Why are the parameters and calculations of the released code different from those reported in your paper? (resnet50 parameters: 25.56M vs 24.37M; Flops: 4.12G vs 3.86G)
Thanks for your question. Different papers may use different conversion units when calculating the amount of parameters and calculations. The ECA-Net uses 1024.
Why are the parameters and calculations of the released code different from those reported in your paper? (resnet50 parameters: 25.56M vs 24.37M; Flops: 4.12G vs 3.86G)