kernel size in primary convolution of Ghost module about efficient-ai-backbones

[YUHAN666]

@dyj1234567890 Not yet, but when applied on my own project, the GhostNet trained with default setting of this code has the best performance among all the backbone I have tried.

[iamhankai]

The code is not clean enough. kernel set in _CONV_DEFS_0 for bottleneck of stride=1 is useless.

[YUHAN666]

So the kernel size of primary convolution in Ghost module is fixed to [1, 1] by default?

[YUHAN666]

https://github.com/huawei-noah/ghostnet/blob/4ccf0993cec68a0b04faeea3271a14b453a96d9b/ghost_net.py#L288-L289
https://github.com/huawei-noah/ghostnet/blob/4ccf0993cec68a0b04faeea3271a14b453a96d9b/ghost_net.py#L270-L271

[iamhankai]

Yes, the kernel size of primary convolution in Ghost module is fixed to [1, 1] by default.

[YUHAN666]

Have you tried with larger size?

[KnightWin123]

Have you tried with larger size?

I have the same question

[iamhankai]

@YUHAN666 @dyj1234567890 Not yet.

[KnightWin123]

@YUHAN666 Have you tried with larger size?