Hi, I’m receiving the following error when attempting to run my Mask-RCNN model on DeepStream.
** ERROR: <main:707>: Failed to set pipeline to PAUSED
Quitting
ERROR from src_bin_muxer: Output width not set
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvmultistream/gstnvstreammux.c(2794): gst_nvstreammux_change_state (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer
App run failed
Further details have been attached below.
• Hardware Platform (Jetson / GPU): Jetson Nano DevKit edition with 16GB eMMC 5.1 flash
• DeepStream Version: 6.0.1
• JetPack Version (valid for Jetson only): 4.6.2
• TensorRT Version: 7.2
• Issue Type( questions, new requirements, bugs): Receiving an error when deploying a Mask-RCNN model retrained using NVIDIA TAO.
• 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): Running deepstream-app -c deepstream-app -c maskrcnn_config_file.txt
. The config file is attached here (2.1 KB), and is edited from the peopleSegNet config file in the samples folder. For reference, I’ve been following this article and this article, with deviations being made to correspond with DeepStream 6.0.1.
• Requirement details: The exported .etlt file and a converted trt engine file, both received by following this article.
Could I have some assistance on how to fix the error? I had the same error when trying to run the peopleSegNet sample. I looked over some other forum posts about this error, but didn’t really find much help. Thanks in advance!