Caffe-LSTM
This is LSTM implementation based on Caffe.
TODO
- Mini-batch update
- Examples for the real datasets (i.e., Handwriting recognition/Speech recognition)
- Peephole connection
Example
An example code is in /examples/lstm_sequence/.
In this code, LSTM network is trained to generate a predefined sequence without any inputs.
This experiment was introduced by Clockwork RNN.
Four different LSTM networks and shell scripts(.sh) for training are provided.
Each script generates a log file containing the predicted sequence and the true sequence.
You can use plot_result.m to visualize the result.
The result of four LSTM networks will be as follows:
- 1-layer LSTM with 15 hidden units for short sequence
- 1-layer LSTM with 50 hidden units for long sequence
- 3-layer deep LSTM with 7 hidden units for short sequence
- 3-layer deep LSTM with 23 hidden units for long sequence
