Legacy ImageMagick Discussions Archive

In a follow up to my previous post about the original tile 3 showing signs of drift, I tried this: I did this for the original tile 3: convert 1200px-Canaletto_-_Bucentaur.jpg 1200px-Sandro_Botticelli.jpg russian.jpg -append -background transparent line.miff ./transfercolor.sh -c rgb neuraldream_3.p...

So trying this: convert 1200px-Canaletto_-_Bucentaur.jpg 1200px-Sandro_Botticelli.jpg russian.jpg -append -background transparent line.miff And convert neuraldream_0.png neuraldream_1.png neuraldream_2.png neuraldream_3.png -append -background transparent line.miff And then both lab and rgb: ./trans...

It may be due to your Unix system. Some need ! escaped to \!. So I am sending you via direct email a new version with that change. Let me know if that fixes the issue. It's still giving the same error. Here's the -xv output of trying to run the script: https://gist.github.com/ProGamerGov/9282913237...

fmw42 wrote: ↑2017-01-29T14:07:17-07:00

The transfercolor2 script seems to result in this error constantly:

What is your IM version and platform? I think some variable is not getting computed, which could be due to an IM version difference.

The output of convert -version:

Also, from my earlier post containing lots of data on the tiles, I noticed this: Unprocessed tiles: Tile 0: mean=27582.4 std=13036.9 Tile 1: mean=25540.2 std=14461.4 Tile 2: mean=27393.2 std=15110.1 Tile 3: mean=33869.1 std=11170.8 Processed Tiles: Tile 0: mean=26306.6 std=13965.7 Tile 1: mean=26522...

Sorry, I did not mean for you to have to list all the verbose data. Just wanted you to compare the overall mean and std. I probably should have had you use "%[fx:mean]" and "%[fx:standard_deviation]" so that you get the normalized mean and std in the range of 0 to 1 or "%[f...

So if all your convert input images have very close statistics, the results from using only one and from using all of them won't be too different. You should look at the mean and std of each of your input images using identify -verbose image or convert image -format "mean=%[mean] std=%[standar...

You list linecolor.png in the first convert command, but you use line.png in the transfercolor script. Are these the same images? They are the same image. So if all your convert input images have very close statistics, the results from using only one and from using all of them won't be too differen...

I suggest you resize so the input is no more than, say, 100,000 pixels. For calculating mean and standard deviation, this won't make a significant difference. So testing this out, created this output: https://i.imgur.com/EYa7fos.jpg I made the image to transfer the color from like this: convert Can...

If your images are not the same size, you can still append them with a transparent background to fill in. I can then modify my script to compute the mean and std so as to ignore the transparent pixels. Let me know if this is needed. For the airplane image and the other image, I used 3 gigapixel sty...

If you need more input images, just append them first and use that as the reference image. If you need to apply one image's color to many output images, then you would need to write a script over all the output images. convert image1 image2 image3 ... -append miff:- | transfercolor <arguments> - ou...

So thinking more about how Neural-Style works, and how various GIMP operations affected my output images, I think that better results could be obtained by using the transfercolor.sh script with my style image(s) and the tiles. But the issue that the transfercolor.sh script only accepts one image to ...

So I tried this combination of techniques on another image: Uncorrected tiled output: https://i.imgur.com/gvhK5VQ.jpg Corrected tile output: https://i.imgur.com/UedL6gc.jpg Uncorrected transferred to corrected via RGB: https://i.imgur.com/IOH21D1.jpg I feel like there is something missing, as while ...

Experimenting father with the transfercolor script: Transfer color from original tile to the new tile using a command like this: ./transfercolor.sh -c lab plane_0_n.png plane_0_o.png plane_0.png Then I transfer the color of the normal tiled output image, to the new tiled output image composed of co...

The link to the paper and to https://github.com/jcjohnson/neural-style are very interesting and clever transfer of styles from one image to another. But I imaging it takes lots of computing power or GPU? GPUs are better at the specific kinds of mathematical operations that deep learning uses by ord...