networks¶
Networks for AID¶
WideNet¶
-
class
indexedconv.nets.aid.
WideNet
(n_out)¶ ResNet like Network from HexaConv paper (Z²).
Parameters: n_out (int) – Number of features after last convolution.
WideNetIndexConvIndexPool¶
-
class
indexedconv.nets.aid.
WideNetIndexConvIndexPool
(index_matrix, camera_layout, n_out)¶ ResNet like Network from HexaConv paper implemented with indexed convolutions and pooling.
Parameters: - index_matrix (torch.Tensor) – The index matrix corresponding to the input images.
- camera_layout (str) – The grid shape of the images.
- n_out (int) – Number of features after last convolution.
Networks for CIFAR¶
WideNetIndexConvIndexPool¶
-
class
indexedconv.nets.cifar.
WideNetIndexConvIndexPool
(index_matrix, camera_layout)¶ ResNet like Network from HexaConv paper implemented with indexed convolutions and pooling.
Parameters: - index_matrix (torch.Tensor) – The index matrix corresponding to the input images.
- camera_layout (str) – The grid shape of the images.
WideNetIndexConvIndexPoolRetina¶
-
class
indexedconv.nets.cifar.
WideNetIndexConvIndexPoolRetina
(index_matrix, camera_layout)¶ ResNet like Network from HexaConv paper implemented with indexed convolutions (retina like kernel) and pooling.
Parameters: - index_matrix (torch.Tensor) – The index matrix corresponding to the input images.
- camera_layout (str) – The grid shape of the images.
Network for MNIST¶
GLNet2HexaConvForMnist¶
-
class
indexedconv.nets.mnist.
GLNet2HexaConvForMnist
(index_matrix)¶ Network with indexed convolutions and pooling (square kernels). 2 CL (after each conv layer, pooling is executed) 1 FC
Parameters: index_matrix (torch.Tensor) – The index matrix corresponding to the input images.