pydbm.cnn.layerablecnn.convolutionlayer package¶
Submodules¶
pydbm.cnn.layerablecnn.convolutionlayer.deconvolution_layer module¶
-
class
pydbm.cnn.layerablecnn.convolutionlayer.deconvolution_layer.
DeconvolutionLayer
¶ Bases:
pydbm.cnn.layerablecnn.convolution_layer.ConvolutionLayer
Deconvolution Layer.
Deconvolution also called transposed convolutions “work by swapping the forward and backward passes of a convolution.” (Dumoulin, V., & Visin, F. 2016, p20.)
References
- Dumoulin, V., & V,kisin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285.
-
back_propagate
¶ Back propagation in CNN layers.
Override.
Parameters: delta_arr – 4-rank array like or sparse matrix. Returns: 4-rank array like or sparse matrix.
-
forward_propagate
¶ Forward propagation in CNN layers.
Override.
Parameters: img_arr – 4-rank array like or sparse matrix. Returns: 4-rank array like or sparse matrix.