Johannes Baiter

I don't think it's possible, since pyrnn and clstm use different model definitions: https://github.com/tmbdev/clstm/blob/master/clstm.proto https://github.com/mittagessen/kraken/blob/master/proto/pyrnn.proto Maybe there's a way to convert between the two, but I wouldn't know how :/

That script converts to the old HDF5-based format, not the new Protobuf-based one, unfortunately :-/ I just had a look at two protobuf models from clstm and from kraken (the...

> Hope contributors fix this problem ASAP. I don't think this will be easy. The codec determines the size of the network's layers, i.e. there will be weights/connections in the...

> I failed to get it to run in Debian Jessie with either Python2/3 but that is probably an include path problem. Cython either refused to import shared_ptr from libcpp.memory...

Hm, that's weird :-) Can you make a core dump and check out the trace with gdb? ``` bash $ ulimit -c unlimited $ python run_uw3_500.py $ gdb $(which python)...

The segfault was due to a compatibility problem with older versions of Pillow, Jessie uses 2.6.1 while I used 3.4.2 for developing. 2.9.0 added the `width` and `height` attributes, which...

Nope, I played around with it for a while, but gave up on it pretty quickly. My main aim was to make accessing the high-level OCR stuff from `clstmhl.h` available...

That's a really good point. I'll see what I can do about exposing the lower-level interfaces :-)

@mittagessen I've started work on exposing the `INetwork` interface, but am now stuck on creating wrappers around the Eigen tensor types (`Eigen::Tensor`, `Eigen::TensorMap`). It would be great if we could...

Weird, with the latest code from master I get step times of ~0.3s with the uw3-500 dataset, while with the a588c8 version they are between 6.5s and 10.5s, i.e. the...