setup:• Hardware Platform:Jetson Xavier NX • DeepStream Version: 6.1 • JetPack Version: 5.0.1 DP • TensorRT Version: 8.4.0.11 • Issue Type( questions)
Hi,https://github.com/marcoslucianops/DeepStream-Yolo to run yolo-nas with deepstream and python bindings. I run Yolo-nas on coco weights, and everything works fine. When I convert the file.pth to file.onnx I do not use the flag –
I attached the configuration files:config_infer_primary_yolonas.txt (576 Bytes)deepstream_app_config.txt (860 Bytes)labels2.txt (30 Bytes)
what you mean about whole log?
Using winsys: x11
0:00:07.116725955 6603 0x162b150 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/DeepStream-Yolo/Gazbo_Nas.onnx_b1_gpu0_fp32.engine
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT input 3x640x640
1 OUTPUT kFLOAT output 8400x6
0:00:07.174871448 6603 0x162b150 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/DeepStream-Yolo/Gazbo_Nas.onnx_b1_gpu0_fp32.engine
0:00:07.184229479 6603 0x162b150 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/DeepStream-Yolo/config_infer_primary_yolonas.txt sucessfully
0:00:07.187108434 6603 0x162b150 WARN basesrc gstbasesrc.c:3600:gst_base_src_start_complete:<source> pad not activated yet
0:00:07.188430855 6603 0x162b150 WARN basesrc gstbasesrc.c:3600:gst_base_src_start_complete:<source> pad not activated yet
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
0:00:07.212219825 6603 0x162a5e0 WARN qtdemux qtdemux.c:3250:qtdemux_parse_trex:<qtdemux0> failed to find fragment defaults for stream 1
Opening in BLOCKING MODE
0:00:07.344578127 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:4477:gst_v4l2_object_probe_caps:<nvv4l2decoder0:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:07.344710449 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
0:00:07.344817842 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
0:00:07.344895508 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
NvMMLiteOpen : Block : BlockType = 261
NVMEDIA: Reading vendor.tegra.display-size : status: 6
NvMMLiteBlockCreate : Block : BlockType = 261
0:00:07.454657434 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:4477:gst_v4l2_object_probe_caps:<nvv4l2decoder0:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:07.454782620 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
0:00:07.454876189 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
0:00:07.454982143 6603 0xfffe8c07eb00 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0xfffe880166e0 Failed to determine interlace mode
** INFO: <bus_callback:180>: Pipeline running
0:00:07.465235771 6603 0xfffe8c07eb00 WARN v4l2videodec gstv4l2videodec.c:1779:gst_v4l2_video_dec_decide_allocation:<nvv4l2decoder0> Duration invalid, not setting latency
0:00:07.465693378 6603 0xfffe8c07eb00 WARN v4l2bufferpool gstv4l2bufferpool.c:1049:gst_v4l2_buffer_pool_start:<nvv4l2decoder0:pool:src> Uncertain or not enough buffers, enabling copy threshold
0:00:07.469246744 6603 0xfffe84010aa0 WARN v4l2bufferpool gstv4l2bufferpool.c:1499:gst_v4l2_buffer_pool_dqbuf:<nvv4l2decoder0:pool:src> Driver should never set v4l2_buffer.field to ANY
**PERF: 21.01 (20.95)
**PERF: 21.05 (20.98)
**PERF: 21.04 (20.99)
**PERF: 21.04 (20.99)
** INFO: <bus_callback:217>: Received EOS. Exiting ...
Quitting
0:00:29.723298654 6603 0x162b150 ERROR GST_BUS gstbus.c:1066:gst_bus_remove_watch:<bus1> no bus watch was present
App run successful
fanzh
June 5, 2023, 12:41pm
5
you can add log in NvDsInferParseYoloE to check if it is because the inference output score is low.
fanzh:
vDsIn
thank you for reply how can I do this?
fanzh
June 5, 2023, 1:21pm
7
I add to the code:
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
fanzh
June 5, 2023, 2:38pm
10
yes, will this line code be executed line ?
thank you for your patience, I am not so expert in cpp when I try to compile I get this message:
sudo CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
make: Entering directory '/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo'
g++ -c -o nvdsparsebbox_Yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-11.4/include nvdsparsebbox_Yolo.cpp
g++ -o libnvdsinfer_custom_impl_Yolo.so utils.o yolo.o nvdsinfer_yolo_engine.o nvdsinitinputlayers_Yolo.o nvdsparsebbox_Yolo.o yoloPlugins.o layers/convolutional_layer.o layers/pooling_layer.o layers/reorg_layer.o layers/batchnorm_layer.o layers/activation_layer.o layers/channels_layer.o layers/sam_layer.o layers/deconvolutional_layer.o layers/route_layer.o layers/shortcut_layer.o layers/upsample_layer.o layers/implicit_layer.o yoloForward_v2.o yoloForward.o yoloForward_nc.o nvdsparsebbox_Yolo_cuda.o -shared -Wl,--start-group -lnvinfer_plugin -lnvinfer -lnvparsers -L/usr/local/cuda-11.4/lib64 -lcudart -lcublas -lstdc++fs -Wl,--end-group
make: Leaving directory '/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo'
and again I dont say any thing printed on the screen
I apologize for the first time I did not add ‘count’ in the right line you right now I see the printed message
how I can fix this problem?
fanzh
June 6, 2023, 7:04am
14
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
please read the doc to understand the meaning of nvinfer parameters, and ensure the settings are correct.
system
July 4, 2023, 2:14am
16
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.
