Hi.
I want to parse onnx that input shape is [1,6,3,256,704].
But when i parse this onnx, parser result give me input shape [256,704,3]
I dont know why this issue appeared.
Parser Log :
(hailo_venv) (base) mdh@homebody:~/Documents/CUDA-FastBEV/model/resnet18$ hailo parser onnx fastbev_pre_trt.onnx --har-path ./har_combine/bev_feature.har --start-node-names image --tensor-shapes image=[1,6,3,256,704] --input-format BNCHW
[info] Current Time: 19:43:38, 09/08/25
[info] CPU: Architecture: x86_64, Model: AMD Ryzen 5 PRO 5650GE with Radeon Graphics, Number Of Cores: 12, Utilization: 0.2%
[info] Memory: Total: 14GB, Available: 11GB
[info] System info: OS: Linux, Kernel: 6.8.0-40-generic
[info] Hailo DFC Version: 3.30.0
[info] HailoRT Version: 4.20.0
[info] PCIe: No Hailo PCIe device was found
[info] Running hailo parser onnx fastbev_pre_trt.onnx --har-path ./har_combine/bev_feature.har --start-node-names image --tensor-shapes image=[1,6,3,256,704] --input-format BNCHW
[info] Translation started on ONNX model fastbev_pre_trt
[info] Restored ONNX model fastbev_pre_trt (completion time: 00:00:00.18)
[info] Extracted ONNXRuntime meta-data for Hailo model (completion time: 00:00:00.66)
[info] Start nodes mapped from original model: ‘image’: ‘fastbev_pre_trt/input_layer1’.
[info] End nodes mapped from original model: ‘Conv_137’.
[info] Translation completed on ONNX model fastbev_pre_trt (completion time: 00:00:01.57)
[warning] hw_arch parameter not given, using the default hw_arch hailo8.
If another device is the target, please run again using one of hailo8, hailo8r, hailo8l, hailo15h, hailo15m, hailo15l, hailo10h
[info] Saved HAR to: /home/mdh/Documents/CUDA-FastBEV/model/resnet18/har_combine/bev_feature.har
Thank you.
