Runtime: I don't know why the time consumption is basically the same as f-pointnet(baseline) 0.011-0.015 s

[horizon-research]

Runtime: I don't know why the time consumption is basically the same as f-pointnet(baseline) 0.011-0.015 s

[yiyiyin]

I use the code test_time.py

[YuFengUofR]

I don't know where is "test_time.py", if you mentioned test_runtime.py. It depends on what gpu you used. If you used something like Nvidia 1080, there is no speedup, because the network is quite light-compute, tthe GPU resource is good enough for both baseline and our new method. If you want to see the difference, change the code to make the batch_size to be a big number, like 16, you will see the speedup. Our method targets on mobile devices like TX2. If you test on those devices, you will see the significant speedup.

[yiyiyin]

I understand. Thank you

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "horizon-research/Efficient-Deep-Learning-for-Point-Clouds" <[email protected]&gt;; 发送时间:&nbsp;2020年11月24日(星期二) 晚上9:15 收件人:&nbsp;"horizon-research/Efficient-Deep-Learning-for-Point-Clouds"<[email protected]&gt;; 抄送:&nbsp;"3143056486"<[email protected]&gt;;"Author"<[email protected]&gt;; 主题:&nbsp;Re: [horizon-research/Efficient-Deep-Learning-for-Point-Clouds] Runtime: I don't know why the time consumption is basically the same as f-pointnet(baseline) 0.011-0.015 s (#14) I don't know where is "test_time.py", if you mentioned test_runtime.py. It depends on what gpu you used. If you used something like Nvidia 1080, there is no speedup, because the network is quite light-compute, tthe GPU resource is good enough for both baseline and our new method. If you want to see the difference, change the code to make the batch_size to be a big number, like 16, you will see the speedup. Our method targets on mobile devices like TX2. If you test on those devices, you will see the significant speedup. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.