How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

yolo11n-seg quantization precision_mode=a16_w16 gives UINT8 for some output layers

calendar_today November 6, 2026 person @Victor_Cheng domain hailo

Hi, could you try a build that starts from the Model Zoo reference script for yolov11n_seg and adds 16-bit only on the outputs? normalization1 = normalization([0.0, 0.0, 0.0], [255.0, 255.0, 255.0]) change_output_activation(conv60, sigmoid) change_output_activation(conv74, sigmoid) change_output_activation(conv92, sigmoid) quantization_param({output_layer*}, precision_mode=a16_w16) allocator_param(automatic_reshapes=disabled) model_optimization_flavor(optimization_level=2, compression_level=0) Please share the parse-hef output and the accuracy you get compared with your FP32 model. If accuracy

open_in_new Read original post