Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU • DeepStream Version
5.0 • JetPack Version (valid for Jetson only) • TensorRT Version
7.0 • NVIDIA GPU Driver Version (valid for GPU only)
cuda 10.2 • Issue Type( questions, new requirements, bugs)
questions&&bugs • 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) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Hi,I try to run deepstream_image_deocode_app because we have requirement on doing image inference base on deepstream, I removed nvtiler,nvvideo-converter,nvdsosd and change sink element to fakesink because we dont need to show the inference result.
the code is here: deepstream_image_decode_app.c (14.8 KB)
but if i add two or more folder like this “./deepstream-image-decode-app /home/wjh/datas/imgs/folder1/%d.jpg /home/wjh/datas/imgs/folder1/%d.jpg” the stream run as normal.
I’ve tried all jpg files you sent with deepstream-image-decode-app, it works well, so the problem has nothing to do with the jpeg files and deepstream.
Since you have removed nvmultistreamtiler from the pipeline, please set the “enable-last-sample” property of fakesink to false.
It works! thanks, but Why I need to set this property? and why if this property is TRUE using 2 folders as inputs can work well but would be hang when using only one folder as input?
“enable-last-sample” property of fakesink will hold the last GstBuffer until new GstBuffer is available. The nvv4l2decoder and nvstreammux all work with buffer pool, so it is important to release GstBuffer ASAP to make the pipeline continue to work.