hi @kazum, Sorry for the late response.
Can you run tests/ios_rpc_test.py successfully? --> Yes I'm able to run the
ios_rpc_test.py and got the results for both iPhone CPU and Metal target.
Your tuning script can run against the llvm target? --> Yes, I'm able to tune
the model on llvm target
in java: x.copyFrom(datax) is OK
but in C/C++: the cpu is ok ,Why does the opencl copy fail? i use
TVMArrayAlloc or CopyFrom ,All failed to be copied
---
TVMArrayAlloc
=
2020-09-07 03:14:48.834 7659-
This is so basic question, but I can't calculate VTA GOPs in batch 1, block in
4, block out 4, clock 142MHz which is Get Started with VTA tutorial.
With the model, VTA have 16Mac so in my calcuation
16 Mac / GEMM * 142 MHz = 2.272GOPs
But I know this is not the correct answer. I want to kn
Hi Experts:
I have one doubt as the title says. The following code return empty:
::tvm::runtime::PackedFunc get_num_inputs =
_infer->GetFunction("get_num_inputs");
if (get_num_inputs == nullptr)
{
int num_inputs = 1;
