标题: rk3588板端调试推理出错各位大佬,在进行板端调试步骤中:E RKNN: [20:12:50.280] failed to submit!,op id: 143, op name: OutputOperatorutput, flags: 0x1, task start: 0, tasknumber: 350, run task counter: 328, int status: 0
使用rknn_toolkit_lite2在RK3588上部署模型,运行rknn_lite.inference时出现E RKNN: failed to submit! Op id:3 , op name: conv:inputs.3_Conv_pads_conv, flags: 0x5, task start:0,task number:218,run task number:218 , run task counter: 146 int status: 0模型推理精度大幅下降。
This model I ran in the PC RKNN simulation is through, no failed to submit, but in the 3588 board with rknn-toolkit-lite run will have problems. This is an EEGnet model, similar to mobilenet, and there should not be a problem of unsupported operators. RKNN mode load over init runtime ...
I wasn’t lucky with the yolov8s.rknn , failed to submit. My first attempt with yolo8m.rknn did not fail to submit but need to adjust something to work with coco. Trying to recover from my eMMC disaster, let’s see what i can get…Dion...
Modified the neural netwotk structure forRK3588NPU to avoid the "Failed to submit" error.Only ...
disconnected.failed to submit UVC request, finally, No realsense device were found!"Collaborator MartyG-RealSense commented Oct 27, 2022 • edited Hi @lantianhaohh Adding additional RealSense cameras places extra processing burden on the computer and consumes more of its computing resources. If ...
Did you make any change to the model? milas: E RKNN: [17:33:58.876] failed to submit!, op id: 12, op name: Add:/model.2/m.0/Add, flags: 0x5, task start: 3410, task number: 3, run task counter: 0, int status: 0 rknn run error -1 ...
Modified the neural netwotk structure forRK3588NPU to avoid the "Failed to submit" error.Only ...
[ 173.939837] rga_mm: failed to map buffer [ 173.939842] rga_job: rga_job_commit: failed to map job info [ 173.939852] rga_job: request[730] task[0] job_commit failed. [ 173.939857] rga_job: rga request commit failed! [ 173.939859] rga: request[730] submit failed!
I'm relatively new to the ARM scene and not very adept at reading device schematics however if I can reverse engineer the values from the T6 to understand how this is mapped I should be able to clean this up and submit a PR. @mariobalanica Maybe you can give me a simple example of...