Total instance number: 1 about rn HOT 7 CLOSED

Hi, thanks for your attention to RN!
I believe the problems you posted are caused by the I/O of the model. Specifically, the file lists you maked are not correct and then the pytorch dataset is maked wrongly. You can vim the flist and check if the image paths are correct.

from rn.

i just chenked and unfortunately i donot know wheres the mistake
this is the path of dataset

and this is the flist

from rn.

I've just ran the main.py and it worked well in my machine. Was your python command of training correct?

I suggest you debug step-by-step. And make sure if the model has loaded data correctly first.

from rn.

oh，thanks for your suggestion，i solved the question above！but there is a new problem as follow：

i think my dataset maybe bad？

from rn.

It seems the "self.mask_data" is empty. Are you sure that the masks loading is correct ?

from rn.

yes！you r right！it works after i modify the masks' path.but when i try the eval.py there are some problems as follow


some say it is because

but it did not work. i notice that you just update the code here to support cpu,but my trainning and evaling are all on the centos,could you give some suggestions?

from rn.

It's weird. It works well for my machine. Are you sure the codes you run are the newest?

from rn.