Neural-Style-MMD

Neural-Style-MMD copied to clipboard

I have tried the bn-loss but it always returns nan gradient and loss. So I want to know what's wrong with it.

wadx2019

mmd_loss line 43

1

Hi, in `line 43` of `mmd_loss.py`, you wrote `dot(x, x.T)`, I think it should be `dot(x.T, x)`, correct?

chanshing

Thxs for sharing the codes. However the experiments with Gaussian kernel seems terrible.  this is with style weight 2.0.

wzc118

neural-style.py line 270 print np.prod(content_array[0].shape)

cicido

confusion in Linear Kernel Loss functions

1

I'm trying to understand the code but unable to understand your loss calculation function can you please explain what are you doing because it doesn't seem you are doing anything...

allugrasm

The paper might has a mistake

1

In the paper "Demystifying Neural Style Transfer", there might be a mistake, which will make Equation (8) incorrect. For a layer L (in the paper, the authors used the lowcase...

michaelhuang74

error happens when running at "gnorm = mx.nd.norm(model_executor.data_grad).asscalar()" in /mnt/d/mahao/codes/Neural-Style-MMD/neural-style.py: MXNetError: Check failed: reinterpret_cast( params.info->callbacks[kCustomOpForward])( ptrs.size(), const_cast(ptrs.data()), const_cast(tags.data()), reinterpret_cast(req.data()), static_cast(ctx.is_train), params.info->contexts[kCustomOpForward]):

fido20160817