-
Hi,
It's quite unclear what you do with the pressure and timestamp features (see Indermühle et al.).
In `writing.py` it seems that you extract features like pressure from the data but when using the…
-
@pvoigtlaender @doetsch I am trying your experiment of mdlstm on IAM, there are some problems about the input and output.
1. why the image are transformed from 2D tensor to 1D sequence?
2. what …
-
-
-
Multilingual documents are common in the computer age of today. Plethora of these
documents exist in the form of translations, books, operational manuals, etc. The
abundance of these multilingual do…
-
Hi everyone, First, I would like to express my gratitude to all people who work daily trying to improve Keras software and its documentation. Thank you guys ;)
After reading many posts trying to sort…
-
I've tried to implement a deep LSTM network and tested it on an autoencoder task in recovering audio magnitude spectrogram. At first I set the number of frames in spectrogram (i.e. time step in LSTM) …
-
I have an idea for adding bidirectional RNNs to Keras and I'm curious what the Keras devs think of it.
- Add a `Reverse` layer which simply slices its input tensor along the timestep dimension (e.g. …
-
[ABB13] ABBYY, January 2013. available at ?iiT,ffrrrX ##vvX+QKf `2+Q;MBiBQMnb2`p2`.
[AHN+14] Q. U. A. Akram, S. Hussain, A. Niazi, U. Anjum, and F. Irfan. Adpating Tesseract for Complex Scripts: An Ex…
-
layers.py, on which most of the nntools code is based, has always been geared towards feed-forward neural networks. We should look into recurrent neural networks as well. Personally I don't have a lot…