Skip to content
This repository was archived by the owner on Aug 5, 2022. It is now read-only.

Commit 362a3b3

Browse files
committed
add an instruction to run full INT8 model of ResNet-50 v1.0 test in README.md
1 parent 58d4396 commit 362a3b3

File tree

1 file changed

+8
-0
lines changed

1 file changed

+8
-0
lines changed

README.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,14 @@ If some system tool like numactl is used to control CPU affinity, by default caf
1717
to use more than one thread per core. When less than required cores are specified, caffe will
1818
limit execution of OpenMP threads to specified cores only.
1919

20+
To collect performance on full INT8 model of ResNet-50 v1.0, please update the variables NUM_CORE, the batch size range s_BS and e_BS, and INSTANCES according to your test requirements, then run:
21+
22+
. run.sh
23+
24+
To verify the accuracy, please run
25+
26+
. run_accuracy.sh
27+
2028
## Best performance solution
2129
Please read [our Wiki](https://github.com/intel/caffe/wiki/Recommendations-to-achieve-best-performance) for our recommendations and configuration to achieve best performance on Intel CPUs.
2230

0 commit comments

Comments
 (0)