ERROR: [TRT]: ../rtSafe/safeRuntime.cpp (25) - Cuda Error in allocate: 999 (unknown error)

[rajkumarsaswamy]

• Hardware Platform (Jetson / GPU) Jetson Nano 4GB
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.5.1
• TensorRT Version 7.1.3

• Issue Type( questions, new requirements, bugs) error
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) deepstream-app -c source8_1080p_dec_infer-resnet_tracker_tiled_display_fp16_nano.txt

i just tried to execute a sample deepstream-app config.

i get error: ERROR: [TRT]: …/rtSafe/safeRuntime.cpp (25) - Cuda Error in allocate: 999 (unknown error)

More errors as shown in the screenshot

More info about my setup

[AastaLLL]

Hi,

Just checked. We can run the following command on Nano+JetPack4.5.1 successfully.

$ deepstream-app -c source8_1080p_dec_infer-resnet_tracker_tiled_display_fp16_nano.txt

Not sure if any issue in the CUDA or TensorRT installation on your environment.
Could you give the below command a try?

$ /usr/src/tensorrt/bin/trtexec --deploy=/opt/nvidia/deepstream/deepstream-5.1/samples/models/Primary_Detector_Nano/resnet10.prototxt --model=/opt/nvidia/deepstream/deepstream-5.1/samples/models/Primary_Detector_Nano/resnet10.caffemodel --saveEngine=/opt/nvidia/deepstream/deepstream-5.1/samples/models/Primary_Detector_Nano/resnet10.caffemodel_b8_gpu0_fp16.engine --output=conv2d_bbox,conv2d_cov/Sigmoid --batch=8 --fp16 --verbose

Thanks.