Tom

In earlier versions of Eigen, the matrix code was more optimized than the tensor code, but that isn't true anymore, so the matrix version isn't needed anymore.

The speed of matrix vs tensor depends crucially on the version of Eigen; the version that you have installed may be too old. Can you install Eigen from github source...

That sounds odd. I benchmarked both versions against each other before switching. Recent versions of Eigen really shouldn't have big differences in linear algebra performance between tensor and matrix; after...

Hmmm... I'm not sure. At this point, all I can say is that when I made the switch, the two performed pretty much identically to each other, and basically gave...

What's the CPU in each case? On Wed, Oct 12, 2016, 13:10 Johannes Baiter [email protected] wrote: > The slowness of the matrix code was due to me using debug=-1 (which...

I already have an LSTM-based OCR for TensorFlow that works like CLSTM, but TensorFlow (and by extension, Keras) support for LSTMs is still less than ideal.

No, that's a multidimensional add-on to TensorFlow. The LSTM code is experimental and in a bunch of iPython notebooks. I'm working on a Torch version right now, which I think...

I just pushed the Tensor-based version. I will try to provide trained models soon.

Last I tried CI, the C++ compilers that the services had available were too outdated to work properly, and they lacked some C++ prerequisites. That's why I gave up on...

The 2D LSTM hasn't been used yet for OCR, so that's still to be worked out. CLSTM's 2D LSTM uses a "separable 2D LSTM"; that is, it doesn't zig-zag across...