Replace Conv2d in my network, however it becomes slower, why? about efficient-ai-backbones

[iamhankai]

More details? Which toolkit/hardware did you use?

We test GhostNet on ARM with TFLite.

[FunkyKoki]

Thanks for your reply!
I test the model on Intel i7 CPU with RTX 1080 Ti. The framework I am using is PyTorch(1.2), cuda10.1 is used by the way.
The basic model structure is ReCombinator network as https://github.com/SinaHonari/RCN

[TheGreatWizards]

Same question,I tested under the Darknet framework, and it will be faster when using the CPU, but it will be much slower when using the GPU.

[iamhankai]

Same question,I tested under the Darknet framework, and it will be faster when using the CPU, but it will be much slower when using the GPU.

Your observation is normal. Ghost module is more suitable for ARM/CPU, and not friendly for GPU due to the Depthwise Conv.

[FunkyKoki]

Same question,I tested under the Darknet framework, and it will be faster when using the CPU, but it will be much slower when using the GPU.

Your observation is normal. Ghost module is more suitable for ARM/CPU, and not friendly for GPU due to the Depthwise Conv.

thanks!

[TheGreatWizards]

Thank you for your answer. After using GhostMoudle, I found that the detection speed has slowed down. This has troubled me for a long time.