allen

In the initial cycle, the time consumption is relatively small, and the later time is very much, such as: First serval loop(include step1 and step2) at main function toatl3 cost...

In the long running time, the memory and CPU are not changed too much, which is basically the same as before.

yes , i used is high_resolution_clock::now()

i use the ORT performance separately with no thread pools ，the same time as before @skottmckay

> It would be best to measure the ORT performance separately with no thread pools, and without the inline call to GetInputNames(). That way you're just measuring the cost of...

by gdb: 0x00007efd417a01a9 in onnxruntime::concurrency::ThreadPool::RunInParallel(std::function, unsigned int) () from /usr/local/lib64/libonnxruntime.so.1.6.0 Missing separate debuginfos, use: debuginfo-install libgcc-4.8.5-44.el7.x86_64 libstdc++-4.8.5-44.el7.x86_64 libuuid-2.23.2-65.el7.x86_64 (gdb) bt #0 0x00007efd417a01a9 in onnxruntime::concurrency::ThreadPool::RunInParallel(std::function, unsigned int) () from /usr/local/lib64/libonnxruntime.so.1.6.0 #1...

do you fixed it ? i used tensorflow 1.14 cuda 10.0 cudnn 7.6 have same problem.

i have the same problem, config two processs and one thread, the GPU memory only increases sometimes. > In one of the threads, you asked about adding processes in Python....

我也有这个问题，如何解决呢

问题也不回复，代码也没有看到更新。