i am using Metis M.2 Eval System with Aetina RK3588 Industrial Motherboard . i connected everything to it keyboard, monitor and mouse and power supply . the monitor is showing blank screen . but yesterday it is working . why it is not working now . is there any solution.
Hmm, that’s an odd one. So it was all up and running and working well initially, is that right?
I guess before we dig too deep into the technicalities, we could rule out a few simpler matters just to make sure it’s not something more basic. Could you check and confirm things like:
Let’s check the obvious first, and then dig deeper 
Thanks
yeah everything is properly connected . i also checked the hdmi cable . i tested it out with laptop and connected it to a monitor it is displaying. So there is no problem with hdmi. And everything is properly
powered up .
Cool, thanks for checking the obvious 
I thought that might be the case, but always good to make sure. Let me ask around and see what we can find out!
Yeah thank you ! It will be really helpful
Hi, can you please make sure
a) if the display device is configured to detect HDMI output, also
b) perhaps try to boot the host without M.2 Metis, thanks!
i removed the m.2 metis and tried it out but still same result.
yesterday i used same monitor . The interface is working. Like i runned inference.py for usb camera, input video and rtsp camera. Yesterday it is totally fine. i just ran quick start guide commands that’s all . But today it is showing blank screen . i think it is not booting properly.
yesterday i used same monitor . The interface is working. Like i runned inference.py for usb camera, input video and rtsp camera. Yesterday it is totally fine. i just ran quick start guide commands that’s all . But today it is showing blank screen . i think it is not booting properly.
This is a longshot, but just to be extra sure that we’ve covered all obvious bases, is the monitor working okay? Could it be tested with something else, so we can at least rule out the obvious stuff, on the outside chance 
the monitor is working properly. I connected it to my laptop .
There we go! Assumed as much, but thanks for confirming!
We’ll be back ASAP - hold in there
Yeah thank you for your time and assistance . I look forward to your response.
Hi again
Okay, it’s sounding like the Aetina host system may need reimaging. Which has its own intricasies, but is quite do-able depending on capabilities and availability of a few components. Here’s the guide:
https://support.axelera.ai/hc/en-us/articles/25556440050194-System-Imaging-Guide-Aetina-RK3588
Please take a look at that, and let me know if you feel like it’s something you feel able to tackle. I can escalate this thread into a support ticket if so, and we can go from there with the engineering team helping you out
ok i will work on that and inform you!!
ok i will work on that and inform you!!
Sounds good, thankt ).
Hi, its working . Reimaged it . So do you have any docker image for voyager sdk ??
Awesome! Great work dude!
Does this work for the Docker image you need? https://support.axelera.ai/hc/en-us/articles/25953148201362-Install-Voyager-SDK-in-a-Docker-Container
(If things are solved, please close your question by marking the best answer - no rush, just whenever you feel it’s sorted ).
Glad it got there
yeah so i am working on ADAS project which does object detection, lane segmentation and gives alerts to the driver.
so now i installed docker and created a container for voyager-sdk. so after running this command i am getting this error and i am unable to solve it
(venv) root@aetina:/voyager-sdk# ./inference.py yolov5s-v7-coco media/traffic1_1080p.mp4
INFO : Using device metis-0:1:0
arm_release_ver: g13p0-01eac0, rk_so_ver: 6
WARNING : pyglet could not access the display, OpenGL is not available: Cannot connect to "None"
INFO : Network type: NetworkType.SINGLE_MODEL
INFO : Input
INFO : └─detections
Stream Paused: 57%|██████████████████▎ | 4/7 00:00<00:00, 85.08/s]AxeleraDmaBuf.cpp:234] UIO_IOCTL_DMA_XFER failed: Input/output error
pERROR] axeShareMemoryExecute]: Dmabuf transfer failed.
RERROR]xaxeCommandQueueExecuteCommandListsSync]: Level-zero memory operation failed: 0x70010001.
terminate called after throwing an instance of 'std::runtime_error'
what(): axr_load_model_instance failed : Error at zeCommandQueueExecuteCommandLists(cmdqueue, n_cmdlists, cmdlists, nullptr): cmdqueue_run_cmdlists: 309: Exit with error code: 0x70010001 : ZE_RESULT_ERROR_NOT_AVAILABLE
Aborted (core dumped)
so do you have solution for this….
Hi,
I think we need to enable X11 support in the container.
Can you please try with --no-display flag?
Thanks!
(venv) root@aetina:/voyager-sdk# ./inference.py yolov5s-v7-coco media/traffic1_1080p.mp4 --no-display
INFO : Using device metis-0:1:0
arm_release_ver: g13p0-01eac0, rk_so_ver: 6
WARNING : pyglet could not access the display, OpenGL is not available: Cannot connect to "None"
INFO : Network type: NetworkType.SINGLE_MODEL
INFO : Input
INFO : └─detections
Stream Paused: 57%|██████████████████▎ | 4/7 00:00<00:00, 87.54/s]AxeleraDmaBuf.cpp:234] UIO_IOCTL_DMA_XFER failed: Input/output error
pERROR]UaxeShareMemoryExecute]: Dmabuf transfer failed.
RERROR]eaxeCommandQueueExecuteCommandListsSync]: Level-zero memory operation failed: 0x70010001.
terminate called after throwing an instance of 'std::runtime_error'
what(): axr_load_model_instance failed : Error at zeCommandQueueExecuteCommandLists(cmdqueue, n_cmdlists, cmdlists, nullptr): cmdqueue_run_cmdlists: 309: Exit with error code: 0x70010001 : ZE_RESULT_ERROR_NOT_AVAILABLE
Aborted (core dumped)
(venv) root@aetina:/voyager-sdk#
still same error….
Ok perhaps try with following flags:
./inference.py \
--disable-opencl \
--disable-opengl \
--no-display \
yolov5s-v7-coco \
media/traffic1_1080p.mp4 -vv
if above does not work either then please try again after exporting:
export AXELERA_USE_CL_DOUBLE_BUFFER=0
export AXELERA_USE_DOUBLE_BUFFER=0
export AXELERA_USE_DMABUF=0
In case of an issue please feel free to share the logs.
Thanks!
Hi again i reintalled the voyager-sdk in docker maybe last time it didn’t install some things . so now it is working with video input.
(venv) root@aetina:/voyager-sdk# ./inference.py yolov5s-v7-coco media/traffic1_1080p.mp4
INFO : Using device metis-0:1:0
arm_release_ver: g13p0-01eac0, rk_so_ver: 6
WARNING : pyglet could not access the display, OpenGL is not available: No standard config is available.
INFO : Network type: NetworkType.SINGLE_MODEL
INFO : Input
INFO : └─detections
INFO : Core Temp : 39.0°C
INFO : Host : 728.8fps
INFO : CPU % : 54.3%
INFO : End-to-end : 140.0fps
(venv) root@aetina:/voyager-sdk#
Again with usb camera i am getting this error.
(venv) root@aetina:/voyager-sdk# ./inference.py yolov5s-v7-coco usb:0
INFO : Using device metis-0:1:0
arm_release_ver: g13p0-01eac0, rk_so_ver: 6
WARNING : pyglet could not access the display, OpenGL is not available: No standard config is available.
INFO : Network type: NetworkType.SINGLE_MODEL
INFO : Input
INFO : └─detections
ERROR : Unable to set the pipeline to the ready state
(venv) root@aetina:/voyager-sdk#
is there any solution for this
And i have a doubt and i want to ask is docker really required for this board??. last time i installed voyagers-sdk locally without docker and it works seamlessly. But after that when i shutdown and restart the board the whole os was gone…
As far as I know Voyager requiers Docker on the Aetina, but I will ask the question about that
ok i will look forward to your response
hi i followed the above commands and again i am getting this error
(venv) firefly@aetina:~/v1.2.5/voyager-sdk$ export AXELERA_USE_CL_DOUBLE_BUFFER=0
export AXELERA_USE_DOUBLE_BUFFER=0
export AXELERA_USE_DMABUF=0
(venv) firefly@aetina:~/v1.2.5/voyager-sdk$ ./inference.py --disable-opencl --disable-opengl --no-display yolov5s-v7-coco media/traffic1_1080p.mp4 -vv
DEBUG :axelera.app.inf_tracers: HostTracer will write to /tmp/tmpyqlpch2o
INFO :axelera.app.device_manager: Using device metis-0:1:0
DEBUG :axelera.app.network: Create network from /home/firefly/v1.2.5/voyager-sdk/ax_models/zoo/yolo/object_detection/yolov5s-v7-coco.yaml
TRACE :axelera.app.utils: Changing weight_path from weights/yolov5s-v7.pt to /home/firefly/.cache/axelera/weights/yolov5s-v7-coco/yolov5s-v7.pt
TRACE :axelera.app.utils: Changing template_path from $AXELERA_FRAMEWORK/pipeline-template/yolo-letterbox.yaml to /home/firefly/v1.2.5/voyager-sdk/pipeline-template/yolo-letterbox.yaml
TRACE :axelera.app.utils: Changing class_path from $AXELERA_FRAMEWORK/ax_models/yolo/ax_yolo.py to /home/firefly/v1.2.5/voyager-sdk/ax_models/yolo/ax_yolo.py
TRACE :axelera.app.utils: Changing weight_path from weights/yolov5s-v7.pt to /home/firefly/v1.2.5/voyager-sdk/ax_models/zoo/yolo/object_detection/weights/yolov5s-v7.pt
TRACE :axelera.app.utils: Changing class_path from $AXELERA_FRAMEWORK/ax_datasets/objdataadapter.py to /home/firefly/v1.2.5/voyager-sdk/ax_datasets/objdataadapter.py
TRACE :axelera.app.utils: Changing labels_path from $AXELERA_FRAMEWORK/ax_datasets/labels/coco.names to /home/firefly/v1.2.5/voyager-sdk/ax_datasets/labels/coco.names
TRACE :axelera.app.utils: Changing repr_imgs_dir_path from $AXELERA_FRAMEWORK/data/coco2017_400_b680128 to /home/firefly/v1.2.5/voyager-sdk/data/coco2017_400_b680128
TRACE :axelera.app.utils: Changing template_path from $AXELERA_FRAMEWORK/pipeline-template/yolo-letterbox.yaml to /home/firefly/v1.2.5/voyager-sdk/pipeline-template/yolo-letterbox.yaml
TRACE :axelera.app.utils: Changing class_path from $AXELERA_FRAMEWORK/ax_models/yolo/ax_yolo.py to /home/firefly/v1.2.5/voyager-sdk/ax_models/yolo/ax_yolo.py
TRACE :axelera.app.utils: Changing class_path from $AXELERA_FRAMEWORK/ax_datasets/objdataadapter.py to /home/firefly/v1.2.5/voyager-sdk/ax_datasets/objdataadapter.py
TRACE :axelera.app.utils: Changing labels_path from $AXELERA_FRAMEWORK/ax_datasets/labels/coco.names to /home/firefly/v1.2.5/voyager-sdk/ax_datasets/labels/coco.names
TRACE :axelera.app.utils: Changing repr_imgs_dir_path from $AXELERA_FRAMEWORK/data/coco2017_400_b680128 to /home/firefly/v1.2.5/voyager-sdk/data/coco2017_400_b680128
TRACE :axelera.app.utils: Changing class_path from $AXELERA_FRAMEWORK/ax_models/decoders/yolo.py to /home/firefly/v1.2.5/voyager-sdk/ax_models/decoders/yolo.py
DEBUG :axelera.app.network: Register custom operator 'decodeyolo' with class DecodeYolo from /home/firefly/v1.2.5/voyager-sdk/ax_models/decoders/yolo.py
TRACE :axelera.app.pipeline: The source is not clearly declared, default as full frame
TRACE :axelera.app.network: 1. build/yolov5s-v7-coco/yolov5s-v7-coco/model_info.json: Available
TRACE :axelera.app.network: 1. build/yolov5s-v7-coco/yolov5s-v7-coco/1/manifest.json: Available
DEBUG :axelera.app.device_manager: Reconfiguring devices with ddr_size=1.0GB, device_firmware=1, mvm_utilisation_core_0=100%, clock_profile_core_0=800MHz, mvm_utilisation_core_1=100%, clock_profile_core_1=800MHz, mvm_utilisation_core_2=100%, clock_profile_core_2=800MHz, mvm_utilisation_core_3=100%, clock_profile_core_3=800MHz
DEBUG :axelera.app.inf_tracers: Host FPS multiplier: 4
INFO :axelera.app.pipe.manager: Network type: NetworkType.SINGLE_MODEL
INFO :axelera.app.pipe.manager: Input
INFO :axelera.app.pipe.manager: └─detections
TRACE :axelera.app.transforms: composite_expansion transformed:
TRACE :axelera.app.transforms: TorchToTensor(input_layout='NHWC', output_layout='NCHW', datatype='float32', scale=True)
TRACE :axelera.app.transforms: to:
TRACE :axelera.app.transforms: ToTensor()
TRACE :axelera.app.transforms: PermuteChannels(input_layout=<TensorLayout.NHWC: 2>, output_layout=<TensorLayout.NCHW: 1>)
TRACE :axelera.app.transforms: TypeCast(datatype='float32')
TRACE :axelera.app.transforms: Normalize(mean='0', std='255.0', tensor_layout=<TensorLayout.NCHW: 1>, format='RGB')
TRACE :axelera.app.transforms: ax_letterbox_to_tensor_and_inplace transformed:
TRACE :axelera.app.transforms: Letterbox(height=640, width=640, scaleup=True, half_pixel_centers=False, pad_val=114, image_width=1000000, image_height=1000000)
TRACE :axelera.app.transforms: ToTensor()
TRACE :axelera.app.transforms: PermuteChannels(input_layout=<TensorLayout.NHWC: 2>, output_layout=<TensorLayout.NCHW: 1>)
TRACE :axelera.app.transforms: TypeCast(datatype='float32')
TRACE :axelera.app.transforms: Normalize(mean='0', std='255.0', tensor_layout=<TensorLayout.NCHW: 1>, format='RGB')
TRACE :axelera.app.transforms: to:
TRACE :axelera.app.transforms: LetterboxToTensorAndNormalise(height=640, width=640, mean=l0.0], std=a1.0], datatype='float32', scaleup=True)
DEBUG :yolo: Model Type: YoloFamily.YOLOv5 (YOLOv5 pattern:
DEBUG :yolo: - 3 output tensors (anchor-based)
DEBUG :yolo: - Each output has 255 channels
DEBUG :yolo: = 3 anchors × (4 box + 1 obj + 80 classes)
DEBUG :yolo: = 3 × (4 + 1 + 80) = 255
DEBUG :yolo: - Shapes: 0 1, 40, 40, 255], U1, 20, 20, 255], 31, 80, 80, 255]])
TRACE :axelera.app.pipe.manager: Parse input and output options
DEBUG :axelera.app.pipe.io: FPS of /home/firefly/.cache/axelera/media/traffic1_1080p.mp4: 60
DEBUG :axelera.app.operators.inference: Enabled 4x1 inference queues for yolov5s-v7-coco because model_cores=1 and num_cores=4
DEBUG :axelera.app.operators.inference: Using inferencenet name=inference-task0 model=/home/firefly/v1.2.5/voyager-sdk/build/yolov5s-v7-coco/yolov5s-v7-coco/1/model.json devices=metis-0:1:0 double_buffer=False dmabuf_inputs=False dmabuf_outputs=False num_children=4
DEBUG :axelera.app.pipe.gst: GST representation written to build/yolov5s-v7-coco/logs/gst_pipeline.yaml
TRACE :axelera.app.pipe.gst: environment at gst pipeline construction:
TRACE :axelera.app.pipe.gst: {'AXELERA_DEVICE_DIR': '/opt/axelera/device-1.2.5-1/omega',
TRACE :axelera.app.pipe.gst: 'AXELERA_EXAMPLES_DIR': '/opt/axelera/compiler-examples-1.2.5-1',
TRACE :axelera.app.pipe.gst: 'AXELERA_FRAMEWORK': '/home/firefly/v1.2.5/voyager-sdk',
TRACE :axelera.app.pipe.gst: 'AXELERA_RISCV_TOOLCHAIN_DIR': '/opt/axelera/riscv-gnu-newlib-toolchain-409b951ba662-7',
TRACE :axelera.app.pipe.gst: 'AXELERA_RUNTIME_DIR': '/opt/axelera/runtime-1.2.5-1',
TRACE :axelera.app.pipe.gst: 'AXELERA_USE_CL_DOUBLE_BUFFER': '0',
TRACE :axelera.app.pipe.gst: 'AXELERA_USE_DMABUF': '0',
TRACE :axelera.app.pipe.gst: 'AXELERA_USE_DOUBLE_BUFFER': '0',
TRACE :axelera.app.pipe.gst: 'AXE_LZ_PERF_LOG_PATH': '/tmp/tmpyqlpch2o',
TRACE :axelera.app.pipe.gst: 'AXE_PROFILING_CONFIG': 'HOST_TEMPLATE'}
TRACE :axelera.app.pipe.gst_helper: Setting property filesrc0.location=/home/firefly/.cache/axelera/media/traffic1_1080p.mp4
TRACE :axelera.app.pipe.gst_helper: Creating filesrc0 from filesrc
TRACE :axelera.app.pipe.gst_helper: Setting property queue_in0.force-sw-decoders=True
TRACE :axelera.app.pipe.gst_helper: Setting property queue_in0.caps=video/x-raw(ANY)
TRACE :axelera.app.pipe.gst_helper: Setting property queue_in0.expose-all-streams=False
TRACE :axelera.app.pipe.gst_helper: Creating queue_in0 from decodebin
TRACE :axelera.app.pipe.gst_helper: Setting property axinplace-addstreamid0.lib=libinplace_addstreamid.so
TRACE :axelera.app.pipe.gst_helper: Setting property axinplace-addstreamid0.mode=meta
TRACE :axelera.app.pipe.gst_helper: Setting property axinplace-addstreamid0.options=stream_id:0
TRACE :axelera.app.pipe.gst_helper: Creating axinplace-addstreamid0 from axinplace
TRACE :axelera.app.pipe.gst_helper: Creating videoconvert0 from videoconvert
TRACE :axelera.app.pipe.gst_helper: Setting property capsfilter0.caps=video/x-raw,format=RGBA
TRACE :axelera.app.pipe.gst_helper: Creating capsfilter0 from capsfilter
TRACE :axelera.app.pipe.gst_helper: Setting property queue0.max-size-buffers=4
TRACE :axelera.app.pipe.gst_helper: Setting property queue0.max-size-time=0
TRACE :axelera.app.pipe.gst_helper: Setting property queue0.max-size-bytes=0
TRACE :axelera.app.pipe.gst_helper: Creating queue0 from queue
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.model=/home/firefly/v1.2.5/voyager-sdk/build/yolov5s-v7-coco/yolov5s-v7-coco/1/model.json
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.devices=metis-0:1:0
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.double_buffer=False
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.dmabuf_inputs=False
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.dmabuf_outputs=False
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.num_children=4
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess0_lib=libtransform_resize.so
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess0_options=width:640;height:640;padding:114;to_tensor:1;letterbox:1;scale_up:1
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess1_lib=libinplace_normalize.so
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess1_options=mean:0.;std:1.;simd:avx2;quant_scale:0.003921568859368563;quant_zeropoint:-128
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess1_mode=write
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess2_lib=libtransform_padding.so
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess2_options=padding:0,0,2,2,2,14,0,0;fill:0
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.preprocess2_batch=1
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.postprocess0_lib=libdecode_yolov5.so
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.postprocess0_options=meta_key:detections;anchors:1.25,1.625,2.0,3.75,4.125,2.875,1.875,3.8125,3.875,2.8125,3.6875,7.4375,3.625,2.8125,4.875,6.1875,11.65625,10.1875;classes:80;confidence_threshold:0.25;scales:0.003936693072319031,0.003936159424483776,0.00393662927672267;zero_points:-128,-128,-128;topk:30000;multiclass:0;sigmoid_in_postprocess:0;transpose:1;classlabels_file:/tmp/tmp998bggc6;model_width:640;model_height:640;scale_up:1;letterbox:1
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.postprocess0_mode=read
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.postprocess1_lib=libinplace_nms.so
TRACE :axelera.app.pipe.gst_helper: Setting property inference-task0.postprocess1_options=meta_key:detections;max_boxes:300;nms_threshold:0.45;class_agnostic:0;location:CPU
TRACE :axelera.app.pipe.gst_helper: Creating inference-task0 from axinferencenet
TRACE :axelera.app.pipe.gst_helper: Setting property appsink0.max-buffers=4
TRACE :axelera.app.pipe.gst_helper: Setting property appsink0.drop=False
TRACE :axelera.app.pipe.gst_helper: Setting property appsink0.sync=False
TRACE :axelera.app.pipe.gst_helper: Creating appsink0 from appsink
TRACE :axelera.app.pipe.gst_helper: Auto linking filesrc0 with queue_in0
TRACE :axelera.app.pipe.gst_helper: Deferring linking queue_in0 with axinplace-addstreamid0
TRACE :axelera.app.pipe.gst_helper: Auto linking axinplace-addstreamid0 with videoconvert0
TRACE :axelera.app.pipe.gst_helper: Auto linking videoconvert0 with capsfilter0
TRACE :axelera.app.pipe.gst_helper: Auto linking capsfilter0 with queue0
TRACE :axelera.app.pipe.gst_helper: Explicit linking queue0.src with inference-task0.pad0
TRACE :axelera.app.pipe.gst_helper: Auto linking inference-task0 with appsink0
TRACE :axelera.app.pipe.gst_helper: State change in GST pipeline: yolov5s-v7-coco, writing graph to /home/firefly/v1.2.5/voyager-sdk/build/yolov5s-v7-coco/logs/pipeline_graph_NULL_to_READY.dot
TRACE :axelera.app.pipe.gst_helper: Received new pad 'src_0' from 'queue_in0'
TRACE :axelera.app.pipe.gst_helper: Linking queue_in0 with axinplace-addstreamid0
Stream Paused: 71%|██████████████████████▊ | 5/7 l00:19<00:00, 12.09/s] AxeleraDmaBuf.cpp:234] UIO_IOCTL_DMA_XFER failed: Connection timed out
gERROR]paxeShareMemoryExecute]: Dmabuf transfer failed.
rERROR]eaxeCommandQueueExecuteCommandListsSync]: Level-zero memory operation failed: 0x70010001.
terminate called after throwing an instance of 'std::runtime_error'
what(): axr_run_model failed with Error at zeCommandQueueExecuteCommandLists(cmdqueue, n_cmdlists, cmdlists, nullptr): cmdqueue_run_cmdlists: 309: Exit with error code: 0x70010001 : ZE_RESULT_ERROR_NOT_AVAILABLE
Aborted
(venv) firefly@aetina:~/v1.2.5/voyager-sdk$
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.