Failed to run deepstream-test2 on Jetson Nano

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Dear NVIDIA,

Failed to run deepstream-test2 with the following CMD. If i were wrong, please point out my mistake, thanks in advance!

How to solve it?

./deepstream-test2-app …/…/…/…/samples/streams/sample_1080p_h264.mp4

Jetson Nano , Deepstream SDK 4.0.1

error log:
./deepstream-test2-app …/…/…/…/samples/streams/sample_1080p_h264.mp4
With tracker
Unknown key ‘gie-mode’ for group [property]
Unknown key ‘gie-mode’ for group [property]
Unknown key ‘gie-mode’ for group [property]
Now playing: …/…/…/…/samples/streams/sample_1080p_h264.mp4

Using winsys: x11
Opening in BLOCKING MODE
Creating LL OSD context new
0:00:00.912126762 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 4]:initialize(): Trying to create engine from model files
0:00:00.912329318 30316 0x55a410df20 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger: NvDsInferContext[UID 4]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
0:02:48.047860069 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 4]:generateTRTModel(): Storing the serialized cuda engine to file at /home/nvidia/deepstream_sdk_v4.0.1_jetson/samples/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_fp16.engine
0:02:48.215362236 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 3]:initialize(): Trying to create engine from model files
0:02:48.215511823 30316 0x55a410df20 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger: NvDsInferContext[UID 3]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
0:05:47.885596427 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 3]:generateTRTModel(): Storing the serialized cuda engine to file at /home/nvidia/deepstream_sdk_v4.0.1_jetson/samples/models/Secondary_CarMake/resnet18.caffemodel_b16_fp16.engine
0:05:48.227017544 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 2]:initialize(): Trying to create engine from model files
0:05:48.227162340 30316 0x55a410df20 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger: NvDsInferContext[UID 2]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.

0:08:49.369836224 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 2]:generateTRTModel(): Storing the serialized cuda engine to file at /home/nvidia/deepstream_sdk_v4.0.1_jetson/samples/models/Secondary_CarColor/resnet18.caffemodel_b16_fp16.engine
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_nvdcf.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is ON
[NvDCF] Initialized
0:08:51.614942947 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 1]:initialize(): Trying to create engine from model files
0:08:51.615111128 30316 0x55a410df20 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger: NvDsInferContext[UID 1]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
0:10:41.453566466 30316 0x55a410df20 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger: NvDsInferContext[UID 1]:generateTRTModel(): Storing the serialized cuda engine to file at /home/nvidia/deepstream_sdk_v4.0.1_jetson/samples/models/Primary_Detector/resnet10.caffemodel_b1_fp16.engine
Running…
ERROR from element h264-parser: Internal data stream error.
Error details: gstbaseparse.c(3611): gst_base_parse_loop (): /GstPipeline:dstest2-pipeline/GstH264Parse:h264-parser:
streaming stopped, reason not-negotiated (-4)

Returned, stopping playback

B.R.

2

Hi 15600219330,

Please use h264 elementary stream to run deepstream-test2-app:

Usage:
$ ./deepstream-test2-app <h264_elementary_stream>
Example:
$ ./deepstream-test2-app ../../../../samples/streams/sample_720p.h264