Results on ETIS-LaribPolypDB dataset

[enric1994]

I tried to reproduce your results following your README instructions. I used the default UACANet-L config with a batch size of 8 instead of 32.

The mDICE I get on 3 runs on ETIS-LaribPolypDB is 0.52/0.56/0.53 while in the paper you get 0.76 Can you verify this? Why is the lower batch size affecting only this dataset?

[plemeri]

Hi, thank you for your comment. Images in the ETIS dataset are more high resolution than other datasets, including training dataset. I think that's the reason why it shows lower performance with the small batch size.

[WangZhi-wz]

Could you please tell me how to get the ETIS dataset

[plemeri]

See #12