YOLOv8 – TildAlice

Pruned YOLOv8 ONNX INT8 Fails: 3 Fixes That Work

2026년 06월 05일

Pruned YOLOv8 + ONNX INT8 dtype mismatch? Here are 3 working fixes with Jetson benchmarks — re-quantize, QAT pruning, or manual graph surgery.

2026년 06월 03일

Migrated Haar Cascade to YOLOv8 face detection: 4.2x faster on CPU, 89% mAP50 vs 67%. Real preprocessing pitfalls and deployment gotchas included.

2026년 05월 08일

Compare YOLOv8, YOLOv9, and YOLO11 for your first object detection project. Speed, accuracy, and ease-of-use benchmarks to help you choose.

2026년 02월 11일

YOLOv8 + PaddleOCR pipeline runs at 21 FPS with 94% accuracy. Here's the preprocessing trick that fixed OCR failures.

2026년 02월 07일

INT8 quantization pushed YOLOv8 from 45 to 180 FPS on Jetson Orin Nano. PTQ beat QAT with 10 lines of calibration code. Here's the recipe.