Hello!
I have just started to learn deep stream. because I have a problem, please help me:
dstest1_pgie_config.txt:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-file=../../../../samples/models/Primary_Detector/resnet10.caffemodel
proto-file=../../../../samples/models/Primary_Detector/resnet10.prototxt
model-engine-file=../../../../samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
labelfile-path=../../../../samples/models/Primary_Detector/labels.txt
int8-calib-file=../../../../samples/models/Primary_Detector/cal_trt.bin
force-implicit-batch-dim=1
batch-size=1
network-mode=1
num-detected-classes=4
interval=0
gie-unique-id=1
output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid
#scaling-filter=0
#scaling-compute-hw=0
cluster-mode=2
[class-attrs-all]
pre-cluster-threshold=0.2
topk=20
nms-iou-threshold=0.5
After I execute the following command:
sudo ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
Output:
pp:2113:gst_nvinfer_submit_input_buffer:<secondary1-nvinference-engine> error: streaming stopped, reason not-negotiated (-4)
ERROR from element secondary3-nvinference-engine: Internal data stream error.
Error details: gstnvinfer.cpp(2113): gst_nvinfer_submit_input_buffer (): /GstPipeline:dstest2-pipeline/GstNvInfer:secondary3-nvinference-engine:
streaming stopped, reason not-negotiated (-4)
Frame Number = 1 Number of objects = 0 Vehicle Count = 0 Person Count = 0
Returned, stopping playback
Frame Number = 2 Number of objects = 0 Vehicle Count = 0 Person Count = 0
Frame Number = 3 Number of objects = 7 Vehicle Count = 5 Person Count = 2
Frame Number = 4 Number of objects = 7 Vehicle Count = 5 Person Count = 2
...
...
So I found the problem on forums, The solution is as follows:
sink = gst_element_factory_make ("nveglglessink", "nvvideo-renderer");
Modified as：
sink = gst_element_factory_make ("fakesink", "nvvideo-renderer");
make and execute:
ubuntu@os:/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-test1$ sudo ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
Now playing: /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars
0:00:01.731719980 9800 0x558b14aefc10 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:01.787689689 9800 0x558b14aefc10 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:01.788619521 9800 0x558b14aefc10 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
Running...
Frame Number = 0 Number of objects = 13 Vehicle Count = 9 Person Count = 4
Frame Number = 1 Number of objects = 11 Vehicle Count = 8 Person Count = 3
Frame Number = 2 Number of objects = 11 Vehicle Count = 7 Person Count = 4
Frame Number = 3 Number of objects = 11 Vehicle Count = 7 Person Count = 4
...
...
...
Frame Number = 1438 Number of objects = 15 Vehicle Count = 14 Person Count = 1
Frame Number = 1439 Number of objects = 14 Vehicle Count = 12 Person Count = 2
Frame Number = 1440 Number of objects = 14 Vehicle Count = 13 Person Count = 1
Frame Number = 1441 Number of objects = 0 Vehicle Count = 0 Person Count = 0
End of stream
Returned, stopping playback
Deleting pipeline
ubuntu@os:/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-test1$
According to my understanding, a video should be displayed after execution, but I haven’t seen the video with cases displayed. Is there a problem? If it is not a problem, where is the output (path)?
Please help me!
yingliu
December 2, 2022, 10:50am
2
You may add “GST_DEBUG=3” before ./deepstream-test-app to display more logs.
Version information:
Gpu model：GeForce RTX3070 Laptop GPU
I added “GST_DEBUG=3” and executed it. I did not get any useful information. Please help me analyze:
ubuntu@os:/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-test1$ sudo GST_DEBUG=3 ./deepstream-test1-app /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
Now playing: /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264
0:00:00.173694910 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173710799 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MJPG
0:00:00.173713657 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173716082 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MJPG
0:00:00.173727867 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173730234 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MPG4
0:00:00.173734945 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173737152 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MPG4
0:00:00.173742755 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173745146 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MPG2
0:00:00.173747138 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173749281 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MPG2
0:00:00.173755372 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173757744 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat H265
0:00:00.173760918 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173763003 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat H265
0:00:00.173767483 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173769758 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat VP90
0:00:00.173772192 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173774786 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat VP90
0:00:00.173778948 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173781881 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat VP80
0:00:00.173786309 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173789372 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat VP80
0:00:00.173794605 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173797539 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat H264
0:00:00.173799837 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.173802851 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat H264
0:00:00.174019420 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:src> Unable to try format: Unknown error -1
0:00:00.174023129 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2937:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:src> Could not probe minimum capture size for pixelformat NM12
0:00:00.174025585 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:3051:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:src> Unable to try format: Unknown error -1
0:00:00.174027886 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2943:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:src> Could not probe maximum capture size for pixelformat NM12
0:00:00.174032465 13690 0x55a407968070 WARN v4l2 gstv4l2object.c:2388:gst_v4l2_object_add_interlace_mode:0x55a406f7ba70 Failed to determine interlace mode
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars
0:00:02.140549450 13690 0x55a407968070 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:02.197578930 13690 0x55a407968070 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:02.198721262 13690 0x55a407968070 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
0:00:02.198908785 13690 0x55a407968070 WARN basesrc gstbasesrc.c:3583:gst_base_src_start_complete:<file-source> pad not activated yet
Running...
0:00:02.309717620 13690 0x55a406f63590 WARN v4l2videodec gstv4l2videodec.c:1685:gst_v4l2_video_dec_decide_allocation:<nvv4l2-decoder> Duration invalid, not setting latency
0:00:02.309744099 13690 0x55a406f63590 WARN v4l2bufferpool gstv4l2bufferpool.c:1065:gst_v4l2_buffer_pool_start:<nvv4l2-decoder:pool:src> Uncertain or not enough buffers, enabling copy threshold
0:00:02.310355289 13690 0x7f6f30003230 WARN v4l2bufferpool gstv4l2bufferpool.c:1512:gst_v4l2_buffer_pool_dqbuf:<nvv4l2-decoder:pool:src> Driver should never set v4l2_buffer.field to ANY
Frame Number = 0 Number of objects = 13 Vehicle Count = 9 Person Count = 4
Frame Number = 1 Number of objects = 11 Vehicle Count = 8 Person Count = 3
Frame Number = 2 Number of objects = 11 Vehicle Count = 7 Person Count = 4
Frame Number = 3 Number of objects = 11 Vehicle Count = 7 Person Count = 4
Frame Number = 4 Number of objects = 11 Vehicle Count = 8 Person Count = 3
Frame Number = 5 Number of objects = 12 Vehicle Count = 8 Person Count = 4
Frame Number = 6 Number of objects = 11 Vehicle Count = 7 Person Count = 4
Frame Number = 7 Number of objects = 11 Vehicle Count = 7 Person Count = 4
...
...
...
Frame Number = 1440 Number of objects = 14 Vehicle Count = 13 Person Count = 1
Frame Number = 1441 Number of objects = 0 Vehicle Count = 0 Person Count = 0
End of stream
Returned, stopping playback
There is no update from you for a period, assuming this is not an issue anymore.
Please refer below guide for installation, your driver and CUDA versions are news than DeepStream 6.0.1 required version, you may follow the guide to re-install.Quickstart Guide — DeepStream 6.0.1 Release documentation (nvidia.com)
Besides, you can also considering install deepstream docker on your laptop: GitHub - NVIDIA/nvidia-docker: Build and run Docker containers leveraging NVIDIA GPUs
system
January 2, 2023, 1:41pm
7
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.