Chang

Very nice work！

My acc value is very high at the beginning, is it over fitting

博主您好，我刚刚开始接触这个， 请问focal loss中的Binary和ori这两个focal loss有什么不同呢？ 谢谢！

About the dataset

1

Thank you very much for your code work. Where can I download the dataset? Can you give me a download link

Questions about testing

1

Hello author, thank you very much for your work！ Does test_list_fid refer to the list of test files in npz format (so get: np.savez(npz_pth, data_arr, label_arr))？ Does test_nii_list_fid refer to...

Some problems were encountered when migrating google attention to other codes

3

Hello author！ Thanks for your code！ In this function： def hw_flatten(x) : return tf.reshape(x, shape=[x.shape[0], -1, x.shape[-1]]) my x.shape[0] is None, how can I change the code?