foscat.BkTensorflow#
Classes#
Module Contents#
- class foscat.BkTensorflow.BkTensorflow(*args, **kwargs)#
Bases:
foscat.BkBase.BackendBase- backend#
- tf_function#
- float64#
- float32#
- int64#
- int32#
- complex64#
- complex128#
- gpulist#
- ngpu = 1#
- tf_loc_function(func)#
- bk_len(S)#
- bk_SparseTensor(indice, w, dense_shape=[])#
- bk_stack(list, axis=0)#
- bk_sparse_dense_matmul(smat, mat)#
- periodic_pad(x, pad_height, pad_width)#
Applies periodic (‘wrap’) padding to a 4D TensorFlow tensor (N, H, W, C).
Args: x (tf.Tensor): Input tensor with shape (batch_size, height, width, channels).
pad_height (tuple): Tuple (top, bottom) defining the vertical padding size. pad_width (tuple): Tuple (left, right) defining the horizontal padding size.
- Returns:
tf.Tensor: Tensor with periodic padding applied.
- binned_mean(data, cell_ids)#
data: Tensor of shape […, N] (float32 or float64) cell_ids: Tensor of shape [N], int indices in [0, n_bins) Returns: mean per bin, shape […, n_bins]
- conv2d(x, w)#
Perform 2D convolution using TensorFlow.
- Args:
x: Tensor of shape […, Nx, Ny] – input w: Tensor of shape [O_c, wx, wy] – conv weights
- Returns:
Tensor of shape […, O_c, Nx, Ny]
- conv1d(x, w)#
Perform 1D convolution using TensorFlow.
- Args:
x: Tensor of shape […, N] – input w: Tensor of shape [k] – conv weights
- Returns:
Tensor of shape […,N]
- bk_threshold(x, threshold, greater=True)#
- bk_maximum(x1, x2)#
- bk_device(device_name)#
- bk_ones(shape, dtype=None)#
- bk_conv1d(x, w)#
- bk_flattenR(x)#
- bk_flatten(x)#
- bk_resize_image(x, shape)#
- bk_L1(x)#
- bk_square_comp(x)#
- bk_reduce_sum(data, axis=None)#
- bk_size(data)#
- bk_reduce_mean(data, axis=None)#
- bk_reduce_min(data, axis=None)#
- bk_random_seed(value)#
- bk_random_uniform(shape)#
- bk_reduce_std(data, axis=None)#
- bk_sqrt(data)#
- bk_abs(data)#
- bk_is_complex(data)#
- bk_distcomp(data)#
- bk_norm(data)#
- bk_square(data)#
- bk_log(data)#
- bk_matmul(a, b)#
- bk_tensor(data)#
- bk_shape_tensor(shape)#
- bk_complex(real, imag)#
- bk_exp(data)#
- bk_min(data)#
- bk_argmin(data)#
- bk_tanh(data)#
- bk_max(data)#
- bk_argmax(data)#
- bk_reshape(data, shape)#
- bk_repeat(data, nn, axis=0)#
- bk_tile(data, nn, axis=0)#
- bk_roll(data, nn, axis=0)#
- bk_expand_dims(data, axis=0)#
- bk_transpose(data, thelist)#
- bk_concat(data, axis=None)#
- bk_zeros(shape, dtype=None)#
- bk_gather(data, idx, axis=0)#
- bk_reverse(data, axis=0)#
- bk_fft(data)#
- bk_fftn(data, dim=None)#
- bk_ifftn(data, dim=None, norm=None)#
- bk_rfft(data)#
- bk_irfft(data)#
- bk_conjugate(data)#
- bk_real(data)#
- bk_imag(data)#
- bk_relu(x)#
- bk_clip_by_value(x, xmin, xmax)#
- bk_cast(x)#
- bk_variable(x)#
- bk_assign(x, y)#
- bk_constant(x)#
- bk_cos(x)#
- bk_sin(x)#
- bk_arctan2(c, s)#
- bk_empty(list)#
- to_numpy(x)#