Deepstream Sample Not Showing Window

Hello, I have a fresh AGX Orin 64gb development kit, and have installed the Deepstream SDK onto it.

When I try to run one of the samples, no window opens to show the output, even with the sink being defined as type “2” (which should be to open a window).

There is also some strange output in the terminal about an “unknown embedded device”, which I’m not sure is related.

Here is the terminal output:

user@neuralone:/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app$ sudo deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt 
[sudo] password for user: 
0:00:02.709504976 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 6]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 2
0   INPUT  kFLOAT input_1         3x224x224       
1   OUTPUT kFLOAT predictions/Softmax 20x1x1          

0:00:02.883285534 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_2> NvDsInferContext[UID 6]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 6]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:02.922413528 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<secondary_gie_2> [UID 6]: Load new model:/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/config_infer_secondary_carmake.txt sucessfully
0:00:04.702838571 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 5]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 2
0   INPUT  kFLOAT input_1         3x224x224       
1   OUTPUT kFLOAT predictions/Softmax 12x1x1          

0:00:04.880630467 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_1> NvDsInferContext[UID 5]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 5]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_CarColor/resnet18.caffemodel_b16_gpu0_int8.engine
0:00:04.927854991 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<secondary_gie_1> [UID 5]: Load new model:/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/config_infer_secondary_carcolor.txt sucessfully
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine open error
0:00:06.705541814 27299 0xaaaacac6cc60 WARN                 nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 4]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine failed
0:00:06.881147016 27299 0xaaaacac6cc60 WARN                 nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 4]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/configs/deepstream-app/../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine failed, try rebuild
0:00:06.881203177 27299 0xaaaacac6cc60 INFO                 nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<secondary_gie_0> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 4]: 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.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
WARNING: [TRT]: Unknown embedded device detected. Using 59655MiB as the allocation cap for memory on embedded devices.

With the last line about the unknown embedded device being output continuously, until I ctrl-C to kill the app.

Based on all that I’ve looked up so far, this sample should be opening an output window, but nothing appears to happen.

Any help would be greatly appreciated. thank you.

Never mind…

I just had to leave the terminal running for quite awhile the first time I ran it.

Now, it opens up almost immediately, and everything works.

For those wondering in the future, since it isn’t entirely clear, it appears that on the first run it takes a good bit before anything actually starts processing.

Is this still an DeepStream issue to support?

@fanzh No, it was entirely on me for not waiting long enough on the first run of the deepstream sample.

I am still curious about this message, however:

WARNING: [TRT]: Unknown embedded device detected. Using 59655MiB as the allocation cap for memory on embedded devices.

Is this expected? Or is it some misconfiguration issue somewhere? The sample runs just fine, I just see this message in the terminal many times before the output window opens.

it is warning level log, please ignore it.

@fanzh

Alright, thanks for your prompt replies, and help. But yes, I think my issue is completely resolved now. I just didn’t know I had to keep the deepstream-app running for long enough the first time.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.