-
gs = gradient(() -> total_loss(img_target, α = 0.1, β=0.01), params(img_target))
Internal error: encountered unexpected error in runtime:
BoundsError(a=Array{Any, (58,)}[
Core.Compiler.VarState(t…
-
博主你好，我下载了您的DeepLearningExamples这个文件。但是解压时显示文件损坏，只能解压出前两个文件，找不到tf2-neural-style-transfer这个文件。请问这种情况该怎么办呢
-
The chainer implementation of Justin's paper "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" uses a script that reduces the model to just the convolutional layers, creating a mod…
-
I tried to run scripts like the one in multigpu examples but still it isn't as nice as prisma. I know that prisma is just derived from this network but still, this should work even better then. It som…
-
Any plan to rewrite this in Tensorflow, since Prof Li is now in Google...
ghost updated
7 years ago
-
Marvellous work! The result is real a magic.
However, one may spend several minutes using this model to generate an output. I think the reason is that this model is based on online image optimizat…
-
I am running slow_neural_style.lua and trying to find the piece of code where I can save the the extracted texture of style image which then is being used to compute the loss. I am checking [this](htt…
-
Great open-source app. Love the feature to define your own convolution matrix. Is there any way to use a specific window instead of the whole desktop as source? I have some OpenCV and other CNN codes…
-
What would it look like if Shakespeare had written Huckleberry Finn, or H.P. Lovecraft had written Harry Potter? I'm going to see if I can find out! There's a recent algorithm that can re-draw picture…
-
I am very interested in this flied and want to run this project. But I do not know what your run environment is