quantization
4 posts · browse all tags
Fundamentals Quantization: How Many Bits a Pixel Deserves
Lesson 3 of The Image as Data. Rounding to fewer levels costs Δ/√12 of error, and on this camera's mid-tones the formula predicts the measurement to within 2%. Set that error equal to the read noise unit 1.2 measured and the crossing lands at 9.3 to 9.5 bits — so a 12-bit file on this sensor carries about two and a half bits of nothing.
Models & Detection YOLO-NAS Strikes Back: Still the Fastest Detector on Hardware You Already Own
Quantized to INT8, YOLO-NAS-S runs at 270 FPS on a laptop CPU and 1146 FPS on a mid-range laptop GPU, and it drops straight into Frigate. The model aged well; its tooling did not. Here is a clean reimplementation, measured across CPU, Intel iGPU and NVIDIA dGPU, and checked bit-for-bit against the original.
Edge Deployment RF-DETR vs YOLO-NAS: A Practical Benchmark for Edge Deployment: CPU, GPU, and Intel iGPU Compared
RF-DETR Nano vs YOLO-NAS-S on COCO across CPU, CUDA GPU, and Intel Iris Xe iGPU, across two resolutions, OpenVINO FP32/FP16/INT8, and a custom fine-tune, all under one consistent evaluation. RF-DETR wins accuracy; YOLO-NAS wins latency, efficiency, and INT8.
Models & Detection CNN vs Transformer, quantized: YOLO26-seg and RF-DETR-Seg race for instance masks on an Intel iGPU
Two opposite small segmentation models, a 2026-era CNN and a DETR transformer, both quantized to INT8 with NNCF and run on a laptop Intel iGPU. YOLO26-seg's forward pass is ~7.4× faster; RF-DETR-Seg keeps its masks more faithful under INT8 on the CPU, and its fully-quantized mask head breaks on the iGPU. The whole shootout, numbers first.