CV Model Workflows

These images are intended for computer vision models such as YOLO, SSD, Faster R-CNN, and ResNet-based architectures.

Recommended image:

  • cloud_ai_inference_pytools

Typical usage:

  • Export or load ONNX models

  • Generate calibration profiles

  • Compile models using qaic-compile

  • Run inference using qaic-runner

Example: Interactive CV workflow

docker pull ghcr.io/quic/cloud_ai_inference_pytools:1.21.2.0

docker run --rm -it \
  --shm-size=2gb \
  --network host \
  -v $PWD:/workspace \
  --device /dev/accel/ \
  ghcr.io/quic/cloud_ai_inference_pytools:1.21.2.0 \
  /bin/bash