Yancheng Wang

Hi, the Efficientnet Flops computed in mmclassification are quite different from the official paper. Why is it

yea, I also found it. I added the Conv2dAdaptivePadding to the 'get_modules_mapping()' function.

> Have you gotten the relatively correct flops of Efficientnet? yes, I got the relatively correct flops, but I'm not very sure if it's precise enough.

> Hi, I just modified the efficientnet flops results in README.md as well as the model_zoo.md on my repo.

> you can create a PR refer to this [doc](https://mmclassification.readthedocs.io/en/latest/community/CONTRIBUTING.html). welcome your contribution to MMClassification. I created it just now

Hi, 已上传测试数据

应该要改路径 -- ———————— 王焱乘 在 2020-11-11 15:58:46，"mstc-xqp" 写道： Hi, 已上传测试数据 感谢大佬！！！ 是运行test.py 就好了嘛 — You are receiving this because you commented. Reply to this email directly, view it on GitHub,...

NTU_voxelz40_feature_2048 对，这个就是生成的3DV数据 -- ———————— 王焱乘 在 2020-11-11 16:25:14，"mstc-xqp" 写道： 应该要改路径 … -- ———————— 王焱乘 在 2020-11-11 15:58:46，"mstc-xqp" [email protected] 写道： Hi, 已上传测试数据 感谢大佬！！！ 是运行test.py 就好了嘛 — You are receiving this because...

这里有两个文件路径分别对应着3DV数据和depthpoint 数据 -- ———————— 王焱乘 在 2020-11-12 15:12:16，"mstc-xqp" 写道： NTU_voxelz40_feature_2048 对，这个就是生成的3DV数据 … -- ———————— 王焱乘 在 2020-11-11 16:25:14，"mstc-xqp" [email protected] 写道： 应该要改路径 … -- ———————— 王焱乘 在 2020-11-11 15:58:46，"mstc-xqp" [email protected] 写道：...

Thanks for your kindly comments. The 'cc' should be 'motion'