Text generation with LSTM

A long time ago I remember I first tried an LSTM implementation in Torch, trying to generate text based on some large text corpus from shakespear (see reference below). The result that could be achieved at that time were already quite surprising. But now I want to give this concept another try. Except that this time, it should be implemented in Tensorflow instead of torch. SO let's get started!

→ Read more...

2019/02/12 21:23

Neural style simulation with tensorflow

I've been away from my blog a bit too long already, but well, the past is the past, and we can't change it. So let's focus on the present and future anyway! Today I wan't to give a try to the so called “neural style” concept, where we can input an image, and say a painting with a “given style”, and get that style applied on the input image.

→ Read more...

2019/02/11 17:36

Using tensorflow queue system with CIFAR dataset

So my first experiment on the CIFAR-10 dataset wasn't that successful. And I current think this must be because I wasn't using all the data augmentation technique suggested in the refenrece book, because I didn't want to introduce the tensorflow queueing system into my pipeline, and preprocessing all the data with numpy only prooved too complex for me :-).

But now I'm back, and this time we are going to handle this queueing mechanism as expected.

→ Read more...

2019/01/12 08:49

SpinLock implementation in C++

Since I read the book Game Engine Architecture I was looking for a way to implement a simple SpinLock in C++. And actually it turns out this is (almost) readily available from boost.

→ Read more...

2019/01/04 10:25
,

CIFAR-10 convolution network with batch normalization

So, continuing our deep learning adventures, we will now try to build a convolution network with batch normalization for training on the CIFAR-10 dataset.

→ Read more...

2019/01/03 18:29

Older entries >>