Statistics on lstm

Number of watchers on Github 535
Number of open issues 10
Average time to close an issue about 2 months
Main language Lua
Average time to merge a PR about 1 hour
Open pull requests 1+
Closed pull requests 5+
Last commit over 3 years ago
Repo Created almost 4 years ago
Repo Last Updated 8 months ago
Size 2.21 MB
Organization / Authorwojzaremba
Page Updated
Do you use lstm? Leave a review!
View open issues (10)
View lstm activity
View on github
Latest Open Source Launches
Trendy new open source projects in your inbox! View examples

Subscribe to our mailing list

Evaluating lstm for your project? Score Explanation
Commits Score (?)
Issues & PR Score (?)

Long Short Term Memory Units

This is self-contained package to train a language model on word level Penn Tree Bank dataset. It achieves 115 perplexity for a small model in 1h, and 81 perplexity for a big model in a day. Model ensemble of 38 big models gives 69 perplexity. This code is derived from (the same author, but a different company).

More information:

lstm open issues Ask a question     (View All Issues)
  • over 2 years QUESTION: How to run on a different treebank corpus
  • over 2 years question about the g_cloneManyTimes() function
  • almost 3 years attempt to call field 'LogSoftMax_updateOutput' (a nil value)
  • almost 3 years why split gates along dimension 2?
  • about 3 years Is cutorch.synchronize() necessary?
  • about 3 years questions about g_cloneManyTimes
  • over 3 years replicate(x_inp, batch_size)
  • over 3 years 1 to params.seq_length -1 ?
lstm open pull requests (View All Pulls)
  • Optimized hyperparameters on "small" model, achieves 87 perplexity in 1 hour.
lstm questions on Stackoverflow (View All Questions)
  • Training, testing, and validation sets for bidirectional LSTM (BLSTM)
  • How to stack LSTM layers to classify speech files
  • Stock market to LSTM
  • How to train the forget gate of an LSTM to keep the value in the cell, while the target of the block is zero?
  • LSTM Training: to backpropagate or not
  • Building Speech Dataset for LSTM binary classification
  • LSTM NN: forward propagation
  • How do I use 4096D vector as input to LSTM?
  • Classification with CNN/LSTM/RNN
  • Translating a TensorFlow LSTM into synapticjs
  • TensorFlow LSTM Generative Model
  • Request for example: Caffe RNN/LSTM regression for Python
  • LSTM network learning
  • Analysing the result of LSTM Theano Sentiment Analysis
  • plot in python for theano LSTM
  • Multivariate time-series RNN using Tensorflow. Is this possible with an LSTM cell or similar?
  • How to perform multi-label learning with LSTM using theano?
  • Keras LSTM predicting only 1 category, in multi-category classification - how to fix?
  • LSTM Model in Torch not Learning
  • How to use LSTM for sequence labelling in python?
  • LSTM with rnn cuda()?
  • LSTM Classifying all the words as the same class
  • Simple LSTM failing due undefined input dimension
  • Simplest Lstm training with Keras io
  • What is a Recurrent Neural Network, what is a Long Short Term Memory (LSTM) network, and is it always better?
  • Training LSTM Model in Torch and Data Structure
  • Training LSTM in Torch
  • PyBrain LSTM Example resultin in ValueError:Attempted relative import in non-package
  • Large Difference in Output: nnGraph based LSTM vs Sequencer LSTM (Torch)
  • Pybrain - lstm sequence bad predictions
lstm list of languages used
Other projects in Lua