Donghee Son comments

Results 8 comments of


                                            Donghee Son

The size of tensor a (16) must match the size of tensor b (4) at non-singleton dimension 0

Please let me know the command you used. It will be helpful!

processing data set

It will be helpful to let me know the error message and dataset directory structure.

Does it only test the input size (1280, 720) ?

I found an error if the test input size is not proper. So I will fix it soon If you want test on your own images, It seems better to...

Intermediate results during training

I will fix the code soon. So I will update the results you want.

TypeError: unsupported operand type(s) for /: 'str' and 'float'

Please let me know the command line you used. It will be helpful! Thank you and sorry for late reply.

Value error : setting an array element with a sequence

In my environment, the code works without the error. It will be helpful to let me know the command you used. Thank you!

Value error : setting an array element with a sequence

Are you using multi-gpu? The code is assumed to run in single gpu environment If you use multi-gpu environment, use this command CUDA_VISIBLE_DEVICES=0 python main.py ....

If "RCAN_X2.data-00000-of-00001", "RCAN_X2.index", "RCAN_X2.meta" files are in directory ./model/RCAN_X2, the option should be "./model/RCAN_X2/RCAN_X2" If the error is not solved, please let me know. Thank you!