std::vector<const char*> input_node_names = { "src", "r1i", "r2i", "r3i", "r4i" };
std::vector<const char*> output_node_names = { "fgr", "pha", "r1o", "r2o", "r3o", "r4o" };
r1i_tensor = mnn_interpreter->getSessionInput(mnn_session, "r1i");
r2i_tensor = mnn_interpreter->getSessionInput(mnn_session, "r2i");
r3i_tensor = mnn_interpreter->getSessionInput(mnn_session, "r3i");
r4i_tensor = mnn_interpreter->getSessionInput(mnn_session, "r4i");
mnn_interpreter->resizeTensor(r1i_tensor, { 1, 16, 135, 240 });
mnn_interpreter->resizeTensor(r2i_tensor, { 1, 20, 68, 120 });
mnn_interpreter->resizeTensor(r3i_tensor, { 1, 40, 34, 60 });
mnn_interpreter->resizeTensor(r4i_tensor, { 1, 64, 17, 30 });
std::fill_n(r1i_tensor->host<float>(), r1i_size, 0.f);
std::fill_n(r2i_tensor->host<float>(), r2i_size, 0.f);
std::fill_n(r3i_tensor->host<float>(), r3i_size, 0.f);
std::fill_n(r4i_tensor->host<float>(), r4i_size, 0.f);
auto device_r1o_ptr = output_tensors.at("r1o");
auto device_r2o_ptr = output_tensors.at("r2o");
auto device_r3o_ptr = output_tensors.at("r3o");
auto device_r4o_ptr = output_tensors.at("r4o");
device_r1o_ptr->copyToHostTensor(r1i_tensor);
device_r2o_ptr->copyToHostTensor(r2i_tensor);
device_r3o_ptr->copyToHostTensor(r3i_tensor);
device_r4o_ptr->copyToHostTensor(r4i_tensor);
// Copyright (c) Microsoft Corporation.
// xutility.h
template
void _Fill_zero_memset(_DestTy* const _Dest, const size_t _Count) {
_CSTD memset(_Dest, 0, _Count * sizeof(_DestTy));
}
input_node_names 和 output_node_names 没看到在哪里用到了，请问这些的rxi_tensor是有什么用处吗？
然后我这里初始化的时候报错了
std::fill_n(r1i_tensor->host<float>(), r1i_size, 0.f);最后报错的地方在这里
// Copyright (c) Microsoft Corporation.
// xutility.h
template
void _Fill_zero_memset(_DestTy* const _Dest, const size_t _Count) {
_CSTD memset(_Dest, 0, _Count * sizeof(_DestTy));
}
这只是一个初始化，怎么看都不应该有问题啊，为什么会报错呢。我把它注掉程序就可以正常运行了，不知道可能是什么原因呢。
然后这边用vulkan的时间反而比CPU更长了，不知道为什么呢？我看python的GPU很快啊