saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-24 02:47:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Optimize concat PrepareForCompute perf by reserve vector size. (#1198)

Browse source
This commit is contained in:
ybrnathan 2019-06-10 12:54:17 -07:00 committed by GitHub
parent 97dfd5ee21
commit f72c1501c5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
onnxruntime/core/providers/cpu/tensor/concat.cc
View file

@ -80,6 +80,7 @@ Status ConcatBase::PrepareForCompute(OpKernelContext* ctx, int input_count, Prep
p.output_axis_pitch = 1;
for (size_t i = inputs_0_rank; i-- > axis;) p.output_axis_pitch *= dims[i];
p.inputs.reserve(input_count);
for (int input_index = 0; input_index < input_count; input_index++) {
const Tensor* data_n_ptr = ctx->Input<Tensor>(input_index);
auto& data_n = *data_n_ptr;