#RNN collection
RNN collection is RNN (Recurrent Neural Networks) & Deep Learning library.
- Collection of state-of-the-art RNN models - Deep LSTM, Reservoir Computing, etc.
- mshadow based implementation - you can easily switch cpu/gpu calculation
- json format parameter file
- supports define original RNN model
- CBLAS or MKL
- C++ compiler (g++, icc, etc.)
- python
- numpy
- wget
- (optional) nvidia GPU & CUDA 6.5
run fetch.sh
and then
make
- If you want to use GPU
make gpu=1
- If you have MKL
make mkl=1
- Both
make gpu=1 mkl=1
./bin/train < ./param_files/narma.json > log.txt