ProGamerGov

@ad48hp I've found that results like those are normally caused by the inputs and parameters that you have chosen. The content image you are using may be affecting the results....

@ad48hp That's because it doesn't have the same layer names as the GoogleNet models. Use the `-print_layers` command when using the model, or check out the list of layer names...

I've added the `-output_start_num` parameter to the master branch, in addition to some other new features and fixes: https://github.com/ProGamerGov/neural-dream/commit/9bea99799e9bd2fb0224ea503d71381fe429439f

@ad48hp Good catch! I'll have to think about how I'd implement such a feature. For the moment though, it's simple enough to manually find the image highest number.

I should mention that if you add `before_` to the layer name of a GoogleNet, Inception, or ResNet model, like adding `before_` to `inception_4d_3x3_reduce` to make `before_inception_4d_3x3_reduce`, the DeepDream layer...

I would expect if there was a memory leak, then usage would increase. I changed a line of code in the update branch that could fix the issue if it...

That looks like it may be a PyTorch bug: https://github.com/NVIDIA/apex/issues/319 https://github.com/pytorch/pytorch/issues/21819 https://discuss.pytorch.org/t/cuda-runtime-error-700-illegal-memory-access/71100/9 It doesn't look like anyone has been able to reliably reproduce the error though.

@SSeanHsu I haven't delved too much into spatial control yet.

@SSeanHsu This project here: https://github.com/martinbenson/deep-photo-styletransfer, has multi-region spatial control in an older version of Neural-Style. But I am having trouble converting the code to the updated Neural-Style code. I separated...

@SSeanHsu This page has information on `torch.gt` and `torch.lt` https://github.com/torch/torch7/blob/master/doc/maths.md They are logical comparison operators, which the creator admit was a lazy way to go about dealing with colored masks:...