(hailodfc) ermac@Ermac:~/hailo_model_zoo$ hailomz compile yolov8s --ckpt=tscreen.onnx --hw-arch hailo8l --calib-path train/images --classes 4 --performance
hailomz compile: error: argument --hw-arch: invalid choice: ‘hailo8l’ (choose from ‘hailo15h’, ‘hailo15m’, ‘hailo15l’, ‘hailo10h’, ‘hailo10p’)
IM using hailo8l accelerator…
need help…
same issue here. tried on wsl and ubuntu. quite annoying
had same issue, check if you downloaded zoo version 5.0.0 released in july 14. It only supports hailo10 and 15, you need to downgrade the version. But i tried every combination according to the Release versions compatibility table.
CuDNN 9.10, CUDA 12.5, everything as installation guide
2025-01
Dataflow Compilerv3.30.0
HailoRTv4.20.0
Integration Toolv1.20.0
Model Zoov2.14.0
TAPPASv3.31.0
still throwing errors with numpy one requiring lower and one requiring higher i can never satisfy all and makes endless errors no matter how many times i try different combinations. Ive never been more frustrated.
ERROR: pip’s dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
tensorflow 2.12.0 requires numpy<1.24,>=1.22, but you have numpy 2.2.6 which is incompatible.
hailort 4.20.0 requires numpy<2, but you have numpy 2.2.6 which is incompatible.
hailo-dataflow-compiler 3.30.0 requires numpy==1.23.3, but you have numpy 2.2.6 which is incompatible.
First this
hailomz compile: error: argument --hw-arch: invalid choice: ‘hailo8’ (choose from ‘hailo15h’, ‘hailo15m’, ‘hailo15l’, ‘hailo10h’, ‘hailo10p’)
Before this i had errors with alls missing even though its in the right path, then i see it error with yaml even though its there, no matter where i put it,
(hailodfc) jm@JM-431:~$ hailomz compile yolov8s --ckpt=best.onnx --hw-arch hailo8 --calib-path train/images --classes 2 --performance --yaml ~/hailodfc/hailo_model_zoo_clone/hailo_model_zoo/cfg/alls/generic/yolov8s.alls
usage: hailomz compile [-h] [–yaml YAML_PATH] [–ckpt CKPT_PATH] [–hw-arch]
[--start-node-names START_NODE_NAMES [START_NODE_NAMES ...]]
[--end-node-names END_NODE_NAMES [END_NODE_NAMES ...]]
[--model-script MODEL_SCRIPT_PATH | --performance] [--har HAR_PATH]
[--calib-path CALIB_PATH] [--resize RESIZE [RESIZE ...]]
[--input-conversion {nv12_to_rgb,yuy2_to_rgb,rgbx_to_rgb}] [--classes]
[model_name]
hailomz compile: error: argument --yaml: not allowed with argument model_name
no matter if i set command line to set it explicitly,
then i see some folder completely missing
No such file or directory: ‘/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/cfg/cascades’
docker throwing this error, cant pick up gpu
System has not been booted with systemd as init system (PID 1). Can’t operate. Failed to connect to bus: Host is down
(hailodfc) jm@JM-431:~$ hailomz parse --hw-arch hailo8 --ckpt ./best.onnx yolov8s
Start run for network yolov8s …
Initializing the runner…
[info] Translation started on ONNX model yolov8s
[info] Restored ONNX model yolov8s (completion time: 00:00:00.17)
[info] Extracted ONNXRuntime meta-data for Hailo model (completion time: 00:00:00.32)
[info] NMS structure of yolov8 (or equivalent architecture) was detected.
[info] In order to use HailoRT post-processing capabilities, these end node names should be used: /model.22/cv2.0/cv2.0.2/Conv /model.22/cv3.0/cv3.0.2/Conv /model.22/cv2.1/cv2.1.2/Conv /model.22/cv3.1/cv3.1.2/Conv /model.22/cv2.2/cv2.2.2/Conv /model.22/cv3.2/cv3.2.2/Conv.
[info] Start nodes mapped from original model: ‘images’: ‘yolov8s/input_layer1’.
[info] End nodes mapped from original model: ‘/model.22/cv2.0/cv2.0.2/Conv’, ‘/model.22/cv3.0/cv3.0.2/Conv’, ‘/model.22/cv2.1/cv2.1.2/Conv’, ‘/model.22/cv3.1/cv3.1.2/Conv’, ‘/model.22/cv2.2/cv2.2.2/Conv’, ‘/model.22/cv3.2/cv3.2.2/Conv’.
[info] Translation completed on ONNX model yolov8s (completion time: 00:00:00.62)
[info] Saved HAR to: /home/jm/yolov8s.har
(hailodfc) jm@JM-431:~$ hailomz optimize --hw-arch hailo8 --har ./yolov8s.har yolov8s
Start run for network yolov8s …
Initializing the hailo8 runner…
Traceback (most recent call last):
File “/home/jm/hailodfc/bin/hailomz”, line 8, in
sys.exit(main())
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/main.py”, line 122, in main
run(args)
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/main.py”, line 111, in run
return handlers[args.command](args)
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/main_driver.py”, line 220, in optimize
model_script = _extract_model_script_path(
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/main_driver.py”, line 55, in _extract_model_script_path
else resolve_alls_path(networks_alls_script, hw_arch=hw_arch, performance=performance)
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/core/main_utils.py”, line 38, in resolve_alls_path
return path_resolver.resolve_alls_path(Path(hw_arch) / Path("base" if not performance else "performance") / path)
File “/home/jm/hailodfc/lib/python3.10/site-packages/hailo_model_zoo/utils/path_resolver.py”, line 29, in resolve_alls_path
raise FileNotFoundError("no alls found for requested hw_arch")
FileNotFoundError: no alls found for requested hw_arch
try to download the earlier version
git clone -b v2.16 https://github.com/hailo-ai/hailo_model_zoo.git