Views
No views yet
1onnx/inference.onnx
2paddlex/inference.json
3paddlex/inference.yml
4engines/sm89-trt10.15-cuda12.6-fp16-b1_8/pp_doclayout_v3.engine
5engines/sm89-trt10.15-cuda12.6-fp16-b1_8/engine_manifest.json
6artifact_manifest.json
7scripts/build_engine.sh1GPU: RTX 4090 / sm89
2TensorRT: 10.15.1.29
3CUDA: 12.6
4Precision: FP16
5Profile: batch 1-8, image 3x800x800onnx/inference.onnx if the engine is not compatible with the deployment GPU or TensorRT version.bash scripts/build_engine.sh