Error loading model TAO 4.0 and DeepStream Python Apps

If you don’t have a display interface, we suggest you save the result to a file or use rtsp sink to play the video on another device. The nveglglessink plugin is used in the source code and it needs display env. So if you run it directly, it will report error.

I am kinda confused now, why this is a display error if the .py works perfectly fine after changing to fakesink like this:

sink = Gst.ElementFactory.make("fakesink", "fakesink")

The only real error happens after I try to use a new .etlt model training in the TAO 4.0 docker. Do I still need to configure the deepstream display docker internally? Even if the original deepstream_imagedata-multistream.py work perfectly fine?

How did you generate the resnet18_detector.trt.int8.engine? From the log you attached, it’s an error of building engine. Theoretically, even if you switch to fakesink, there will still be mistakes.
Could you run it with GST_DEBUG=3 and attach the log generated?

I did it using the TAO 4.0 toolkit jupyters and I just change the extension since the conf file that I am using as an example use .engine

# Need to pass the actual image directory instead of data root for tao-deploy to locate images for calibration
!sed -i "s|/workspace/tao-experiments/data/training|/workspace/tao-experiments/data/training/image_2|g" $LOCAL_SPECS_DIR/detectnet_v2_retrain_resnet18_kitti.txt
# Convert to TensorRT engine (INT8)
!tao-deploy detectnet_v2 gen_trt_engine \
                  -m $USER_EXPERIMENT_DIR/experiment_dir_final/resnet18_detector.etlt \
                  -k $KEY  \
                  --data_type int8 \
                  --batches 20 \
                  --batch_size 16 \
                  --max_batch_size 16\
                  --engine_file $USER_EXPERIMENT_DIR/experiment_dir_final/resnet18_detector.trt.int8.engine \
                  --cal_cache_file $USER_EXPERIMENT_DIR/experiment_dir_final/calibration.bin \
                  -e $SPECS_DIR/detectnet_v2_retrain_resnet18_kitti.txt \
                  --verbose
# Convert back the spec file
!sed -i "s|/workspace/tao-experiments/data/training/image_2|/workspace/tao-experiments/data/training|g" $LOCAL_SPECS_DIR/detectnet_v2_retrain_resnet18_kitti.txt

Did you put the model and config file int the path described by the configuration file? From the log, it cannot find the file from the path. Or you can try to use the sudo command.

Everything is there and sudo command return the same error, I move the models to the original path of the file and didnt work. I wonder if this problem is because the Ampere A100 dont have encode support according to this post

Yes, the Ampere A100 don’t have hardware encode support. But the error from your log is from nvinfer. You can try to chang the encode to software and try it first.

How can I do that? Also, I realise something, I do not have the prototxt since TAO didn’t create it, how can I make it with TAO? Or I need another element to make it?

1.deepstream_imagedata-multistream.py doesn’t use encoder, so you don’t have to worry about the encoder problem.
2.You need to reconfirm whether it can be run well with fakesink. If it is run well with fakesink, there should be no problem with the model.
3. Could you run it with GST_DEBUG=3 and attach the log generated?

GST_DEBUG=3  python3.8 deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame

This is the log generate by GST_DEBUG=3

Otest.h264 frame
Frames will be saved in  frame
Creating Pipeline

Creating streamux

Creating source_bin  0

Creating source bin
source-bin-00
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating EGLSink

Adding elements to Pipeline

Linking elements in the Pipeline

Now playing...
1 :  file:///share_data_deepstream/tao/WH_TAOtest.h264
Starting pipeline

ERROR: [TRT]: 1: [stdArchiveReader.cpp::StdArchiveReader::40] Error Code 1: Serialization (Serialization assertion stdVersionRead == serializationVersion failed.Version tag does not match. Note: Current Version: 213, Serialized Engine Version: 232)
ERROR: [TRT]: 4: [runtime.cpp::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1528 Deserialize engine failed from file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine
0:00:02.239533096  1536      0x3b1ea70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed
0:00:02.332333380  1536      0x3b1ea70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed, try rebuild
0:00:02.332787012  1536      0x3b1ea70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file '/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/../../../../samples/models/tao_model/resnet18_detector.prototxt'
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:966 failed to build network since parsing model errors.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
0:00:03.279153086  1536      0x3b1ea70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 1]: build engine file failed
0:00:03.372307926  1536      0x3b1ea70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2029> [UID = 1]: build backend context failed
0:00:03.372367257  1536      0x3b1ea70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1266> [UID = 1]: generate backend failed, check config file settings
0:00:03.372409026  1536      0x3b1ea70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Failed to create NvDsInferContext instance
0:00:03.372426088  1536      0x3b1ea70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
0:00:03.372477875  1536      0x3b1ea70 WARN                GST_PADS gstpad.c:1142:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Exiting app

1.Please make sure you run the command with sudo.

sudo GST_DEBUG=3  python3  deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame

2.You can run our demo by referring the README first to make sure that your environment is OK. It’s a resnet model too.

/opt/nvidia/deepstream/deepstream/sources\apps\sample_apps\deepstream-test1\

Sorry about that, here are the results using the same .h264 file:

sudo GST_DEBUG=3  python3.8 deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame

WH_TAOtest.h264 frame
Frames will be saved in  frame
Creating Pipeline

Creating streamux

Creating source_bin  0

Creating source bin
source-bin-00
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating EGLSink

Adding elements to Pipeline

Linking elements in the Pipeline

Now playing...
1 :  file:///share_data_deepstream/tao/WH_TAOtest.h264
Starting pipeline

ERROR: [TRT]: 1: [stdArchiveReader.cpp::StdArchiveReader::40] Error Code 1: Serialization (Serialization assertion stdVersionRead == serializationVersion failed.Version tag does not match. Note: Current Version: 213, Serialized Engine Version: 232)
ERROR: [TRT]: 4: [runtime.cpp::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1528 Deserialize engine failed from file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine
0:00:02.302206549  1554      0x2c0fe70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed
0:00:02.400428793  1554      0x2c0fe70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed, try rebuild
0:00:02.400778037  1554      0x2c0fe70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file '/opt/nvidia/deepstream/deepstream-6.1/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/../../../../samples/models/tao_model/resnet18_detector.prototxt'
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:966 failed to build network since parsing model errors.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
0:00:03.316092175  1554      0x2c0fe70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 1]: build engine file failed
0:00:03.411608674  1554      0x2c0fe70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2029> [UID = 1]: build backend context failed
0:00:03.411648709  1554      0x2c0fe70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1266> [UID = 1]: generate backend failed, check config file settings
0:00:03.411667574  1554      0x2c0fe70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Failed to create NvDsInferContext instance
0:00:03.411679767  1554      0x2c0fe70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
0:00:03.411714632  1554      0x2c0fe70 WARN                GST_PADS gstpad.c:1142:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Exiting app

This one is the deepstream_test_1.py without changing anything:

sudo GST_DEBUG=3  python3 deepstream_test_1.py /share_data_deepstream/tao/WH_TAOtest.h264

Creating Pipeline

Creating Source

Creating H264Parser

Creating Decoder

Creating EGLSink

Playing file /share_data_deepstream/tao/WH_TAOtest.h264
Adding elements to Pipeline

Linking elements in the Pipeline

Starting pipeline

0:00:00.931492286  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931517272  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MJPG
0:00:00.931530197  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931539865  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MJPG
0:00:00.931554693  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931562728  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat AV10
0:00:00.931574871  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931582595  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat AV10
0:00:00.931594748  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931620556  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat DVX5
0:00:00.931624584  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931632388  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat DVX5
0:00:00.931642698  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931650342  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat DVX4
0:00:00.931660862  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931668215  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat DVX4
0:00:00.931679587  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931686670  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MPG4
0:00:00.931689726  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931698272  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MPG4
0:00:00.931708391  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931721666  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat MPG2
0:00:00.931728989  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931732145  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat MPG2
0:00:00.931744699  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931752253  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat H265
0:00:00.931759547  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931767712  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat H265
0:00:00.931777891  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931781859  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat VP90
0:00:00.931785074  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931795394  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat VP90
0:00:00.931805062  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931808288  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat VP80
0:00:00.931812075  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931816012  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat VP80
0:00:00.931826723  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931834146  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe minimum capture size for pixelformat H264
0:00:00.931837723  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:sink> Unable to try format: Unknown error -1
0:00:00.931845358  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:sink> Could not probe maximum capture size for pixelformat H264
0:00:00.932126054  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:src> Unable to try format: Unknown error -1
0:00:00.932133919  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2942:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:src> Could not probe minimum capture size for pixelformat NM12
0:00:00.932137305  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:3057:gst_v4l2_object_get_nearest_size:<nvv4l2-decoder:src> Unable to try format: Unknown error -1
0:00:00.932141322  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2948:gst_v4l2_object_probe_caps_for_format:<nvv4l2-decoder:src> Could not probe maximum capture size for pixelformat NM12
0:00:00.932146923  1658      0x3ec92c0 WARN                    v4l2 gstv4l2object.c:2395:gst_v4l2_object_add_interlace_mode:0x2d63670 Failed to determine interlace mode
0:00:00.933097875  1658      0x3ec92c0 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
0:00:02.242788203  1658      0x3ec92c0 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/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

0:00:02.333858712  1658      0x3ec92c0 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:02.335822753  1658      0x3ec92c0 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-inference> [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
0:00:02.336751354  1658      0x3ec92c0 WARN                 basesrc gstbasesrc.c:3600:gst_base_src_start_complete:<file-source> pad not activated yet
0:00:02.444684176  1658      0x35e0640 ERROR            egladaption ext/eglgles/gstegladaptation.c:669:gst_egl_adaptation_choose_config:<nvvideo-renderer> Could not find matching framebuffer config
0:00:02.444708081  1658      0x35e0640 ERROR            egladaption ext/eglgles/gstegladaptation.c:683:gst_egl_adaptation_choose_config:<nvvideo-renderer> Couldn't choose an usable config
0:00:02.444712459  1658      0x35e0640 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2802:gst_eglglessink_configure_caps:<nvvideo-renderer> Couldn't choose EGL config
0:00:02.444715865  1658      0x35e0640 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2862:gst_eglglessink_configure_caps:<nvvideo-renderer> Configuring caps failed
0:00:02.444734977  1658      0x35e08c0 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.444758150  1658      0x35e08c0 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.444766365  1658      0x35e08c0 WARN                GST_PADS gstpad.c:4231:gst_pad_peer_query:<onscreendisplay:src> could not send sticky events
0:00:02.445113606  1658      0x35e08c0 WARN            v4l2videodec gstv4l2videodec.c:1847:gst_v4l2_video_dec_decide_allocation:<nvv4l2-decoder> Duration invalid, not setting latency
0:00:02.445136559  1658      0x35e08c0 WARN          v4l2bufferpool gstv4l2bufferpool.c:1082:gst_v4l2_buffer_pool_start:<nvv4l2-decoder:pool:src> Uncertain or not enough buffers, enabling copy threshold
0:00:02.445523970  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.445651334  1658     0x2d1f4360 WARN          v4l2bufferpool gstv4l2bufferpool.c:1533:gst_v4l2_buffer_pool_dqbuf:<nvv4l2-decoder:pool:src> Driver should never set v4l2_buffer.field to ANY
0:00:02.445765168  1658     0x2d1f4360 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.445851139  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.445869553  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.445878670  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.446072944  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.446082272  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.446091218  1658     0x2d1f4300 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
Frame Number=0 Number of Objects=1 Vehicle_count=0 Person_count=1
0:00:02.454968334  1658      0x35e06a0 ERROR          nveglglessink ext/eglgles/gsteglglessink.c:2907:gst_eglglessink_setcaps:<nvvideo-renderer> Failed to configure caps
0:00:02.455004271  1658      0x35e06a0 WARN                 nvinfer gstnvinfer.cpp:2300:gst_nvinfer_output_loop:<primary-inference> error: Internal data stream error.
0:00:02.455014600  1658      0x35e06a0 WARN                 nvinfer gstnvinfer.cpp:2300:gst_nvinfer_output_loop:<primary-inference> error: streaming stopped, reason not-negotiated (-4)
Error: gst-stream-error-quark: Internal data stream error. (1): gstnvinfer.cpp(2300): gst_nvinfer_output_loop (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
streaming stopped, reason not-negotiated (-4)
Frame Number=1 Number of Objects=1 Vehicle_count=0 Person_count=1
0:00:02.456027233  1658      0x35e08c0 WARN               baseparse gstbaseparse.c:3666:gst_base_parse_loop:<h264-parser> error: Internal data stream error.
0:00:02.456042452  1658      0x35e08c0 WARN               baseparse gstbaseparse.c:3666:gst_base_parse_loop:<h264-parser> error: streaming stopped, reason not-negotiated (-4)

And this is the .log after running the deepstream_test_1.py with fakesink:
out.log (7.2 MB)

From the log of deepstream_test_1.py, the tensorRT environment is OK. The reason for the error is that there is a problem with your display environment.
From your project log, there may be a problem with your owm model. You can try the following methods to check:
1.You should make sure there are correct files in the corresponding path of your configuration file. Please notice that it’s a relative path.

model-file=../../../../samples/models/tao_model/resnet18_detector.etlt
proto-file=../../../../samples/models/tao_model/resnet18_detector.prototxt
model-engine-file=../../../../samples/models/tao_model/resnet18_detector.trt.int8.engine
labelfile-path=../../../../samples/models/tao_model/labels.txt
int8-calib-file=../../../../samples/models/tao_model/calibration.bin

2.You can try to commet out the line below to run the cli:

model-file=../../../../samples/models/tao_model/resnet18_detector.etlt
proto-file=../../../../samples/models/tao_model/resnet18_detector.prototxt
#model-engine-file=../../../../samples/models/tao_model/resnet18_detector.trt.int8.engine
labelfile-path=../../../../samples/models/tao_model/labels.txt
int8-calib-file=../../../../samples/models/tao_model/calibration.bin

3.You can try to use the model we provided to run your demo with the fakesink:

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

This is the result:

1.You should make sure there are correct files in the corresponding path of your configuration file. Please notice that it’s a relative path:

root@vm-ai-shared-instance-001:/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model# ls -lah
total 55M
drwxr-xr-x 2 root root 4.0K Jan 11 19:37 .
drwxr-xr-x 1 root root 4.0K Jan 11 19:33 ..
-rw-r--r-- 1 root root 4.1K Jan 11 19:34 calibration.bin
-rw-r--r-- 1 root root   44 Jan 11 19:34 labels.txt
-rw-r--r-- 1 root root  312 Jan 11 19:34 nvinfer_config.txt
-rw-r--r-- 1 root root  43M Jan 11 19:35 resnet18_detector.etlt
-rw-r--r-- 1 root root  12M Jan 11 19:36 resnet18_detector.trt.int8.engine
root@vm-ai-shared-instance-001:/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model# pwd
/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model
root@vm-ai-shared-instance-001:/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model#

I even try to replace the full path and the same error:

sudo GST_DEBUG=3  python3.8 deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame
Frames will be saved in  frame
Creating Pipeline

Creating streamux

Creating source_bin  0

Creating source bin
source-bin-00
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating EGLSink

Adding elements to Pipeline

Linking elements in the Pipeline

Now playing...
1 :  file:///share_data_deepstream/tao/WH_TAOtest.h264
Starting pipeline

ERROR: [TRT]: 1: [stdArchiveReader.cpp::StdArchiveReader::40] Error Code 1: Serialization (Serialization assertion stdVersionRead == serializationVersion failed.Version tag does not match. Note: Current Version: 213, Serialized Engine Version: 232)
ERROR: [TRT]: 4: [runtime.cpp::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1528 Deserialize engine failed from file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine
0:00:02.361779767  1765      0x3e7be70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed
0:00:02.460520666  1765      0x3e7be70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed, try rebuild
0:00:02.460773330  1765      0x3e7be70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file '/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.prototxt'
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:966 failed to build network since parsing model errors.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
0:00:03.441291454  1765      0x3e7be70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 1]: build engine file failed
0:00:03.542571515  1765      0x3e7be70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2029> [UID = 1]: build backend context failed
0:00:03.542629764  1765      0x3e7be70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1266> [UID = 1]: generate backend failed, check config file settings
0:00:03.542659460  1765      0x3e7be70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Failed to create NvDsInferContext instance
0:00:03.542670831  1765      0x3e7be70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
0:00:03.542708111  1765      0x3e7be70 WARN                GST_PADS gstpad.c:1142:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Exiting app

2.You can try to commet out the line below to run the cli:

sudo GST_DEBUG=3  python3.8 deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame
Frames will be saved in  frame
Creating Pipeline

Creating streamux

Creating source_bin  0

Creating source bin
source-bin-00
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating EGLSink

Adding elements to Pipeline

Linking elements in the Pipeline

Now playing...
1 :  file:///share_data_deepstream/tao/WH_TAOtest.h264
Starting pipeline

0:00:01.661185229  1775      0x3d46c70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file '/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.prototxt'
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:966 failed to build network since parsing model errors.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
0:00:03.044372415  1775      0x3d46c70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 1]: build engine file failed
0:00:03.139302305  1775      0x3d46c70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2029> [UID = 1]: build backend context failed
0:00:03.139866463  1775      0x3d46c70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1266> [UID = 1]: generate backend failed, check config file settings
0:00:03.139930453  1775      0x3d46c70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Failed to create NvDsInferContext instance
0:00:03.139941584  1775      0x3d46c70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary-inference> error: Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
0:00:03.139976279  1775      0x3d46c70 WARN                GST_PADS gstpad.c:1142:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
Config file path: dstest_imagedata_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Exiting app

3.You can try to use the model we provided to run your demo with the fakesink:

This is the output log:
out.log (7.6 MB)

This is the configuration I use for the first 2 tests:
deepstream_imagedata-multistream.py (16.8 KB)
dstest_imagedata_config.txt (3.6 KB)

For the last test, I used the original configuration files with the only change being the replacement of the sink with a fakesink.

Are you sure the resnet18_detector.prototxtfile is in tao_model path?

Hi, as I say before, I don’t have it since TAO didn’t generate it, there is a way to generate it outside TAO? Or do I miss something?

@ganmobar
For running inference with TAO models in deepstream, official github is GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream .
Please use it instead.
More, TAO did not generate any prototxt. To config in deepstream, seems that you are running with detectnet_v2 network, so you leverage facenet’s config. deepstream_tao_apps/config_infer_primary_facenet.txt at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub . Facenet is based on detectnet_v2 network.

Hi! After a few days of trial and error, I decide to reinstall everything from zero and the error changes:

sudo GST_DEBUG=3  python3.8 deepstream_imagedata-multistream.py file:///share_data_deepstream/tao/WH_TAOtest.h264 frame
Frames will be saved in  frame
Creating Pipeline

Creating streamux

Creating source_bin  0

Creating source bin
source-bin-00
Creating Pgie

Creating nvvidconv1

Creating filter1

Creating tiler

Creating nvvidconv

Creating nvosd

Creating EGLSink

Adding elements to Pipeline

Linking elements in the Pipeline

Now playing...
1 :  file:///share_data_deepstream/tao/WH_TAOtest.h264
Starting pipeline

0:00:00.527023634  2047      0x3efea70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
ERROR: [TRT]: 1: [stdArchiveReader.cpp::StdArchiveReader::40] Error Code 1: Serialization (Serialization assertion stdVersionRead == serializationVersion failed.Version tag does not match. Note: Current Version: 213, Serialized Engine Version: 232)
ERROR: [TRT]: 4: [runtime.cpp::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1528 Deserialize engine failed from file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine
0:00:01.654741495  2047      0x3efea70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed
0:00:01.743019611  2047      0x3efea70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.1/samples/models/tao_model/resnet18_detector.trt.int8.engine failed, try rebuild
0:00:01.743371591  2047      0x3efea70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
ERROR: [TRT]: UffParser: Could not read buffer.
parseModel: Failed to parse UFF model
ERROR: tlt/tlt_decode.cpp:358 Failed to build network, error in model parsing.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:723 Failed to create network using custom network creation function
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:789 Failed to get cuda engine from custom library API
0:00:02.705357405  2047      0x3efea70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1943> [UID = 1]: build engine file failed
ERROR: [TRT]: 2: [logging.cpp::decRefCount::61] Error Code 2: Internal Error (Assertion mRefCount > 0 failed. )
corrupted size vs. prev_size while consolidating
Aborted

Any suggestion on how to follow up this change? Retrain the model?

You can refer the link below:https://forums.developer.nvidia.com/t/lprnet-custom-trained-model-error-trt-uffparser-could-not-read-buffer/189322 and check if it can solve your problem.

Hi, I finally made it work. The problem was the version of the TAO docker container and the $DISPLAY variable. After retraining in the computer-vision version of it and mounting the deepstream-devel using a virtual $DISPLAY everything work fine. Thank you for sticking with me on this problem.

1 Like