Keras documentation: NN ops (2024)

[source]

average_pool function

keras.ops.average_pool( inputs, pool_size, strides=None, padding="valid", data_format=None)

Average pooling operation.

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". Pooling happens over the spatial dimensions only.
• pool_size: int or tuple/list of integers of size len(inputs_spatial_shape), specifying the size of the pooling window for each spatial dimension of the input tensor. If pool_size is int, then every spatial dimension shares the same pool_size.
• strides: int or tuple/list of integers of size len(inputs_spatial_shape). The stride of the sliding window for each spatial dimension of the input tensor. 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, ...).

Returns

A tensor of rank N+2, the result of the average pooling operation.

[source]

batch_normalization function

keras.ops.batch_normalization( x, mean, variance, axis, offset=None, scale=None, epsilon=0.001)

Normalizes x by mean and variance.

This op is typically used by the batch normalization step in a neuralnetwork. It normalizes the input tensor along the given axis.

Arguments

• x: Input tensor.
• mean: A mean vector of the same length as the axis dimension of the input thensor.
• variance: A variance vector of the same length as the axis dimension of the input tensor.
• axis: Integer, the axis that should be normalized.
• offset: An offset vector of the same length as the axis dimension of the input tensor. If not None, offset is added to the normalized tensor. Defaults to None.
• scale: A scale vector of the same length as the axis dimension of the input tensor. If not None, the normalized tensor is multiplied by scale. Defaults to None.
• epsilon: Small float added to variance to avoid dividing by zero. Defaults to 1e-3.

Returns

The normalized tensor.

Example

>>> x = keras.ops.convert_to_tensor(... [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9]]... )>>> keras.ops.batch_normalization(... x,... mean=[0.4, 0.5, 0.6],... variance=[0.67, 0.67, 0.67],... axis=-1... )array([[-3.6624e-01, -3.6624e-01, -3.6624e-01], [-4.6445e-09, 0.0000e+00, -1.8578e-08], [ 3.6624e-01, 3.6624e-01, 3.6624e-01]])

[source]

binary_crossentropy function

keras.ops.binary_crossentropy(target, output, from_logits=False)

Computes binary cross-entropy loss between target and output tensor.

The binary cross-entropy loss is commonly used in binaryclassification tasks where each input sample belongs to oneof the two classes. It measures the dissimilarity between thetarget and output probabilities or logits.

Arguments

• target: The target tensor representing the true binary labels. Its shape should match the shape of the output tensor.
• output: The output tensor representing the predicted probabilities or logits. Its shape should match the shape of the target tensor.
• from_logits: (optional) Whether output is a tensor of logits or probabilities. Set it to True if output represents logits; otherwise, set it to False if output represents probabilities. Defaults to False.

Returns

• Integer tensor: The computed binary cross-entropy loss betweentarget and output.

Example

>>> target = keras.ops.convert_to_tensor([0, 1, 1, 0])>>> output = keras.ops.convert_to_tensor([0.1, 0.9, 0.8, 0.2])>>> binary_crossentropy(target, output)array([0.10536054 0.10536054 0.22314355 0.22314355], shape=(4,), dtype=float32)

[source]

categorical_crossentropy function

keras.ops.categorical_crossentropy(target, output, from_logits=False, axis=-1)

Computes categorical cross-entropy loss between target and output tensor.

The categorical cross-entropy loss is commonly used in multi-classclassification tasks where each input sample can belong to one ofmultiple classes. It measures the dissimilaritybetween the target and output probabilities or logits.

Arguments

• target: The target tensor representing the true categorical labels. Its shape should match the shape of the output tensor except for the last dimension.
• output: The output tensor representing the predicted probabilities or logits. Its shape should match the shape of the target tensor except for the last dimension.
• from_logits: (optional) Whether output is a tensor of logits or probabilities. Set it to True if output represents logits; otherwise, set it to False if output represents probabilities. Defaults to False.
• axis: (optional) The axis along which the categorical cross-entropy is computed. Defaults to -1, which corresponds to the last dimension of the tensors.

Returns

• Integer tensor: The computed categorical cross-entropy loss betweentarget and output.

Example

>>> target = keras.ops.convert_to_tensor(... [[1, 0, 0],... [0, 1, 0],... [0, 0, 1]])>>> output = keras.ops.convert_to_tensor(... [[0.9, 0.05, 0.05],... [0.1, 0.8, 0.1],... [0.2, 0.3, 0.5]])>>> categorical_crossentropy(target, output)array([0.10536054 0.22314355 0.6931472 ], shape=(3,), dtype=float32)

[source]

conv function

keras.ops.conv( inputs, kernel, strides=1, padding="valid", data_format=None, dilation_rate=1)

General N-D convolution.

This ops supports 1D, 2D and 3D convolution.

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".
• kernel: Tensor of rank N+2. kernel has shape (kernel_spatial_shape, num_input_channels, num_output_channels). num_input_channels should match the number of channels in inputs.
• 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.

Returns

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

[source]

conv_transpose function

keras.ops.conv_transpose( inputs, kernel, strides, padding="valid", output_padding=None, data_format=None, dilation_rate=1,)

General N-D convolution transpose.

Also known as de-convolution. This ops supports 1D, 2D and 3D convolution.

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".
• kernel: Tensor of rank N+2. kernel has shape [kernel_spatial_shape, num_output_channels, num_input_channels], num_input_channels should match the number of channels in inputs.
• 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.
• output_padding: int or int tuple/list of len(inputs_spatial_shape), specifying the amount of padding along the height and width of the output tensor. Can be a single integer to specify the same value for all spatial dimensions. The amount of output padding along a given dimension must be lower than the stride along that same dimension. If set to None (default), the output shape is inferred.
• 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.

Returns

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

[source]

depthwise_conv function

keras.ops.depthwise_conv( inputs, kernel, strides=1, padding="valid", data_format=None, dilation_rate=1)

General N-D depthwise convolution.

This ops supports 1D and 2D depthwise convolution.

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".
• kernel: Tensor of rank N+2. kernel has shape [kernel_spatial_shape, num_input_channels, num_channels_multiplier], num_input_channels should match the number of channels in inputs.
• 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.

Returns

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

[source]

elu function

keras.ops.elu(x, alpha=1.0)

Exponential Linear Unit activation function.

It is defined as:

f(x) = alpha * (exp(x) - 1.) for x < 0, f(x) = x for x >= 0.

Arguments

• x: Input tensor.
• alpha: A scalar, slope of positive section. Defaults to 1.0.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_elu = keras.ops.elu(x)>>> print(x_elu)array([-0.63212055, 0., 1.], shape=(3,), dtype=float64)

[source]

gelu function

keras.ops.gelu(x, approximate=True)

Gaussian Error Linear Unit (GELU) activation function.

If approximate is True, it is defined as:f(x) = 0.5 * x * (1 + tanh(sqrt(2 / pi) * (x + 0.044715 * x^3)))

Or if approximate is False, it is defined as:f(x) = x * P(X <= x) = 0.5 * x * (1 + erf(x / sqrt(2))),where P(X) ~ N(0, 1).

Arguments

• x: Input tensor.
• approximate: Approximate version of GELU activation. Defaults to True.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_gelu = keras.ops.gelu(x)>>> print(x_gelu)array([-0.15865525, 0., 0.84134475], shape=(3,), dtype=float64)

[source]

hard_sigmoid function

keras.ops.hard_sigmoid(x)

Hard sigmoid activation function.

It is defined as:

0 if x < -2.5, 1 if x > 2.5, (0.2 * x) + 0.5 if -2.5 <= x <= 2.5.

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_hard_sigmoid = keras.ops.hard_sigmoid(x)>>> print(x_hard_sigmoid)array([0.3, 0.5, 0.7], shape=(3,), dtype=float64)

[source]

leaky_relu function

keras.ops.leaky_relu(x, negative_slope=0.2)

Leaky version of a Rectified Linear Unit activation function.

It allows a small gradient when the unit is not active, it is defined as:

f(x) = alpha * x for x < 0 or f(x) = x for x >= 0.

Arguments

• x: Input tensor.
• negative_slope: Slope of the activation function at x < 0. Defaults to 0.2.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_leaky_relu = keras.ops.leaky_relu(x)>>> print(x_leaky_relu)array([-0.2, 0. , 1. ], shape=(3,), dtype=float64)

[source]

log_sigmoid function

keras.ops.log_sigmoid(x)

Logarithm of the sigmoid activation function.

It is defined as f(x) = log(1 / (1 + exp(-x))).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-0.541391, 0.0, 0.50, 5.0])>>> keras.ops.log_sigmoid(x)array([-1.0000418, -0.6931472, -0.474077, -0.00671535], dtype=float32)

[source]

log_softmax function

keras.ops.log_softmax(x, axis=-1)

Log-softmax activation function.

It is defined as:f(x) = x - max(x) - log(sum(exp(x - max(x))))

Arguments

• x: Input tensor.
• axis: Integer, axis along which the log-softmax is applied. Defaults to -1.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_log_softmax = keras.ops.log_softmax(x)>>> print(x_log_softmax)array([-2.40760596, -1.40760596, -0.40760596], shape=(3,), dtype=float64)

[source]

max_pool function

keras.ops.max_pool( inputs, pool_size, strides=None, padding="valid", data_format=None)

Max pooling operation.

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". Pooling happens over the spatial dimensions only.
• pool_size: int or tuple/list of integers of size len(inputs_spatial_shape), specifying the size of the pooling window for each spatial dimension of the input tensor. If pool_size is int, then every spatial dimension shares the same pool_size.
• strides: int or tuple/list of integers of size len(inputs_spatial_shape). The stride of the sliding window for each spatial dimension of the input tensor. 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, ...).

Returns

A tensor of rank N+2, the result of the max pooling operation.

[source]

moments function

keras.ops.moments(x, axes, keepdims=False, synchronized=False)

Calculates the mean and variance of x.

The mean and variance are calculated by aggregating the contents of xacross axes. If x is 1-D and axes = [0] this is just the mean andvariance of a vector.

Arguments

• x: Input tensor.
• axes: A list of axes which to compute mean and variance.
• keepdims: If this is set to True, the axes which are reduced are left in the result as dimensions with size one.
• synchronized: Only applicable with the TensorFlow backend. If True, synchronizes the global batch statistics (mean and variance) across all devices at each training step in a distributed training strategy. If False, each replica uses its own local batch statistics.

Returns

A tuple containing two tensors - mean and variance.

Example

>>> x = keras.ops.convert_to_tensor([0, 1, 2, 3, 100], dtype="float32")>>> keras.ops.moments(x, axes=[0])(array(21.2, dtype=float32), array(1553.3601, dtype=float32))

[source]

multi_hot function

keras.ops.multi_hot( inputs, num_classes=None, axis=-1, dtype=None, sparse=False, **kwargs)

Encodes integer labels as multi-hot vectors.

This function encodes integer labels as multi-hot vectors, where each labelis mapped to a binary value in the resulting vector.

Arguments

• inputs: Tensor of integer labels to be converted to multi-hot vectors.
• num_classes: Integer, the total number of unique classes.
• axis: (optional) Axis along which the multi-hot encoding should be added. Defaults to -1, which corresponds to the last dimension.
• dtype: (optional) The data type of the resulting tensor. Default is backend's float type.
• sparse: Whether to return a sparse tensor; for backends that support sparse tensors.

Returns

• Tensor: The multi-hot encoded tensor.

Example

>>> data = keras.ops.convert_to_tensor([0, 4])>>> keras.ops.multi_hot(data, num_classes=5)array([1.0, 0.0, 0.0, 0.0, 1.0], dtype=float32)

[source]

one_hot function

keras.ops.one_hot(x, num_classes, axis=-1, dtype=None, sparse=False)

Converts integer tensor x into a one-hot tensor.

The one-hot encoding is a representation where each integer value isconverted into a binary vector with a length equal to num_classes,and the index corresponding to the integer value is marked as 1, whileall other indices are marked as 0.

Arguments

• x: Integer tensor to be encoded. The shape can be arbitrary, but the dtype should be integer.
• num_classes: Number of classes for the one-hot encoding.
• axis: Axis along which the encoding is performed. -1 represents the last axis. Defaults to -1.
• dtype: (Optional) Data type of the output tensor. If not provided, it defaults to the default data type of the backend.
• sparse: Whether to return a sparse tensor; for backends that support sparse tensors.

Returns

• Integer tensor: One-hot encoded tensor with the same shape as xexcept for the specified axis dimension, which will havea length of num_classes. The dtype of the output tensoris determined by dtype or the default data type of the backend.

Example

>>> x = keras.ops.convert_to_tensor([1, 3, 2, 0])>>> one_hot(x, num_classes=4)array([[0. 1. 0. 0.] [0. 0. 0. 1.] [0. 0. 1. 0.] [1. 0. 0. 0.]], shape=(4, 4), dtype=float32)

[source]

relu function

keras.ops.relu(x)

Rectified linear unit activation function.

It is defined as f(x) = max(0, x).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x1 = keras.ops.convert_to_tensor([-1.0, 0.0, 1.0, 0.2])>>> keras.ops.relu(x1)array([0.0, 0.0, 1.0, 0.2], dtype=float32)

[source]

relu6 function

keras.ops.relu6(x)

Rectified linear unit activation function with upper bound of 6.

It is defined as f(x) = np.clip(x, 0, 6).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-3.0, -2.0, 0.1, 0.2, 6.0, 8.0])>>> keras.ops.relu6(x)array([0.0, 0.0, 0.1, 0.2, 6.0, 6.0], dtype=float32)

[source]

selu function

keras.ops.selu(x)

Scaled Exponential Linear Unit (SELU) activation function.

It is defined as:

f(x) = scale * alpha * (exp(x) - 1.) for x < 0,f(x) = scale * x for x >= 0.

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_selu = keras.ops.selu(x)>>> print(x_selu)array([-1.11133055, 0., 1.05070098], shape=(3,), dtype=float64)

[source]

separable_conv function

keras.ops.separable_conv( inputs, depthwise_kernel, pointwise_kernel, strides=1, padding="valid", data_format=None, dilation_rate=1,)

General N-D separable convolution.

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

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.

Returns

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

[source]

sigmoid function

keras.ops.sigmoid(x)

Sigmoid activation function.

It is defined as f(x) = 1 / (1 + exp(-x)).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-6.0, 1.0, 0.0, 1.0, 6.0])>>> keras.ops.sigmoid(x)array([0.00247262, 0.7310586, 0.5, 0.7310586, 0.9975274], dtype=float32)

[source]

silu function

keras.ops.silu(x)

Sigmoid Linear Unit (SiLU) activation function, also known as Swish.

The SiLU activation function is computed by the sigmoid function multipliedby its input. It is defined as f(x) = x * sigmoid(x).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-6.0, 1.0, 0.0, 1.0, 6.0])>>> keras.ops.sigmoid(x)array([0.00247262, 0.7310586, 0.5, 0.7310586, 0.9975274], dtype=float32)>>> keras.ops.silu(x)array([-0.0148357, 0.7310586, 0.0, 0.7310586, 5.9851646], dtype=float32)

[source]

hard_silu function

keras.ops.hard_silu(x)

Hard SiLU activation function, also known as Hard Swish.

It is defined as:

• 0 if if x < -3
• x if x > 3
• x * (x + 3) / 6 if -3 <= x <= 3

It's a faster, piecewise linear approximation of the silu activation.

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-3.0, -1.0, 0.0, 1.0, 3.0])>>> keras.ops.hard_silu(x)array([-0.0, -0.3333333, 0.0, 0.6666667, 3.0], shape=(5,), dtype=float32)

[source]

softmax function

keras.ops.softmax(x, axis=-1)

Softmax activation function.

The elements of the output vector lie within the range (0, 1), and theirtotal sum is exactly 1 (excluding the floating point rounding error).

Each vector is processed independently. The axis argument specifies theaxis along which the function is applied within the input.

It is defined as:f(x) = exp(x) / sum(exp(x))

Arguments

• x: Input tensor.
• axis: Integer, axis along which the softmax is applied.

Returns

A tensor with the same shape as x.

Example

>>> x = np.array([-1., 0., 1.])>>> x_softmax = keras.ops.softmax(x)>>> print(x_softmax)array([0.09003057, 0.24472847, 0.66524096], shape=(3,), dtype=float64)

[source]

softplus function

keras.ops.softplus(x)

Softplus activation function.

It is defined as f(x) = log(exp(x) + 1), where log is the naturallogarithm and exp is the exponential function.

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-0.555, 0.0, 0.555])>>> keras.ops.softplus(x)array([0.45366603, 0.6931472, 1.008666], dtype=float32)

[source]

softsign function

keras.ops.softsign(x)

Softsign activation function.

It is defined as f(x) = x / (abs(x) + 1).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-0.100, -10.0, 1.0, 0.0, 100.0])>>> keras.ops.softsign(x)Array([-0.09090909, -0.90909094, 0.5, 0.0, 0.990099], dtype=float32)

[source]

sparse_categorical_crossentropy function

keras.ops.sparse_categorical_crossentropy(target, output, from_logits=False, axis=-1)

Computes sparse categorical cross-entropy loss.

The sparse categorical cross-entropy loss is similar to categoricalcross-entropy, but it is used when the target tensor contains integerclass labels instead of one-hot encoded vectors. It measures thedissimilarity between the target and output probabilities or logits.

Arguments

• target: The target tensor representing the true class labels as integers. Its shape should match the shape of the output tensor except for the last dimension.
• output: The output tensor representing the predicted probabilities or logits. Its shape should match the shape of the target tensor except for the last dimension.
• from_logits: (optional) Whether output is a tensor of logits or probabilities. Set it to True if output represents logits; otherwise, set it to False if output represents probabilities. Defaults to False.
• axis: (optional) The axis along which the sparse categorical cross-entropy is computed. Defaults to -1, which corresponds to the last dimension of the tensors.

Returns

• Integer tensor: The computed sparse categorical cross-entropyloss between target and output.

Example

>>> target = keras.ops.convert_to_tensor([0, 1, 2], dtype=int32)>>> output = keras.ops.convert_to_tensor(... [[0.9, 0.05, 0.05],... [0.1, 0.8, 0.1],... [0.2, 0.3, 0.5]])>>> sparse_categorical_crossentropy(target, output)array([0.10536056 0.22314355 0.6931472 ], shape=(3,), dtype=float32)

[source]

silu function

keras.ops.swish(x)

Sigmoid Linear Unit (SiLU) activation function, also known as Swish.

The SiLU activation function is computed by the sigmoid function multipliedby its input. It is defined as f(x) = x * sigmoid(x).

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-6.0, 1.0, 0.0, 1.0, 6.0])>>> keras.ops.sigmoid(x)array([0.00247262, 0.7310586, 0.5, 0.7310586, 0.9975274], dtype=float32)>>> keras.ops.silu(x)array([-0.0148357, 0.7310586, 0.0, 0.7310586, 5.9851646], dtype=float32)

[source]

hard_silu function

keras.ops.hard_swish(x)

Hard SiLU activation function, also known as Hard Swish.

It is defined as:

• 0 if if x < -3
• x if x > 3
• x * (x + 3) / 6 if -3 <= x <= 3

It's a faster, piecewise linear approximation of the silu activation.

Arguments

• x: Input tensor.

Returns

A tensor with the same shape as x.

Example

>>> x = keras.ops.convert_to_tensor([-3.0, -1.0, 0.0, 1.0, 3.0])>>> keras.ops.hard_silu(x)array([-0.0, -0.3333333, 0.0, 0.6666667, 3.0], shape=(5,), dtype=float32)