Deepstream Yolo output is not generating

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

Hardware Platform: Tesla T4 GPU
DeepStream Version: 6.1.1
TensorRT Version: 8.4
NVIDIA GPU Driver Version: 525.60.11
I am using marcoslucianops/DeepStream-Yolo: NVIDIA DeepStream SDK 6.1.1 / 6.1 / 6.0.1 / 6.0 configuration for YOLO models (github.com) git repo.
I have followed all the steps mentioned in the link. I am using Yolov7 wts and cfg. Still output video is not generating and output is as shown below.
**PERF: FPS 0 (Avg)
**PERF: 0.00 (0.00)
** INFO: <bus_callback:194>: Pipeline ready

**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)

Hardware requirements are:
root@e2e-96-190:~# nvidia-smi
Thu Jan 5 17:05:56 2023
±----------------------------------------------------------------------------+
| NVIDIA-SMI 525.60.11 Driver Version: 525.60.11 CUDA Version: 12.0 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Tesla T4 Off | 00000000:01:01.0 Off | 0 |
| N/A 40C P0 27W / 70W | 837MiB / 15360MiB | 0% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1931 G /usr/lib/xorg/Xorg 4MiB |
| 0 N/A N/A 60058 C deepstream-app 828MiB |
±----------------------------------------------------------------------------+
root@e2e-96-190:~#

3
  1. did you modify code and configuration file? if yes, please share the diff?
  2. could share the whole terminal logs?
4

I have not modified code And I have modified configuration file as per documentation. Below I am attaching files for reference.

root@e2e-96-190:/opt/nvidia/deepstream/deepstream-6.1/DeepStream-Yolo# deepstream-app -c deepstream_app_config.txt
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
Deserialize yoloLayer plugin: yolo
0:00:04.631752672 16841 0x7fac54001f90 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/DeepStream-Yolo/model_b1_gpu0_fp32.engine
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 5
0 INPUT kFLOAT data 3x640x640
1 OUTPUT kFLOAT num_detections 1
2 OUTPUT kFLOAT detection_boxes 25200x4
3 OUTPUT kFLOAT detection_scores 25200
4 OUTPUT kFLOAT detection_classes 25200

0:00:04.681207789 16841 0x7fac54001f90 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1841> [UID = 1]: Backend has maxBatchSize 1 whereas 5 has been requested
0:00:04.681264255 16841 0x7fac54001f90 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2018> [UID = 1]: deserialized backend context :/opt/nvidia/deepstream/deepstream-6.1/DeepStream-Yolo/model_b1_gpu0_fp32.engine failed to match config params, trying rebuild
0:00:04.734305662 16841 0x7fac54001f90 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.

Loading pre-trained weights
Loading weights of yolov7 complete
Total weights read: 37669853
Building YOLO network

    Layer                         Input Shape         Output Shape        WeightPtr

(0) conv_silu [3, 640, 640] [32, 640, 640] 992
(1) conv_silu [32, 640, 640] [64, 320, 320] 19680
(2) conv_silu [64, 320, 320] [64, 320, 320] 56800
(3) conv_silu [64, 320, 320] [128, 160, 160] 131040
(4) conv_silu [128, 160, 160] [64, 160, 160] 139488
(5) route: 3 - [128, 160, 160] -
(6) conv_silu [128, 160, 160] [64, 160, 160] 147936
(7) conv_silu [64, 160, 160] [64, 160, 160] 185056
(8) conv_silu [64, 160, 160] [64, 160, 160] 222176
(9) conv_silu [64, 160, 160] [64, 160, 160] 259296
(10) conv_silu [64, 160, 160] [64, 160, 160] 296416
(11) route: 10, 8, 6, 4 - [256, 160, 160] -
(12) conv_silu [256, 160, 160] [256, 160, 160] 362976
(13) maxpool [256, 160, 160] [256, 80, 80] -
(14) conv_silu [256, 80, 80] [128, 80, 80] 396256
(15) route: 12 - [256, 160, 160] -
(16) conv_silu [256, 160, 160] [128, 160, 160] 429536
(17) conv_silu [128, 160, 160] [128, 80, 80] 577504
(18) route: 17, 14 - [256, 80, 80] -
(19) conv_silu [256, 80, 80] [128, 80, 80] 610784
(20) route: 18 - [256, 80, 80] -
(21) conv_silu [256, 80, 80] [128, 80, 80] 644064
(22) conv_silu [128, 80, 80] [128, 80, 80] 792032
(23) conv_silu [128, 80, 80] [128, 80, 80] 940000
(24) conv_silu [128, 80, 80] [128, 80, 80] 1087968
(25) conv_silu [128, 80, 80] [128, 80, 80] 1235936
(26) route: 25, 23, 21, 19 - [512, 80, 80] -
(27) conv_silu [512, 80, 80] [512, 80, 80] 1500128
(28) maxpool [512, 80, 80] [512, 40, 40] -
(29) conv_silu [512, 40, 40] [256, 40, 40] 1632224
(30) route: 27 - [512, 80, 80] -
(31) conv_silu [512, 80, 80] [256, 80, 80] 1764320
(32) conv_silu [256, 80, 80] [256, 40, 40] 2355168
(33) route: 32, 29 - [512, 40, 40] -
(34) conv_silu [512, 40, 40] [256, 40, 40] 2487264
(35) route: 33 - [512, 40, 40] -
(36) conv_silu [512, 40, 40] [256, 40, 40] 2619360
(37) conv_silu [256, 40, 40] [256, 40, 40] 3210208
(38) conv_silu [256, 40, 40] [256, 40, 40] 3801056
(39) conv_silu [256, 40, 40] [256, 40, 40] 4391904
(40) conv_silu [256, 40, 40] [256, 40, 40] 4982752
(41) route: 40, 38, 36, 34 - [1024, 40, 40] -
(42) conv_silu [1024, 40, 40] [1024, 40, 40] 6035424
(43) maxpool [1024, 40, 40] [1024, 20, 20] -
(44) conv_silu [1024, 20, 20] [512, 20, 20] 6561760
(45) route: 42 - [1024, 40, 40] -
(46) conv_silu [1024, 40, 40] [512, 40, 40] 7088096
(47) conv_silu [512, 40, 40] [512, 20, 20] 9449440
(48) route: 47, 44 - [1024, 20, 20] -
(49) conv_silu [1024, 20, 20] [256, 20, 20] 9712608
(50) route: 48 - [1024, 20, 20] -
(51) conv_silu [1024, 20, 20] [256, 20, 20] 9975776
(52) conv_silu [256, 20, 20] [256, 20, 20] 10566624
(53) conv_silu [256, 20, 20] [256, 20, 20] 11157472
(54) conv_silu [256, 20, 20] [256, 20, 20] 11748320
(55) conv_silu [256, 20, 20] [256, 20, 20] 12339168
(56) route: 55, 53, 51, 49 - [1024, 20, 20] -
(57) conv_silu [1024, 20, 20] [1024, 20, 20] 13391840
(58) conv_silu [1024, 20, 20] [512, 20, 20] 13918176
(59) route: 57 - [1024, 20, 20] -
(60) conv_silu [1024, 20, 20] [512, 20, 20] 14444512
(61) conv_silu [512, 20, 20] [512, 20, 20] 16805856
(62) conv_silu [512, 20, 20] [512, 20, 20] 17070048
(63) maxpool [512, 20, 20] [512, 20, 20] -
(64) route: 62 - [512, 20, 20] -
(65) maxpool [512, 20, 20] [512, 20, 20] -
(66) route: 62 - [512, 20, 20] -
(67) maxpool [512, 20, 20] [512, 20, 20] -
(68) route: 62, 63, 65, 67 - [2048, 20, 20] -
(69) conv_silu [2048, 20, 20] [512, 20, 20] 18120672
(70) conv_silu [512, 20, 20] [512, 20, 20] 20482016
(71) route: 70, 58 - [1024, 20, 20] -
(72) conv_silu [1024, 20, 20] [512, 20, 20] 21008352
(73) conv_silu [512, 20, 20] [256, 20, 20] 21140448
(74) upsample [256, 20, 20] [256, 40, 40] -
(75) route: 42 - [1024, 40, 40] -
(76) conv_silu [1024, 40, 40] [256, 40, 40] 21403616
(77) route: 76, 74 - [512, 40, 40] -
(78) conv_silu [512, 40, 40] [256, 40, 40] 21535712
(79) route: 77 - [512, 40, 40] -
(80) conv_silu [512, 40, 40] [256, 40, 40] 21667808
(81) conv_silu [256, 40, 40] [128, 40, 40] 21963232
(82) conv_silu [128, 40, 40] [128, 40, 40] 22111200
(83) conv_silu [128, 40, 40] [128, 40, 40] 22259168
(84) conv_silu [128, 40, 40] [128, 40, 40] 22407136
(85) route: 84, 83, 82, 81, 80, 78 - [1024, 40, 40] -
(86) conv_silu [1024, 40, 40] [256, 40, 40] 22670304
(87) conv_silu [256, 40, 40] [128, 40, 40] 22703584
(88) upsample [128, 40, 40] [128, 80, 80] -
(89) route: 27 - [512, 80, 80] -
(90) conv_silu [512, 80, 80] [128, 80, 80] 22769632
(91) route: 90, 88 - [256, 80, 80] -
(92) conv_silu [256, 80, 80] [128, 80, 80] 22802912
(93) route: 91 - [256, 80, 80] -
(94) conv_silu [256, 80, 80] [128, 80, 80] 22836192
(95) conv_silu [128, 80, 80] [64, 80, 80] 22910176
(96) conv_silu [64, 80, 80] [64, 80, 80] 22947296
(97) conv_silu [64, 80, 80] [64, 80, 80] 22984416
(98) conv_silu [64, 80, 80] [64, 80, 80] 23021536
(99) route: 98, 97, 96, 95, 94, 92 - [512, 80, 80] -
(100) conv_silu [512, 80, 80] [128, 80, 80] 23087584
(101) maxpool [128, 80, 80] [128, 40, 40] -
(102) conv_silu [128, 40, 40] [128, 40, 40] 23104480
(103) route: 100 - [128, 80, 80] -
(104) conv_silu [128, 80, 80] [128, 80, 80] 23121376
(105) conv_silu [128, 80, 80] [128, 40, 40] 23269344
(106) route: 105, 102, 86 - [512, 40, 40] -
(107) conv_silu [512, 40, 40] [256, 40, 40] 23401440
(108) route: 106 - [512, 40, 40] -
(109) conv_silu [512, 40, 40] [256, 40, 40] 23533536
(110) conv_silu [256, 40, 40] [128, 40, 40] 23828960
(111) conv_silu [128, 40, 40] [128, 40, 40] 23976928
(112) conv_silu [128, 40, 40] [128, 40, 40] 24124896
(113) conv_silu [128, 40, 40] [128, 40, 40] 24272864
(114) route: 113, 112, 111, 110, 109, 107- [1024, 40, 40] -
(115) conv_silu [1024, 40, 40] [256, 40, 40] 24536032
(116) maxpool [256, 40, 40] [256, 20, 20] -
(117) conv_silu [256, 20, 20] [256, 20, 20] 24602592
(118) route: 115 - [256, 40, 40] -
(119) conv_silu [256, 40, 40] [256, 40, 40] 24669152
(120) conv_silu [256, 40, 40] [256, 20, 20] 25260000
(121) route: 120, 117, 72 - [1024, 20, 20] -
(122) conv_silu [1024, 20, 20] [512, 20, 20] 25786336
(123) route: 121 - [1024, 20, 20] -
(124) conv_silu [1024, 20, 20] [512, 20, 20] 26312672
(125) conv_silu [512, 20, 20] [256, 20, 20] 27493344
(126) conv_silu [256, 20, 20] [256, 20, 20] 28084192
(127) conv_silu [256, 20, 20] [256, 20, 20] 28675040
(128) conv_silu [256, 20, 20] [256, 20, 20] 29265888
(129) route: 128, 127, 126, 125, 124, 122- [2048, 20, 20] -
(130) conv_silu [2048, 20, 20] [512, 20, 20] 30316512
(131) route: 100 - [128, 80, 80] -
(132) conv_linear [128, 80, 80] [256, 80, 80] 30350304
(133) route: 131 - [128, 80, 80] -
(134) conv_linear [128, 80, 80] [256, 80, 80] 30646240
(135) shortcut_add_silu: 132 [256, 80, 80] [256, 80, 80] -
(136) route: 115 - [256, 40, 40] -
(137) conv_linear [256, 40, 40] [512, 40, 40] 30779360
(138) route: 136 - [256, 40, 40] -
(139) conv_linear [256, 40, 40] [512, 40, 40] 31961056
(140) shortcut_add_silu: 137 [512, 40, 40] [512, 40, 40] -
(141) route: 130 - [512, 20, 20] -
(142) conv_linear [512, 20, 20] [1024, 20, 20] 32489440
(143) route: 141 - [512, 20, 20] -
(144) conv_linear [512, 20, 20] [1024, 20, 20] 37212128
(145) shortcut_add_silu: 142 [1024, 20, 20] [1024, 20, 20] -
(146) route: 135 - [256, 80, 80] -
(147) conv_logistic [256, 80, 80] [255, 80, 80] 37277663
(148) yolo [255, 80, 80] - -
(149) route: 140 - [512, 40, 40] -
(150) conv_logistic [512, 40, 40] [255, 40, 40] 37408478
(151) yolo [255, 40, 40] - -
(152) route: 145 - [1024, 20, 20] -
(153) conv_logistic [1024, 20, 20] [255, 20, 20] 37669853
(154) yolo [255, 20, 20] - -

Output YOLO blob names:
yolo_149
yolo_152
yolo_155

Total number of YOLO layers: 399

Building YOLO network complete
Building the TensorRT Engine

NOTE: letter_box is set in cfg file, make sure to set maintain-aspect-ratio=1 in config_infer file to get better accuracy

Building complete

0:01:30.113377212 16841 0x7fac54001f90 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1955> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.1/DeepStream-Yolo/model_b5_gpu0_fp32.engine successfully
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 5
0 INPUT kFLOAT data 3x640x640
1 OUTPUT kFLOAT num_detections 1
2 OUTPUT kFLOAT detection_boxes 25200x4
3 OUTPUT kFLOAT detection_scores 25200
4 OUTPUT kFLOAT detection_classes 25200

0:01:30.213986928 16841 0x7fac54001f90 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-6.1/DeepStream-Yolo/config_infer_primary_yoloV7.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

    p: Pause
    r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

**PERF: FPS 0 (Avg)
**PERF: 0.00 (0.00)
** INFO: <bus_callback:194>: Pipeline ready

**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
**PERF: 0.00 (0.00)
PERF: 0.00 (0.00)
^C ERROR: <_intr_handler:140>: User Interrupted…

Deepstream-yolo-folder-content
Deepstream-yolo-folder-content1801×140 58.8 KB

config_infer_primary_yoloV7.txt (626 Bytes)
deepstream_app_config.txt (1.2 KB)

5

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

I can 't reproduce this issue on nvcr.io/nvidia/deepstream:6.1.1-triton, the only one difference with your configuration is
uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
here is the log:log.txt (16.9 KB)

7

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