I created a segmentation model in YOLOv8, the inference on YOLO and export to ONNX was working fine, but an error occurred in the conversion to a HEF file.
I used Hailo AI Suite from Docker, and running on Ubuntu 24.04.
Below is the full log of the return.
hailomz compile --ckpt best.onnx --calib-path /local/shared_with_docker/imgs --yaml yolov8m_seg.yaml --start-node-names images --end-node-names output0 output1
<Hailo Model Zoo INFO> Start run for network yolov8m_seg ...
<Hailo Model Zoo INFO> Initializing the hailo8 runner...
[info] Translation started on ONNX model yolov8m_seg
[info] Restored ONNX model yolov8m_seg (completion time: 00:00:00.48)
[info] Extracted ONNXRuntime meta-data for Hailo model (completion time: 00:00:01.60)
[info] Simplified ONNX model for a parsing retry attempt (completion time: 00:00:03.00)
[info] According to recommendations, retrying parsing with end node names: ['/model.22/Concat', '/model.22/proto/cv3/act/Mul', '/model.22/Concat_4'].
[info] Translation started on ONNX model yolov8m_seg
[info] Restored ONNX model yolov8m_seg (completion time: 00:00:00.34)
[info] Extracted ONNXRuntime meta-data for Hailo model (completion time: 00:00:01.53)
[info] Start nodes mapped from original model: 'images': 'yolov8m_seg/input_layer1'.
[info] End nodes mapped from original model: '/model.22/Concat', '/model.22/proto/cv3/act/Mul', '/model.22/Concat_4'.
[info] Translation completed on ONNX model yolov8m_seg (completion time: 00:00:02.35)
[info] Saved HAR to: /local/workspace/yolov8-seg/yolov8m_seg.har
<Hailo Model Zoo INFO> Preparing calibration data...
[info] Loading model script commands to yolov8m_seg from /local/workspace/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov8m_seg.alls
[info] Starting Model Optimization
[warning] Reducing optimization level to 0 (the accuracy won't be optimized and compression won't be used) because there's less data than the recommended amount (1024), and there's no available GPU
[warning] Running model optimization with zero level of optimization is not recommended for production use and might lead to suboptimal accuracy results
[info] Model received quantization params from the hn
[info] MatmulDecompose skipped
[info] Starting Mixed Precision
[info] Model Optimization Algorithm Mixed Precision is done (completion time is 00:00:00.65)
[info] LayerNorm Decomposition skipped
[info] Starting Statistics Collector
[info] Using dataset with 64 entries for calibration
Calibration: 100%|█████████████████████████████████████████████████████████████| 64/64 [01:17<00:00, 1.21s/entries]
[info] Model Optimization Algorithm Statistics Collector is done (completion time is 00:01:19.19)
[info] Starting Fix zp_comp Encoding
[info] Model Optimization Algorithm Fix zp_comp Encoding is done (completion time is 00:00:00.00)
[info] Matmul Equalization skipped
[info] No shifts available for layer yolov8m_seg/conv36/conv_op, using max shift instead. delta=0.4213
[info] No shifts available for layer yolov8m_seg/conv36/conv_op, using max shift instead. delta=0.2106
[info] Finetune encoding skipped
[info] Bias Correction skipped
[info] Adaround skipped
[info] Quantization-Aware Fine-Tuning skipped
[info] Layer Noise Analysis skipped
[info] Model Optimization is done
[info] Saved HAR to: /local/workspace/yolov8-seg/yolov8m_seg.har
[info] Loading model script commands to yolov8m_seg from /local/workspace/hailo_model_zoo/hailo_model_zoo/cfg/alls/generic/yolov8m_seg.alls
[info] To achieve optimal performance, set the compiler_optimization_level to "max" by adding performance_param(compiler_optimization_level=max) to the model script. Note that this may increase compilation time.
[info] Loading network parameters
[info] Starting Hailo allocation and compilation flow
[error] Mapping Failed (allocation time: 20s)
No successful assignments: concat18 errors:
Agent infeasible
[error] Failed to produce compiled graph
[error] BackendAllocatorException: Compilation failed: No successful assignments: concat18 errors:
Agent infeasible