Kernel Size Discrepancy

digantamisra98 commented 3 years ago

As described in this issue along with many others, the codebase uses a fixated kernel size of 3 for each layer in the ResNet-50 architecture as shown in this code file. However, upon calculation using the adaptive kernel size formula it was found that the kernel size values are [3,5,5,5].

Although the kernel size formula says the values should be [3,5,5,5] and the codebase has values set to be [3,3,3,3], the authors used [3,5,5,7] in their ECANet-50 which is different from the codebase fixed values and the values obtained from the formula.
Additionally, the results for Mask R-CNN which uses the pretrained ResNet-50 backbone has different kernel size [3,3,7,7] than what was originally used to train the ECA-ResNet-50 which was 3,5,5,7. Why was that so?

I would encourage the authors to clarify on the reason behind using different kernel sizes than what is obtained from the kernel size formula presented in the paper which as stated in the paper is used for every experiments.

digantamisra98 commented 3 years ago

Based on my experience of loading the weights for ECANet-50, it seems the authors have set up the kernel sizes manually based on the input tensor size to the bottleneck block and not the ECA layer.