All Projects → durner → STORN-keras

durner / STORN-keras

Licence: other
This is a STORN (Stochastical Recurrent Neural Network) implementation for keras!

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to STORN-keras

Punctuator2
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
Stars: ✭ 483 (+2000%)
Mutual labels:  theano, recurrent-neural-networks
sequence-rnn-py
Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras
Stars: ✭ 28 (+21.74%)
Mutual labels:  theano, recurrent-neural-networks
Returnn
The RWTH extensible training framework for universal recurrent neural networks
Stars: ✭ 290 (+1160.87%)
Mutual labels:  theano, recurrent-neural-networks
Parrot
RNN-based generative models for speech.
Stars: ✭ 601 (+2513.04%)
Mutual labels:  theano, recurrent-neural-networks
Machine Learning Curriculum
💻 Make machines learn so that you don't have to struggle to program them; The ultimate list
Stars: ✭ 761 (+3208.7%)
Mutual labels:  theano, recurrent-neural-networks
Rnn ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (+856.52%)
Mutual labels:  theano, recurrent-neural-networks
Theano Kaldi Rnn
THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.
Stars: ✭ 31 (+34.78%)
Mutual labels:  theano, recurrent-neural-networks
rnn benchmarks
RNN benchmarks of pytorch, tensorflow and theano
Stars: ✭ 85 (+269.57%)
Mutual labels:  theano, recurrent-neural-networks
DeepSegmentor
Sequence Segmentation using Joint RNN and Structured Prediction Models (ICASSP 2017)
Stars: ✭ 17 (-26.09%)
Mutual labels:  recurrent-neural-networks
Meetup-Content
Entirety.ai Intuition to Implementation Meetup Content.
Stars: ✭ 33 (+43.48%)
Mutual labels:  recurrent-neural-networks
entity-network
Tensorflow implementation of "Tracking the World State with Recurrent Entity Networks" [https://arxiv.org/abs/1612.03969] by Henaff, Weston, Szlam, Bordes, and LeCun.
Stars: ✭ 58 (+152.17%)
Mutual labels:  recurrent-neural-networks
regulatory-prediction
Code and Data to accompany "Dilated Convolutions for Modeling Long-Distance Genomic Dependencies", presented at the ICML 2017 Workshop on Computational Biology
Stars: ✭ 26 (+13.04%)
Mutual labels:  recurrent-neural-networks
Conversational-AI-Chatbot-using-Practical-Seq2Seq
A simple open domain generative based chatbot based on Recurrent Neural Networks
Stars: ✭ 17 (-26.09%)
Mutual labels:  recurrent-neural-networks
Sequence-to-Sequence-Learning-of-Financial-Time-Series-in-Algorithmic-Trading
My bachelor's thesis—analyzing the application of LSTM-based RNNs on financial markets. 🤓
Stars: ✭ 64 (+178.26%)
Mutual labels:  recurrent-neural-networks
Deep-Learning
This repo provides projects on deep-learning mainly using Tensorflow 2.0
Stars: ✭ 22 (-4.35%)
Mutual labels:  recurrent-neural-networks
binary.com-bot
Scripts for using on Binary.com Bots.
Stars: ✭ 60 (+160.87%)
Mutual labels:  stochastic
automatic-personality-prediction
[AAAI 2020] Modeling Personality with Attentive Networks and Contextual Embeddings
Stars: ✭ 43 (+86.96%)
Mutual labels:  recurrent-neural-networks
classifying-cancer
A Python-Tensorflow neural network for classifying cancer data
Stars: ✭ 30 (+30.43%)
Mutual labels:  recurrent-neural-networks
imessage-chatbot
💬 Recurrent neural network -- generates messages in your style of speech! Trained on imessage data. Sqlite3, TensorFlow, Flask, Twilio SMS, AWS.
Stars: ✭ 33 (+43.48%)
Mutual labels:  recurrent-neural-networks
rnn darts fastai
Implement Differentiable Architecture Search (DARTS) for RNN with fastai
Stars: ✭ 21 (-8.7%)
Mutual labels:  recurrent-neural-networks

STORN implementation for keras

The implementation can be found in greenarm/models/STORN.py!

Required packages

  • keras >= 1.0.6
  • theano >= 0.8.2
  • numpy >= 1.11.0
  • scipy >= 0.17.1
  • h5py = 2.6.0
  • hdf5 = 1.8.16
  • hualos (optional monitoring)

Please replace this code snippet in the keras library!

Keras does not currently have proper support for Masking and merged layer outputs.

Changes for Masked Layer Merge building on top of keras 1.0.6 file: keras/engine/topology.py, method: compute_mask, line: 1349

   def compute_mask(self, inputs, mask=None):
       if mask is None or all([m is None for m in mask]):
           return None

       assert hasattr(mask, '__len__') and len(mask) == len(inputs)

       if self.mode in ['sum', 'mul', 'ave']:
           masks = [K.expand_dims(m, 0) for m in mask if m is not None]
           return K.all(K.concatenate(masks, axis=0), axis=0, keepdims=False)
       elif self.mode == 'concat':
            # Make a list of masks while making sure the dimensionality of each mask
            # is the same as the corresponding input.
            masks = []
            for input_i, mask_i in zip(inputs, mask):
                if mask_i is None:
                    # Input is unmasked. Append all 1s to masks
                    masks.append(K.ones_like(input_i))
                elif K.ndim(mask_i) < K.ndim(input_i):
                    # Mask is smaller than the input, expand it
                    masks.append(K.expand_dims(mask_i))
                else:
                    masks.append(mask)
            concatenated = K.concatenate(masks, axis=self.concat_axis)
            return K.all(concatenated, axis=-1, keepdims=False)
       elif self.mode in ['cos', 'dot']:
           return None
       elif hasattr(self.mode, '__call__'):
           if hasattr(self._output_mask, '__call__'):
               return self._output_mask(mask)
           else:
               return self._output_mask
       else:
           # this should have been caught earlier
           raise Exception('Invalid merge mode: {}'.format(self.mode))
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].