I was trying to run GazeNet model from NVIDIA-AI-IOT repository in docker container nvcr.io/nvidia/deepstream:6.0.1 -devel
Running the command ./deepstream-gaze-app 1 …/…/…/configs/facial_tao/sample_faciallandmarks_config.txt file:///usr/data/faciallandmarks_test.jpg ./gazenet leads to segmentation fault:
root@f08b7b1c9119:/opt/nvidia/deepstream/deepstream-6.0/samples/deepstream_tao_apps/apps/tao_others/deepstream-gaze-app# ./deepstream-gaze-app 2 ../../../configs/facial_tao/sample_faciallandmarks_config.txt file:///usr/data/faciallandmarks_test.jpg ./gazenet
Request sink_0 pad from streammux
Now playing: file:///usr/data/faciallandmarks_test.jpg
Library Opened Successfully
Setting custom lib properties # 1
Adding Prop: config-file : ../../../configs/gaze_tao/sample_gazenet_model_config.txt
Inside Custom Lib : Setting Prop Key=config-file Value=../../../configs/gaze_tao/sample_gazenet_model_config.txt
0:00:01.610298053 5746 0x561895abbc90 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<second-infer-engine1> NvDsInferContext[UID 2]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 2]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/deepstream_tao_apps/models/faciallandmark/faciallandmarks.etlt_b32_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 4
0 INPUT kFLOAT input_face_images 1x80x80 min: 1x1x80x80 opt: 32x1x80x80 Max: 32x1x80x80
1 OUTPUT kFLOAT conv_keypoints_m80 80x80x80 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT softargmax 80x2 min: 0 opt: 0 Max: 0
3 OUTPUT kFLOAT softargmax:1 80 min: 0 opt: 0 Max: 0
ERROR: [TRT]: 3: Cannot find binding of given name: softargmax,softargmax:1,conv_keypoints_m80
0:00:01.610396748 5746 0x561895abbc90 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<second-infer-engine1> NvDsInferContext[UID 2]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1868> [UID = 2]: Could not find output layer 'softargmax,softargmax:1,conv_keypoints_m80' in engine
0:00:01.610406056 5746 0x561895abbc90 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<second-infer-engine1> NvDsInferContext[UID 2]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 2]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/deepstream_tao_apps/models/faciallandmark/faciallandmarks.etlt_b32_gpu0_int8.engine
0:00:01.719849422 5746 0x561895abbc90 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<second-infer-engine1> [UID 2]: Load new model:../../../configs/facial_tao/faciallandmark_sgie_config.txt sucessfully
0:00:01.719993704 5746 0x561895abbc90 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1161> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
0:00:01.738319234 5746 0x561895abbc90 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-infer-engine1> 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/deepstream_tao_apps/models/faciallandmark/facenet.etlt_b1_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x416x736
1 OUTPUT kFLOAT output_bbox/BiasAdd 4x26x46
2 OUTPUT kFLOAT output_cov/Sigmoid 1x26x46
0:00:01.738361013 5746 0x561895abbc90 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-infer-engine1> 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/deepstream_tao_apps/models/faciallandmark/facenet.etlt_b1_gpu0_int8.engine
0:00:01.739077070 5746 0x561895abbc90 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-infer-engine1> [UID 1]: Load new model:../../../configs/facial_tao/config_infer_primary_facenet.txt sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Segmentation fault (core dumped)
According to Known Issue section:
The GazeNet is a multiple input layers model. DeepStream can generate engine from such models but the implementation of buffer allocation has some problems. So if running the GazeNet sample application without engine, it will fail with core dump for the first time running. The engine will be generated after the first time running. When running the applications again, it will work.
I ran GazeNet application again, but with no result
Before run GazeNet I did this from section ** Build And Run**:
export CUDA_VER=11.4
cd /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate
make
cp libnvdsgst_videotemplate.so /opt/nvidia/deepstream/deepstream/lib/gst-plugins/
rm -rf ~/.cache/gstreamer-1.0/
cd apps/tao_others/deepstream-gaze-app/gazeinfer_impl
make
cd ../
make
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/nvidia/deepstream/deepstream/lib/cvcore_libs
Maybe I missed something or do something wrong. Can anyone give advice?
CUDA version: 11.4
Driver Version: 470.63.01
GPU: RTX 3060 Ti