Mobile AI 2021 Learned Smartphone ISP Challenge Forum

Go back to competition Back to thread list Post in this thread

> Tflite runtime error

hi All:
I get an error when submiting. the scoring error log as follow:

WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
* daemon not running; starting now at tcp:5037
* daemon started successfully
WARNING: linker: Warning: "/data/local/tmp/MAI_21/benchmark_model" unused DT entry: DT_RPATH (type 0xf arg 0x951) (ignoring)
INFO: Initialized TensorFlow Lite runtime.
INFO: TFLiteNeuronDelegate delegate: 75 nodes delegated out of 75 nodes with 1 partitions.

INFO: Init
INFO: BuildGraph
INFO: AddOpsAndTensors
INFO: AddOpsAndTensors done
INFO: total_input_byte_size: 8355840
INFO: total_output_byte_size: 25067520
INFO: NeuronModel_identifyInputsAndOutputs
INFO: NeuronModel_relaxComputationFloat32toFloat16: 1
INFO: NeuronModel_finish
INFO: BuildGraph done
INFO: NeuronCompilation_setPreference: 1
INFO: NeuronCompilation_setPriority: 110
ERROR: Neuron returned error NEURON_UNMAPPABLE at line 778 while completing Neuron compilation.

ERROR: Node number 75 (TFLiteNeuronDelegate) failed to prepare.

ERROR: Restored original execution plan after delegate application failure.
Failed to apply NeuronDelegate delegate.
Benchmarking failed.
Traceback (most recent call last):
File "/tmp/codalab/tmpn0lChm/run/program/evaluation.py", line 174, in <module>
file = open(LOG_NAME, 'r')
IOError: [Errno 2] No such file or directory: '/tmp/codalab/tmpn0lChm/run/output/output.csv'

the tflite is converted under the window 8 by your provided code ,the version of tensorflow is 1.15.0

Could you please give me some suggestions. Thanks a lot.

Posted by: aijisong @ March 3, 2021, 2:15 p.m.

Hi,

We had revise the evaluation flow to avoid some unexpected crash. Please try again w/ new submission.

Posted by: HsienKaiKuo @ March 4, 2021, 8:32 a.m.
Post in this thread