Instructions to use bndos/pp-doclayout-v3-trt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use bndos/pp-doclayout-v3-trt with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| set -euo pipefail | |
| ONNX_PATH=${ONNX_PATH:-onnx/inference.onnx} | |
| OUT_DIR=${OUT_DIR:-engines/sm89-trt10.15-cuda12.6-fp16-b1_8} | |
| ENGINE_PATH=${ENGINE_PATH:-${OUT_DIR}/pp_doclayout_v3.engine} | |
| TRTEXEC=${TRTEXEC:-trtexec} | |
| mkdir -p "${OUT_DIR}" | |
| "${TRTEXEC}" \ | |
| --onnx="${ONNX_PATH}" \ | |
| --saveEngine="${ENGINE_PATH}" \ | |
| --fp16 \ | |
| --minShapes=image:1x3x800x800,im_shape:1x2,scale_factor:1x2 \ | |
| --optShapes=image:8x3x800x800,im_shape:8x2,scale_factor:8x2 \ | |
| --maxShapes=image:8x3x800x800,im_shape:8x2,scale_factor:8x2 \ | |
| --memPoolSize=workspace:4096 \ | |
| --builderOptimizationLevel=3 | |