Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU): RTX 2080
• DeepStream Version: 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version: 7.0
• NVIDIA GPU Driver Version (valid for GPU only): 410.xx
Hi, Im currently working on segmentation problem using deepstream with python, I have also read over the deepstream-python-apps for samples, but still struggle deploying a pretrained model in Pytorch to deepstream. Is there any reference or code snippets that I could get along with, especially working with segmentation task. I have found a repos seems to work with segmentation problem using deepstream. As far as I understand, the flow is almost the same with the detection task, so what distinguishes those 2 tasks, is it the metadata, cause the manual said that the input to nvsegvisual plugin is NvDsInferSegmentationMeta.
Link to repos: https://github.com/anilsathyan7/Portrait-Segmentation
Link to manual: https://docs.nvidia.com/metropolis/deepstream/plugin-manual/index.html#page/DeepStream%20Plugins%20Development%20Guide/deepstream_plugin_details.3.01.html#wwpID0E0ADB0HA