344
(16) conv-linear 512 x 13 x 13 21 x 13 x 13 7754117
(17) yolo 21 x 13 x 13 21 x 13 x 13 7754117
(18) route - 256 x 13 x 13 7754117
(19) conv-bn-leaky 256 x 13 x 13 128 x 13 x 13 7787397
(20) upsample 128 x 13 x 13 128 x 26 x 26 -
(21) route - 384 x 26 x 26 7787397
(22) conv-bn-leaky 384 x 26 x 26 256 x 26 x 26 8673157
(23) conv-linear 256 x 26 x 26 21 x 26 x 26 8678554
(24) yolo 21 x 26 x 26 21 x 26 x 26 8678554
Number of unused weights left : 180180
trt-yolo-app: yolo.cpp:397: void Yolo::createYOLOEngine(int, std::__cxx11::string, std::__cxx11::string, std::__cxx11::string, nvinfer1::DataType, Int8EntropyCalibrator*): Assertion `0’ failed.
Aborted (core dumped)

How did you solve this problem? I’m on TX2 ,using command :trt-yolo-app
(GitHub - NVIDIA-AI-IOT/deepstream_reference_apps at 7f27f22d674c64f4859dd1da896a43e35b0b9063)

it’s OK now ,thanks you question history!!!