Open zardadi opened 1 year ago
Can you send me the full log from the terminal and your config_infer_primary_yoloV5.txt
file?
And the `deepstream_app_config.txt``file.
@marcoslucianops , thanks for your reply.
I run GST_DEBUG=2 deepstream-app -c deepstream_app_config.txt
to get more details fo the error.
Below is the full log from the terminal.
Opening in BLOCKING MODE
0:00:00.100849936 107195 0xaaaace331aa0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xaaaace01c180 Failed to determine interlace mode
0:00:00.100905713 107195 0xaaaace331aa0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xaaaace01c180 Failed to determine interlace mode
0:00:00.100928465 107195 0xaaaace331aa0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xaaaace01c180 Failed to determine interlace mode
0:00:00.100945777 107195 0xaaaace331aa0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xaaaace01c180 Failed to determine interlace mode
0:00:00.101010642 107195 0xaaaace331aa0 WARN v4l2 gstv4l2object.c:4512:gst_v4l2_object_probe_caps:<sink_sub_bin_encoder1:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:02.746773501 107195 0xaaaace331aa0 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/home/DeepStream-Yolo/yolov5lv6.1_img640_class9_fp16.engine
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: 2
0 INPUT kFLOAT input 3x640x640
1 OUTPUT kFLOAT output 25200x6
0:00:02.916267621 107195 0xaaaace331aa0 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model:/home/DeepStream-Yolo/yolov5lv6.1_img640_class9_fp16.engine
0:00:02.945555245 107195 0xaaaace331aa0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/home/DeepStream-Yolo/config_infer_primary_yoloV5.txt sucessfully
0:00:02.946657983 107195 0xaaaace331aa0 WARN basesrc gstbasesrc.c:3600:gst_base_src_start_complete:<source> pad not activated yet
0:00:02.947216872 107195 0xaaaace331aa0 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
** INFO: <bus_callback:239>: Pipeline ready
0:00:02.951004999 107195 0xaaaaeb679b00 WARN qtdemux qtdemux_types.c:239:qtdemux_type_get: unknown QuickTime node type pasp
0:00:02.951092425 107195 0xaaaaeb679b00 WARN qtdemux qtdemux.c:3250:qtdemux_parse_trex:<qtdemux0> failed to find fragment defaults for stream 1
Opening in BLOCKING MODE
0:00:02.983389091 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:4512:gst_v4l2_object_probe_caps:<nvv4l2decoder0:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:02.983432996 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:02.983466724 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:02.983487749 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:02.983509829 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
NvMMLiteOpen : Block : BlockType = 261
NVMEDIA: Reading vendor.tegra.display-size : status: 6
NvMMLiteBlockCreate : Block : BlockType = 261
0:00:03.088406488 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:4512:gst_v4l2_object_probe_caps:<nvv4l2decoder0:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:03.088441049 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:03.088466777 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:03.088481145 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
0:00:03.088494618 107195 0xffff100519e0 WARN v4l2 gstv4l2object.c:2398:gst_v4l2_object_add_interlace_mode:0xffff08015450 Failed to determine interlace mode
** INFO: <bus_callback:225>: Pipeline running
0:00:03.090514523 107195 0xffff100519e0 WARN v4l2videodec gstv4l2videodec.c:1880:gst_v4l2_video_dec_decide_allocation:<nvv4l2decoder0> Duration invalid, not setting latency
0:00:03.090726015 107195 0xffff100519e0 WARN v4l2bufferpool gstv4l2bufferpool.c:1114:gst_v4l2_buffer_pool_start:<nvv4l2decoder0:pool:src> Uncertain or not enough buffers, enabling copy threshold
NvMMLiteOpen : Block : BlockType = 4
===== NVMEDIA: NVENC =====
NvMMLiteBlockCreate : Block : BlockType = 4
0:00:03.121188570 107195 0xaaaace3029e0 WARN v4l2bufferpool gstv4l2bufferpool.c:1114:gst_v4l2_buffer_pool_start:<sink_sub_bin_encoder1:pool:src> Uncertain or not enough buffers, enabling copy threshold
0:00:03.123351326 107195 0xffff14021d80 WARN v4l2bufferpool gstv4l2bufferpool.c:1565:gst_v4l2_buffer_pool_dqbuf:<nvv4l2decoder0:pool:src> Driver should never set v4l2_buffer.field to ANY
Segmentation fault
config_infer_primary_yoloV5.txt:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
onnx-file=yolov5lv6.1_img640_class9.onnx
model-engine-file=yolov5lv6.1_img640_class9_fp16.engine
#int8-calib-file=calib.table
labelfile-path=labels.txt
batch-size=1 # number of frames for inference
network-mode=2 # 0:fp32 1:int8 2:fp16
num-detected-classes=9
interval=0
gie-unique-id=1
process-mode=1 # 1:primary 2:secondary
network-type=0 # 0:detector 1: classifier
cluster-mode=2 # 2: NMS
maintain-aspect-ratio=1
symmetric-padding=1
#force-implicit-batch-dim=1
#workspace-size=1000
parse-bbox-func-name=NvDsInferParseYolo
#parse-bbox-func-name=NvDsInferParseYoloCuda
custom-lib-path=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
deepstream_app_config.txt:
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[tiled-display]
enable=0
rows=1
columns=1
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0
[source0]
enable=1
type=3
uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4
num-sources=1
gpu-id=0
cudadec-memtype=0
[sink0]
enable=0
type=2
sync=0
gpu-id=0
nvbuf-memory-type=0
[sink1]
enable=1
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=4000000
output-file=output_benchmark.mp4
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=config_infer_primary_yoloV5.txt
[tests]
file-loop=0
You are using the old files (the output layers are wrong). Please use the new files from this repo and regenerate the engine file (delete the engine file to recreate it).
Thanks for the prompt reply. I cloned the repo one week ago on Jetosn Orin. I will clone it again and try to build the engine again if that helps. Do I need to regenerate the onnx file using the export_yoloV5.py
file from DeepStream-Yolo/utils
?
Do I need to regenerate the onnx file using the
export_yoloV5.py
file fromDeepStream-Yolo/utils
?
Yes
Generating new onnx files solved the issue. I didn't need to update the repo on the Jetson as it was the lastest update. I needed to regenerate the onnx files as they were generated from the older commit of this repo. Thanks for your help @marcoslucianops
Trying to run yolov5 engine file on Jetson, orin I am running DS 6.2. I passed Onnx file in config file. Deepstream could generate engine file successfully, but deepstream can’t run the pipeline to start inference and got the following error:
Environment
TensorRT Version: 8.5.2-1+cuda11.4 GPU Type: Jetson Orin Nvidia Driver Version: Jetson Orin CUDA Version: 11.4 CUDNN Version: 8.6.0.166-1+cuda11.4 arm64 Operating System + Version: Ubuntu 20.04 Python Version (if applicable): NA TensorFlow Version (if applicable): NA PyTorch Version (if applicable): NA Baremetal or Container (if container which image + tag): Baremetal
Steps To Reproduce $ Deepstream-app -c deepstream-app-config.txt