mittagessen

They are for all intents and purposes completely different networks because of the peephole connections (so not really convertible). The code linked above only reserializes pickled pyrnn into HDF5 or...

The line image normalization is identical, the text line normalization is not. Ocropy normalizes output to NFKC(/D?), clstm doesn't normalize output to any Unicode normalization form.

@moucmou if you want a mostly out of the box OCR with gpu acceleration you could use @andbue's kraken branch that uses pytorch instead of clstm. IIRC it's performance isn't...

Resizing the output layer of the network after training is generally not possible, although it would be possible to precreate unused nodes and making up codec entries for these afterwards....

Awesome. Are already working on interfacing the lower level INetwork interface? If not I'll put something together as I'm currently working on a new training subcommand for kraken and the...

My main need is having access to the output matrix for running a slightly modified label extractor producing bounding boxes as the label locations are just the point of the...

I had a short look at mxnet as it seemed promising and I prefer its interface to theano's; initialization still takes quite a bit of time and warp-ctc is prone...

Sorry for spamming but there's one major reason for using the lower level interface. By preloading the entire training set into memory and doing all the normalization, encoding, etc. once,...

@wanghaisheng: You don't really as the old swig interface is broken, so it isn't quite possible to instantiate a network. What is working (since yesterday night) is continuing training a...

The eigency code for eigen->numpy is just: ``` @cython.boundscheck(False) cdef np.ndarray[float, ndim=2] ndarray_float_C(float *data, long rows, long cols, long row_stride, long col_stride): cdef float[:,:] mem_view = data dtype = 'float'...