I AM A PRODUCT MANAGER

@Zehaos 想问下gpu的3ms是怎样的条件，我在TITANX上无法稳定复现3ms

2017-08-15 10:53:28.821269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/gpu:0) -> (device: 0, name: TITAN Xp, pci bus id: 0000:02:00.0, compute capability: 6.1) 2017-08-15 10:53:31.591376: step 0, duration = 0.008 2017-08-15 10:53:31.655964:...

TITAN Xp 和 TITANX Pascal 均尝试过，这两个有很大差异吗？

2017-08-15 11:06:14.477316: step 890, duration = 0.006 2017-08-15 11:06:14.517504: step 900, duration = 0.005 2017-08-15 11:06:14.550230: step 910, duration = 0.003 2017-08-15 11:06:14.579801: step 920, duration = 0.003 2017-08-15 11:06:14.615377:...

@Zehaos 有尝试过将inception或者其他的网络中的卷积转换为depthwise这种结构吗，我试验的结果不太理想

想问下，shuffle Channel 具体的操作是怎样的，看了论文也不太清楚具体的操作，是直接任意打乱再均分到下一层不同group,还是有其它的做法，还有就是反传的时候会对shuflle Channel 有什么调整吗，谢谢

@farmingyard Here is my test for shufflenet with caffe_time (TITAN xp) Average Forward pass: 9.85734 ms. Average Backward pass: 9.51034 ms. And the test for mobilenet you recommended (from https://github.com/farmingyard/caffe-mobilenet...

我现在测试 center loss 越来越大