Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
I try to add one MicroMutableOpResolver<1> micro_op_resolver;
micro_op_resolver.AddFullyConnected()
But the memory has increased by about 150k
Is the increased memory size correct?
Is there a list of how many memories will be generated for each OP added?
I try to add one MicroMutableOpResolver<1> micro_op_resolver; micro_op_resolver.AddFullyConnected()
But the memory has increased by about 150k Is the increased memory size correct? Is there a list of how many memories will be generated for each OP added?