the prediction results are all black

[ARnnn]

I fixed the errors in the model prediction in the same way as you, but now the prediction results are all black. What's the problem. What I did was a dichotomy. During the test, there was such a warning:

[ARnnn]

I solved the above problem, but the predicted result looks very bad

the tensorboard is as follows：

[MontaEllis]

I can't see your tensorboard.

[ARnnn]

I can't see your tensorboard.

[MontaEllis]

Can I see your hparam.py? I guess you set 'croporpad' in a wrong way.

[ARnnn]

I set the same parameters of hparam.py as you

[ARnnn]

I haven't changed anything except my own dataset

[MontaEllis]

You should modify 'croporpad' at your own dataset.

[ARnnn]

Different cases in my data have different sizes，so how can I set the croporpad according to my own data?

[ARnnn]

In many slices in my case, some contain the parts to be segmented and some do not (the label is all black). Do I need to remove the slices that do not contain the parts to be segmented?

[MontaEllis]

Yes.