Layer factory function to create a 2D convolution layer with optional
non-linearity. Same as Convolution() except that filter_shape
is verified to be 2-dimensional. See Convolution() for extensive
documentation.
Convolution2D(filter_shape, num_filters = NULL, activation = activation_identity, init = init_glorot_uniform(), pad = FALSE, strides = 1, bias = TRUE, init_bias = 0, reduction_rank = 1, name = "")
| filter_shape | int or list of int - shape (spatial extent) of the receptive field, not including the input feature-map depth. E.g. (3,3) for a 2D convolution. |
|---|---|
| num_filters | (int, defaults to None) – number of filters (output feature-map depth), or () to denote scalar output items (output shape will have no depth axis). integer of number of filters |
| activation | (Function) - optional activation Function optional function to apply at end |
| init | (scalar or matrix or initializer, defaults to
init_glorot_uniform()) – initial value of weights W vector array or
cntk$initializer, defaults to |
| pad | (bool or list of bools) – if False, then the operation will be shifted over the “valid” area of input, that is, no value outside the area is used. If pad=True on the other hand, the operation will be applied to all input positions, and positions outside the valid region will be considered containing zero. Use a list to specify a per-axis value. |
| strides | (int or tuple of ints, defaults to 1) – stride of the operation. Use a list of ints to specify a per-axis value. integer of stride for convolution |
| bias | (bool) – whether to include bias logical if the layer should have a bias term |
| init_bias | (scalar or matrix or initializer, defaults to 0) – initial value of weights b |
| reduction_rank | integer whether input items have or do not have a depth axis |
| name | string (optional) the name of the Function instance in the network |
A cntk$ops$functions$Function class for defining tensor operations in network architecture.