Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser,…
---
name: Deepstream Import Vision Model
description: Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser,…
---
# Deepstream Import Vision Model
Part of the **NVIDIA Skills** pack by NVIDIA (`NVIDIA/skills`).
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser,…
This catalog entry summarizes the skill for discovery. Get the full skill - including any bundled scripts and resources - from the source:
Full skill & source: https://github.com/NVIDIA/skills/tree/main/skills/deepstream-import-vision-model
It activates automatically in your next session.
Not connected yet? Connect your AI first →
MCP endpoint
https://skillme.dev/api/mcp