Tag: INT8 양자화
-
ONNX Runtime과 TensorRT로 컴퓨터비전 모델 경량화하기: Edge AI 배포 실전 가이드
Speed up YOLO inference 8x on Jetson with TensorRT INT8 quantization. ONNX conversion pitfalls and FP16 vs INT8 accuracy tradeoffs included.
Speed up YOLO inference 8x on Jetson with TensorRT INT8 quantization. ONNX conversion pitfalls and FP16 vs INT8 accuracy tradeoffs included.