Computes a N-D convolution given (N+1+batch_dims)-D `input` and (N+2)-D `filter` tensors.
General function for computing a N-D convolution. It is required that `1 <= N <= 3`.
Nested Classes
class | Conv.Options | Optional attributes for Conv
|
Public Methods
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static Conv.Options |
batchDims(Long batchDims)
|
static <T extends Number> Conv<T> |
create(Scope scope, Operand<T> input, Operand<T> filter, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new Conv operation.
|
static Conv.Options |
dataFormat(String dataFormat)
|
static Conv.Options |
dilations(List<Long> dilations)
|
static Conv.Options |
explicitPaddings(List<Long> explicitPaddings)
|
static Conv.Options |
groups(Long groups)
|
Output<T> |
output()
A (N+1+batch_dims)-D tensor.
|
Inherited Methods
Public Methods
public Output<T> asOutput ()
Returns the symbolic handle of a tensor.
Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
public static Conv.Options batchDims (Long batchDims)
Parameters
batchDims | A positive integer specifying the number of batch dimensions for the input tensor. Should be less than the rank of the input tensor. |
---|
public static Conv<T> create (Scope scope, Operand<T> input, Operand<T> filter, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new Conv operation.
Parameters
scope | current scope |
---|---|
input | Tensor of type T and shape `batch_shape + spatial_shape + [in_channels]` in the case that `channels_last_format = true` or shape `batch_shape + [in_channels] + spatial_shape` if `channels_last_format = false`. spatial_shape is N-dimensional with `N=2` or `N=3`. Also note that `batch_shape` is dictated by the parameter `batch_dims` and defaults to 1. |
filter | An `(N+2)-D` Tensor with the same type as `input` and shape `spatial_filter_shape + [in_channels, out_channels]`, where spatial_filter_shape is N-dimensional with `N=2` or `N=3`. |
strides | 1-D tensor of length `N+2`. The stride of the sliding window for each dimension of `input`. Must have `strides[0] = strides[N+1] = 1`. |
padding | The type of padding algorithm to use. |
options | carries optional attributes values |
Returns
- a new instance of Conv
public static Conv.Options dataFormat (String dataFormat)
Parameters
dataFormat | Used to set the data format. By default `CHANNELS_FIRST`, uses `NHWC (2D) / NDHWC (3D)` or if `CHANNELS_LAST`, uses `NCHW (2D) / NCDHW (3D)`. |
---|
public static Conv.Options dilations (List<Long> dilations)
Parameters
dilations | 1-D tensor of length `N+2`. The dilation factor for each dimension of `input`. If set to `k > 1`, there will be `k-1` skipped cells between each filter element on that dimension. The dimension order is determined by the value of `channels_last_format`, see above for details. Dilations in the batch and depth dimensions must be 1. |
---|
public static Conv.Options explicitPaddings (List<Long> explicitPaddings)
Parameters
explicitPaddings | If `padding` is `"EXPLICIT"`, the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is `explicit_paddings[2 * i]` and `explicit_paddings[2 * i + 1]`, respectively. If `padding` is not `"EXPLICIT"`, `explicit_paddings` must be empty. |
---|
public static Conv.Options groups (Long groups)
Parameters
groups | A positive integer specifying the number of groups in which the input is split along the channel axis. Each group is convolved separately with `filters / groups` filters. The output is the concatenation of all the groups results along the channel axis. Input channels and filters must both be divisible by groups. |
---|
public Output<T> output ()
A (N+1+batch_dims)-D tensor. The dimension order is determined by the value of `channels_last_format`, see below for details.