a question about upsampling when training model。

Question

a question about upsampling when training model。

shenhai1895 opened this issue 5 years ago · 2 comments

i find that the ops up0_sum = add([line0, up0]) in denseunet.py is used in the training stage but not in the test stage in . is it right? and why to do it?

Answer 1 · 2019-09-10T05:20:53.000Z

i can't understand that why you delete up0_sum = add([line0, up0]) in denseunet when it predicting.

Answer 2 · 2019-09-10T07:45:24.000Z

i find this function load_weights_from_hdf5_group_by_name_mulgpu_twomodelcombine.
so, when you train the denseunet2d, you use the unet connection, while you delete the unet connection when training the hdenseunet. do i got it?
thank you for your reply.