results in shadows about hdr-expandnet HOT 21 CLOSED

Hey, what do you mean by shadows? Is it the band on the right and bottom? Also, can you include your input image?

from hdr-expandnet.

Hi, thank you for your reply.
The shadow I said means that the square inside looks darker.
input

output

from hdr-expandnet.

Hm.. I just ran it and the .hdr output looks fine. Did you use any other arguments when you ran it?

from hdr-expandnet.

This is the (reinhard) tone mapped prediction I get.

Which version of PyTorch are you using?

from hdr-expandnet.

I did not use other arguments. I run this code according to the Readme, and the instruction is python expand.py ldr_input.jpg
And I am using the version of PyTorch is 0.3.1

from hdr-expandnet.

This is weird. I am using version '1.0.0a0+bcb62cb' of PyTorch but things shouldn't be any different for torch > 0.3.

How are you creating the tone mapped version of the prediction that you attach here?

from hdr-expandnet.

I think this problem has nothing to do with the tone mapping operator.
I tried the function tonemap in MATLAB, and there will still be obvious boundaries(as shown below).

from hdr-expandnet.

I just installed a new environment with PyTorch 0.3.1 and I couldn't reproduce the problem. Have you tried rerunning it? It kinda looks like the operation was stopped midway.

from hdr-expandnet.

Thank you very much, you are an enthusiastic person！！
I used pip install OpenCV not conda install opencv -c menpo. Does this have an impact on results?

from hdr-expandnet.

No worries. Yeah that could cause some problems but I don't think that that's the problem in this case. Can you reproduce this effect if you run it for a second time?

from hdr-expandnet.

I ran it for a second time and tested other inputs. It still has problem with boundaries.
input

output

input

output

from hdr-expandnet.

does the problem remain if you use a different patch size?
e.g.
python expand.py img.jpg --patch_size 128

from hdr-expandnet.

It seems smaller

from hdr-expandnet.

It looks like there might be a bug with the patch indexing, I'll try and reproduce it/figure it out some time later today.

from hdr-expandnet.

In the meantime, can you email me the actual images you are using as inputs? There might be some downsampling going on in the ones attached here. Or jist let me know the original dimensions

from hdr-expandnet.

Ok. Thanks again.

from hdr-expandnet.

Hey, I managed to reproduce the effect and i think i fixed it. Can you please try again and let me know?

from hdr-expandnet.

The boundary still exists.
And I use python2.7 which not support print(,end=''), but it will not affect the results.

from hdr-expandnet.

Hey, you should have opened with that :). Python 2.7 was not supported, but you are right, it wasn't mentioned anywhere.

I managed to reproduce exactly what you had in a Python 2.7 environment. The problem was division (and printing). I added the imports and it should work now. Please let me know.

from hdr-expandnet.

Hi, It works now！ Thank you very much!
So the problem was division because of python vision.
Thanks again！
(reinhard)

from hdr-expandnet.

No worries, glad to help!

from hdr-expandnet.