未验证 提交 0a232a00 编写于 作者: G gmm 提交者: GitHub

fix benchmark (#6361)

上级 5d749951
......@@ -52,7 +52,7 @@ inference:./deploy/pptracking/python/mot_jde_infer.py
===========================train_benchmark_params==========================
batch_size:6|22
fp_items:fp32|fp16
epoch:1
epoch:2
--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
flags:null
===========================infer_benchmark_params===========================
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册