pydbm.rnn.lstmmodel.convlstmmodel package¶
Submodules¶
pydbm.rnn.lstmmodel.convlstmmodel.deconv_lstm_model module¶
-
class
pydbm.rnn.lstmmodel.convlstmmodel.deconv_lstm_model.DeconvLSTMModel¶ Bases:
pydbm.rnn.lstmmodel.conv_lstm_model.ConvLSTMModelDeconvolutional LSTM(ConvLSTM).
Convolutional LSTM(ConvLSTM)(Xingjian, S. H. I. et al., 2015), which is a model that structurally couples convolution operators to LSTM networks, can be utilized as components in constructing the Encoder/Decoder. The ConvLSTM is suitable for spatio-temporal data due to its inherent convolutional structure.
In this class, the convolution and deconvolution are mutually substituted. Deconvolution also called transposed convolutions “work by swapping the forward and backward passes of a convolution.” (Dumoulin, V., & Visin, F. 2016, p20.)
References
- https://github.com/chimera0/accel-brain-code/blob/master/Deep-Learning-by-means-of-Design-Pattern/demo/demo_conv_lstm.ipynb
- Dumoulin, V., & V,kisin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
- Xingjian, S. H. I., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems (pp. 802-810)
-
get_graph¶ getter
-
graph¶ getter
-
set_graph¶ setter