Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
Jetson AGX Orin
• DeepStream Version
6.3
• JetPack Version (valid for Jetson only)
5.1.2
• Issue Type( questions, new requirements, bugs)
question
Hi, I have yolov7 tiny model and I convert it to onnx model work with deepstream using Deepstream-Yolo package. When I tried to convert onnx to engine file with this package I am getting errors as follows:
WARNING: [TRT]: Unknown embedded device detected. Using 59659MiB as the allocation cap for memory on embedded devices.
Building complete
0:05:32.596015447 32657 0xaaaacd3fcea0 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2034> [UID = 1]: serialize cuda engine to file: /home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/model_b1_gpu0_fp32.engine successfully
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: [Implicit Engine Info]: layers num: 4
0 INPUT kFLOAT input 3x640x640
1 OUTPUT kFLOAT boxes 25200x4
2 OUTPUT kFLOAT scores 25200x1
3 OUTPUT kFLOAT classes 25200x1
nvbufsurface: Failed to create EGLImage.
0:05:32.921130946 32657 0xaaaacd3fcea0 WARN nvinfer gstnvinfer.cpp:994:gst_nvinfer_start:<primary_gie> error: Failed to set buffer pool to active
** ERROR: <main:716>: Failed to set pipeline to PAUSED
Quitting
nvstreammux: Successfully handled EOS for source_id=0
ERROR from primary_gie: Failed to set buffer pool to active
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(994): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
App run failed
I have done many search about the problems, most of them was about connecting orin to monitor, now I cannot access monitor to connect orin and not sure that is related to monitor.
If it is, is it a bug? Because cannot use it with monitor all the time.
Also here are1 the files to run deepstream app.
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[tiled-display]
enable=1
rows=1
columns=1
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0
[source0]
enable=1
type=3
uri=file:///home/ubuntu/Documents/img2vid_v2.mp4
num-sources=1
gpu-id=0
cudadec-memtype=0
[sink0]
enable=1
type=2
sync=0
gpu-id=0
nvbuf-memory-type=0
[sink1]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=3
#1=mp4 2=mkv
container=2
#1=h264 2=h265
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=1
#iframeinterval=10
bitrate=6000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
profile=0
output-file=video.mkv
source-id=0
[osd]
enable=1
gpu-id=0
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0
[streammux]
gpu-id=0
live-source=0
batch-size=1
batched-push-timeout=40000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/config_infer_primary_yoloV7_deneme.txt
[tests]
file-loop=0
also:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
#custom-network-config=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/transfer_learning2.cfg
onnx-file=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/transfer_learning2.onnx
model-engine-file=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/transfer_learning2.engine
labelfile-path=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/labels_deneme.txt
batch-size=1
network-mode=0
num-detected-classes=7
interval=0
gie-unique-id=1
process-mode=1
network-type=0
cluster-mode=2
maintain-aspect-ratio=1
symmetric-padding=1
#workspace-size=2000
parse-bbox-func-name=NvDsInferParseYolo
#parse-bbox-func-name=NvDsInferParseYoloCuda
custom-lib-path=/home/ubuntu/Documents/Barkod_Gap/utils/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet
[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=300
I have tried closing sinks, opening them, changing source0 type 2-3 but nothing solved the issue. Also when I change the xorg settings my issue changes as follows:
Opening in BLOCKING MODE
** ERROR: <main:716>: Failed to set pipeline to PAUSED
Quitting
nvstreammux: Successfully handled EOS for source_id=0
ERROR from sink_sub_bin_sink1: GStreamer error: state change failed and some element failed to post a proper error message with the reason for the failure.
Debug info: gstbasesink.c(5367): gst_base_sink_change_state (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstNv3dSink:sink_sub_bin_sink1:
Failed to start
App run failed
How can I solve that issue?
Have a nice day.