Implementation:Kornia Kornia Pip Install ONNX
| Knowledge Sources | |
|---|---|
| Domains | ONNX, Environment |
| Last Updated | 2026-02-09 15:00 GMT |
Overview
External tool documentation for installing ONNX dependencies required by Kornia's ONNX pipeline features.
Description
This documents the pip installation commands needed to use Kornia's ONNX features. The onnx package provides model format support. ONNX Runtime provides the inference engine with CPU or GPU execution providers. Installation is a prerequisite for ONNXSequential, ONNXLoader, and related APIs.
Usage
Run pip install before using any Kornia ONNX functionality.
Code Reference
| Source | External (pip packages) |
|---|---|
| CPU Command | pip install onnx onnxruntime
|
| GPU Command | pip install onnx onnxruntime-gpu
|
| Import Verification | import onnx; import onnxruntime
|
I/O Contract
Inputs
Python environment with pip available.
Outputs
onnx and onnxruntime packages available for import.
Usage Examples
CPU installation
pip install onnx onnxruntime
GPU installation (CUDA)
pip install onnx onnxruntime-gpu
Verification
import onnx
import onnxruntime as ort
print(f"ONNX version: {onnx.__version__}")
print(f"ONNX Runtime version: {ort.__version__}")
print(f"Available providers: {ort.get_available_providers()}")
Related Pages
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment