Nvvideoconvert : buffer transform failed

[sujin.kim]

• Hardware Platform (Jetson / GPU) Jetson xavier AGX
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) Jetpack 5.1
• TensorRT Version 8.5.2-1+cuda11.4
• Issue Type( questions, new requirements, bugs) questions

I’m running multiple processes simultaneously on a Jetson board. The process running YOLOv5 inference module sometimes operates normally and sometimes does not.
When it fails, it outputs the following error message and does not execute.

Lowering the input camera’s FPS or reducing the model size resolves the issue, but I would like to understand exactly why this error occurs.

[Fiona.Chen]

Can you tell us which application you are working with? The configurations?

[sujin.kim]

I’m running the custom pipeline which includes rtsp source, preprocess, pgie, tracker.
Here are the configurations:

[property]
enable=1
target-unique-ids=1
network-input-order=0
process-on-frame=1
unique-id=5
gpu-id=0
maintain-aspect-ratio=1
symmetric-padding=1
processing-width=800
processing-height=448
scaling-buf-pool-size=6
tensor-buf-pool-size=6
network-input-shape= 1;3;448;800
network-color-format=0
tensor-data-type=0
tensor-name=input
scaling-pool-memory-type=0
scaling-pool-compute-hw=0
scaling-filter=0
custom-lib-path=/opt/nvidia/deepstream/deepstream/lib/gst-plugins/libcustom2d_preprocess.so
custom-tensor-preparation-function=CustomTensorPreparation

[user-configs]
   # Below parameters get used when using default custom library nvdspreprocess_lib
   # network scaling factor
pixel-normalization-factor=0.003921568
   # mean file path in ppm format
#mean-file=
   # array of offsets for each channel
#offsets=

[group-0]
src-ids=0;
custom-input-transformation-function=CustomAsyncTransformation
process-on-roi=1
roi-params-src-0=0;240;1920;720

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
onnx-file=a.onnx
model-engine-file=a.onnx_b1_gpu0_fp16.engine
labelfile-path=labels.txt
batch-size=1
#0: FP32/ 1: INT8/ 2: FP16
network-mode=2
num-detected-classes=7
interval=0
gie-unique-id=1
process-mode=1
#0: Detector/1: Classifier/2: Segmentation/3: Instance Segmentation
network-type=0
cluster-mode=2
filter-out-class-ids=0
maintain-aspect-ratio=1
parse-bbox-func-name=NvDsInferParseYolo
custom-lib-path=/root/copilot/lib/libfcam_or_dsyolo.so
#engine-create-func-name=NvDsInferYoloCudaEngineGet
symmetric-padding=1

[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=100

[Fiona.Chen]

1. The attached files are just nvpreprocess and nvinfer configurations. We have no idea about your models or your app just with these two files.
2. Seems you have done some customization with your models, please debug with your own implementation. The gst-nvinfer and gst-nvdspreprocess are open source.

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks