limbee / NTIRE2017

Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"
651 stars 146 forks source link

MDSR not working #11

Closed owang closed 6 years ago

owang commented 7 years ago

Hi, I am having some trouble running the demos. if I run

th test.lua -model EDSR_x2 -selfEnsemble false

it works fine, but then when I run

th test.lua -model MDSR -scale 2 -selfEnsemble false

I get this error:

Model: [MDSR]
This is a multi-scale model! Swap the model
/opt/torch/install/bin/luajit: test.lua:64: attempt to index a nil value
stack traceback:
    test.lua:64: in function 'swap'
    test.lua:222: in main chunk
    [C]: in function 'dofile'
    /opt/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
    [C]: at 0x00406670

or if I run

th test.lua -model EDSR_x4 -selfEnsemble false

I get this error:

Model: [EDSR_x4]
>> [1/3]    2276523950_e06e9065b2_z.jpg /opt/torch/install/bin/luajit: /NTIRE2017/code/utils.lua:313: bad argument #1 to 'copy' (sizes do not match at /opt/torch/extra/cutorch/lib/THC/THCTensorCopy.cu:31)
stack traceback:
    [C]: in function 'copy'
    /NTIRE2017/code/utils.lua:313: in function 'chopForward'
    /NTIRE2017/code/utils.lua:320: in function 'chopForward'
    test.lua:252: in main chunk
    [C]: in function 'dofile'
    /opt/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
    [C]: at 0x00406670

Any idea what I am doing wrong? Thanks!

sanghyun-son commented 7 years ago

Hi.

Maybe there was a mistake when we re-named the model. We will re-upload the model as soon as possible.

Please check https://drive.google.com/open?id=0B_riD-4WK4WwOE9PV0RfN3M2QXM to download the right MDSR before we fix the link.

Also, for the EDSR scale 4 model, would you send us your test images?

We will check the error and fix it.

Thank you.

owang commented 7 years ago

Thanks, the new model works great!

For EDSRx4, it happens on any image I tried. For example, this one from your webpage: https://github.com/LimBee/NTIRE2017/blob/master/figs/result/result_1.jpg

sanghyun-son commented 7 years ago

Oh, to run the EDSR / MDSR with scale, you have to specify it with -scale argument. (Because default scale is 2)

For example, th test.lua -model EDSR_x4 -scale 4 -selfEnsemble false