Skip to content
RNNs and LSTMs for torch trained with E. Coli and Human reference Genome
Lua Python
Branch: master
Clone or download
Pull request Compare This branch is 9 commits ahead of jcjohnson:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Adam
Eli
data
doc
imgs
scripts
test
util
.gitignore
LICENSE.md
LSTM.lua
LanguageModel.lua
README.md
Screen Shot 2018-08-20 at 2.49.26 PM.png
Screen Shot 2018-08-20 at 2.54.59 PM.png
TemporalAdapter.lua
TemporalCrossEntropyCriterion.lua
VanillaRNN.lua
eval.lua
init.lua
requirements.txt
sample.lua
torch-rnn-scm-1.rockspec
train.lua

README.md

Torch-RNN-Trained

torch-rnn

from https://github.com/jcjohnson/torch-rnn
torch-rnn provides high-performance, reusable RNN and LSTM modules for torch7, and uses these modules for character-level language modeling similar to char-rnn.

You can find documentation for the RNN and LSTM modules here; they have no dependencies other than torch and nn, so they should be easy to integrate into existing projects.

Compared to char-rnn, torch-rnn is up to 1.9x faster and uses up to 7x less memory. For more details see the Benchmark.

Biological Samples

  1. Human GRCh38 reference genome (Adam)
  2. E. Coli reference genome (Eli)

Input Arguments

-max_epochs 8 -rnn_size 128 -dropout 0.05 -num_layers 3

Blastn Alignment Results

See blast at: https://blast.ncbi.nlm.nih.gov/Blast.cgi
Sampling from the longest checkpoints

Eli: alt text

Adam: alt text

You can’t perform that action at this time.