search

marcoslucianops / DeepStream-Yolo

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
MIT License
1.39k stars 344 forks source link

Cannot access memory at address #406

Closed ioir123ju closed 1 year ago

ioir123ju commented 1 year ago

I have the Segmentation fault with YoloV8.

image

config file:

[property]

gpu-id=0

net-scale-factor=0.0039215697906911373

0=RGB, 1=BGR

model-color-format=0 onnx-file=../models/2023_06_30.onnx

model-engine-file=../models/primary.trt

int8-calib-file=calib.table

labelfile-path=det_labels.txt

int8-calib-file=../models/yolov4.cache

batch-size=32

network-mode=2 num-detected-classes=5 gie-unique-id=1 network-type=0 is-classifier=0

cluster-mode=2 maintain-aspect-ratio=1 parse-bbox-func-name=NvDsInferParseYolo custom-lib-path=/opt/nvidia/deepstream/deepstream/lib/libnvdsinfer_custom_impl_Yolo.so engine-create-func-name=NvDsInferYoloCudaEngineGet symmetric-padding=1

[class-attrs-all] nms-iou-threshold=0.45 pre-cluster-threshold=0.5

marcoslucianops commented 1 year ago

https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/YOLOv8.md

ioir123ju commented 1 year ago

https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/YOLOv8.md

Of course, I followed this document to do it, but the result was a segmentation fault.

marcoslucianops commented 1 year ago

The current files in this repo don't use yoloLayer plugin for YOLOv8 models. Please update the files and generate the engine again running the DeepStream code.

ioir123ju commented 1 year ago

The current files in this repo don't use yoloLayer plugin for YOLOv8 models. Please update the files and generate the engine again running the DeepStream code.

Thank you for your response, but I have already implemented the latest version of DeepStream-Yolo. But it is not work.