op_separable_conv: General N-D separable convolution.
In rstudio/keras: R Interface to 'Keras'

op_separable_conv

R Documentation

General N-D separable convolution.

Description

This ops supports 1D and 2D separable convolution. separable_conv is a depthwise conv followed by a pointwise conv.

Usage

op_separable_conv(
  inputs,
  depthwise_kernel,
  pointwise_kernel,
  strides = 1L,
  padding = "valid",
  data_format = NULL,
  dilation_rate = 1L
)

Arguments

`inputs`	Tensor of rank N+2. `inputs` has shape `⁠(batch_size,) + inputs_spatial_shape + (num_channels,)⁠` if `data_format="channels_last"`, or `⁠(batch_size, num_channels) + inputs_spatial_shape⁠` if `data_format="channels_first"`.
`depthwise_kernel`	Tensor of rank N+2. `depthwise_kernel` has shape `⁠[kernel_spatial_shape, num_input_channels, num_channels_multiplier],⁠` `num_input_channels` should match the number of channels in `inputs`.
`pointwise_kernel`	Tensor of rank N+2. `pointwise_kernel` has shape `⁠(ones_like(kernel_spatial_shape), num_input_channels num_channels_multiplier, num_output_channels)⁠`.
`strides`	int or int tuple/list of `len(inputs_spatial_shape)`, specifying the strides of the convolution along each spatial dimension. If `strides` is int, then every spatial dimension shares the same `strides`.
`padding`	string, either `"valid"` or `"same"`. `"valid"` means no padding is applied, and `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input when `strides=1`.
`data_format`	A string, either `"channels_last"` or `"channels_first"`. `data_format` determines the ordering of the dimensions in the inputs. If `data_format="channels_last"`, `inputs` is of shape `⁠(batch_size, ..., channels)⁠` while if `data_format="channels_first"`, `inputs` is of shape `⁠(batch_size, channels, ...)⁠`.
`dilation_rate`	int or int tuple/list of `len(inputs_spatial_shape)`, specifying the dilation rate to use for dilated convolution. If `dilation_rate` is int, then every spatial dimension shares the same `dilation_rate`.

Value

A tensor of rank N+2, the result of the depthwise conv operation.

Other nn ops:
op_average_pool()
op_batch_normalization()
op_binary_crossentropy()
op_categorical_crossentropy()
op_conv()
op_conv_transpose()
op_ctc_loss()
op_depthwise_conv()
op_elu()
op_gelu()
op_hard_sigmoid()
op_hard_silu()
op_leaky_relu()
op_log_sigmoid()
op_log_softmax()
op_max_pool()
op_moments()
op_multi_hot()
op_normalize()
op_one_hot()
op_relu()
op_relu6()
op_selu()
op_sigmoid()
op_silu()
op_softmax()
op_softplus()
op_softsign()
op_sparse_categorical_crossentropy()

Other ops:
op_abs()
op_add()
op_all()
op_any()
op_append()
op_arange()
op_arccos()
op_arccosh()
op_arcsin()
op_arcsinh()
op_arctan()
op_arctan2()
op_arctanh()
op_argmax()
op_argmin()
op_argsort()
op_array()
op_average()
op_average_pool()
op_batch_normalization()
op_binary_crossentropy()
op_bincount()
op_broadcast_to()
op_cast()
op_categorical_crossentropy()
op_ceil()
op_cholesky()
op_clip()
op_concatenate()
op_cond()
op_conj()
op_conv()
op_conv_transpose()
op_convert_to_numpy()
op_convert_to_tensor()
op_copy()
op_correlate()
op_cos()
op_cosh()
op_count_nonzero()
op_cross()
op_ctc_decode()
op_ctc_loss()
op_cumprod()
op_cumsum()
op_custom_gradient()
op_depthwise_conv()
op_det()
op_diag()
op_diagonal()
op_diff()
op_digitize()
op_divide()
op_divide_no_nan()
op_dot()
op_eig()
op_eigh()
op_einsum()
op_elu()
op_empty()
op_equal()
op_erf()
op_erfinv()
op_exp()
op_expand_dims()
op_expm1()
op_extract_sequences()
op_eye()
op_fft()
op_fft2()
op_flip()
op_floor()
op_floor_divide()
op_fori_loop()
op_full()
op_full_like()
op_gelu()
op_get_item()
op_greater()
op_greater_equal()
op_hard_sigmoid()
op_hard_silu()
op_hstack()
op_identity()
op_imag()
op_image_affine_transform()
op_image_crop()
op_image_extract_patches()
op_image_map_coordinates()
op_image_pad()
op_image_resize()
op_image_rgb_to_grayscale()
op_in_top_k()
op_inv()
op_irfft()
op_is_tensor()
op_isclose()
op_isfinite()
op_isinf()
op_isnan()
op_istft()
op_leaky_relu()
op_less()
op_less_equal()
op_linspace()
op_log()
op_log10()
op_log1p()
op_log2()
op_log_sigmoid()
op_log_softmax()
op_logaddexp()
op_logical_and()
op_logical_not()
op_logical_or()
op_logical_xor()
op_logspace()
op_logsumexp()
op_lu_factor()
op_matmul()
op_max()
op_max_pool()
op_maximum()
op_mean()
op_median()
op_meshgrid()
op_min()
op_minimum()
op_mod()
op_moments()
op_moveaxis()
op_multi_hot()
op_multiply()
op_nan_to_num()
op_ndim()
op_negative()
op_nonzero()
op_norm()
op_normalize()
op_not_equal()
op_one_hot()
op_ones()
op_ones_like()
op_outer()
op_pad()
op_power()
op_prod()
op_qr()
op_quantile()
op_ravel()
op_real()
op_reciprocal()
op_relu()
op_relu6()
op_repeat()
op_reshape()
op_rfft()
op_roll()
op_round()
op_rsqrt()
op_scatter()
op_scatter_update()
op_segment_max()
op_segment_sum()
op_select()
op_selu()
op_shape()
op_sigmoid()
op_sign()
op_silu()
op_sin()
op_sinh()
op_size()
op_slice()
op_slice_update()
op_softmax()
op_softplus()
op_softsign()
op_solve()
op_solve_triangular()
op_sort()
op_sparse_categorical_crossentropy()
op_split()
op_sqrt()
op_square()
op_squeeze()
op_stack()
op_std()
op_stft()
op_stop_gradient()
op_subtract()
op_sum()
op_svd()
op_swapaxes()
op_take()
op_take_along_axis()
op_tan()
op_tanh()
op_tensordot()
op_tile()
op_top_k()
op_trace()
op_transpose()
op_tri()
op_tril()
op_triu()
op_unstack()
op_var()
op_vdot()
op_vectorize()
op_vectorized_map()
op_vstack()
op_where()
op_while_loop()
op_zeros()
op_zeros_like()