Skip to content

Commit

Permalink
modify yxt (PaddlePaddle#37)
Browse files Browse the repository at this point in the history
* updata_yxt

* update_yxt

* add_yxt

* update_yxt

* update_yxt

* update_yxt
  • Loading branch information
tink2123 authored and shanyi15 committed Aug 14, 2018
1 parent c46c7ba commit ea2ed59
Show file tree
Hide file tree
Showing 23 changed files with 2,446 additions and 73 deletions.
1 change: 0 additions & 1 deletion source/advanced_usage/deploy/anakin_arm_benchmark.md
Original file line number Diff line number Diff line change
Expand Up @@ -54,4 +54,3 @@
3. 接着在测试机含有Anakin model的目录中运行'./benchmark_arm ./ anakin_model.anakin.bin 1 10 10 1' 命令
4. 最后,终端显示器上将会打印该模型的运行时间
5. 其中运行命令的参数个数和含义可以通过运行'./benchmark_arm'看到

29 changes: 28 additions & 1 deletion source/advanced_usage/deploy/anakin_example.md
5 changes: 0 additions & 5 deletions source/advanced_usage/deploy/anakin_gpu_benchmark.md
Original file line number Diff line number Diff line change
Expand Up @@ -168,8 +168,3 @@ We tested them on single-GPU with single-thread.
> 2. Switch to *source_root/benchmark/CNN* directory. Use 'mkdir ./models' to create ./models and put anakin models into this file.
> 3. Use command 'sh run.sh', we will create files in logs to save model log with different batch size. Finally, model latency summary will be displayed on the screen.
> 4. If you want to get more detailed information with op time, you can modify CMakeLists.txt with setting `ENABLE_OP_TIMER` to `YES`, then recompile and run. You will find detailed information in model log file.




Loading

0 comments on commit ea2ed59

Please sign in to comment.