LostTech.TensorFlow : API Documentation

Type tf.keras.layers

Namespace tensorflow

Methods

Properties

Public static methods

object add(IEnumerable<IGraphNodeBase> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Add` layer.
Parameters
IEnumerable<IGraphNodeBase> inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the sum of the inputs.

Examples:

```python import keras

input1 = keras.layers.Input(shape=(16,)) x1 = keras.layers.Dense(8, activation='relu')(input1) input2 = keras.layers.Input(shape=(32,)) x2 = keras.layers.Dense(8, activation='relu')(input2) added = keras.layers.add([x1, x2])

out = keras.layers.Dense(4)(added) model = keras.models.Model(inputs=[input1, input2], outputs=out) ```

object add(IGraphNodeBase inputs, IDictionary<string, object> kwargs)

Functional interface to the `Add` layer.
Parameters
IGraphNodeBase inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the sum of the inputs.

Examples:

```python import keras

input1 = keras.layers.Input(shape=(16,)) x1 = keras.layers.Dense(8, activation='relu')(input1) input2 = keras.layers.Input(shape=(32,)) x2 = keras.layers.Dense(8, activation='relu')(input2) added = keras.layers.add([x1, x2])

out = keras.layers.Dense(4)(added) model = keras.models.Model(inputs=[input1, input2], outputs=out) ```

object add_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Add` layer.
Parameters
object inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the sum of the inputs.

Examples:

```python import keras

input1 = keras.layers.Input(shape=(16,)) x1 = keras.layers.Dense(8, activation='relu')(input1) input2 = keras.layers.Input(shape=(32,)) x2 = keras.layers.Dense(8, activation='relu')(input2) added = keras.layers.add([x1, x2])

out = keras.layers.Dense(4)(added) model = keras.models.Model(inputs=[input1, input2], outputs=out) ```

object average(IEnumerable<object> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Average` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the average of the inputs.

object average_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Average` layer.
Parameters
object inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the average of the inputs.

object concatenate(IGraphNodeBase inputs, int axis, IDictionary<string, object> kwargs)

Functional interface to the `Concatenate` layer.
Parameters
IGraphNodeBase inputs
A list of input tensors (at least 2).
int axis
Concatenation axis.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the concatenation of the inputs alongside axis `axis`.

object concatenate(IEnumerable<IGraphNodeBase> inputs, int axis, IDictionary<string, object> kwargs)

Functional interface to the `Concatenate` layer.
Parameters
IEnumerable<IGraphNodeBase> inputs
A list of input tensors (at least 2).
int axis
Concatenation axis.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the concatenation of the inputs alongside axis `axis`.

object concatenate_dyn(object inputs, ImplicitContainer<T> axis, IDictionary<string, object> kwargs)

Functional interface to the `Concatenate` layer.
Parameters
object inputs
A list of input tensors (at least 2).
ImplicitContainer<T> axis
Concatenation axis.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the concatenation of the inputs alongside axis `axis`.

object dot(IEnumerable<object> inputs, int axes, bool normalize, IDictionary<string, object> kwargs)

Functional interface to the `Dot` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2).
int axes
Integer or tuple of integers, axis or axes along which to take the dot product.
bool normalize
Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the dot product of the samples from the inputs.

object dot(IEnumerable<object> inputs, ValueTuple<int, object> axes, bool normalize, IDictionary<string, object> kwargs)

Functional interface to the `Dot` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2).
ValueTuple<int, object> axes
Integer or tuple of integers, axis or axes along which to take the dot product.
bool normalize
Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the dot product of the samples from the inputs.

object dot_dyn(object inputs, object axes, ImplicitContainer<T> normalize, IDictionary<string, object> kwargs)

Functional interface to the `Dot` layer.
Parameters
object inputs
A list of input tensors (at least 2).
object axes
Integer or tuple of integers, axis or axes along which to take the dot product.
ImplicitContainer<T> normalize
Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the dot product of the samples from the inputs.

object maximum(IEnumerable<object> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Maximum` layer that computes

the maximum (element-wise) list of `inputs`.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2) of same shape.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor (of same shape as input tensor) with the element-wise maximum of the inputs.
Show Example 
input1 = tf.keras.layers.Input(shape=(16,))
            x1 = tf.keras.layers.Dense(8, activation='relu')(input1) #shape=(None, 8)
            input2 = tf.keras.layers.Input(shape=(32,))
            x2 = tf.keras.layers.Dense(8, activation='relu')(input2) #shape=(None, 8)
            max_inp=tf.keras.layers.maximum([x1,x2]) #shape=(None, 8)
            out = tf.keras.layers.Dense(4)(max_inp)
            model = tf.keras.models.Model(inputs=[input1, input2], outputs=out)

object maximum_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Maximum` layer that computes

the maximum (element-wise) list of `inputs`.
Parameters
object inputs
A list of input tensors (at least 2) of same shape.
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor (of same shape as input tensor) with the element-wise maximum of the inputs.
Show Example 
input1 = tf.keras.layers.Input(shape=(16,))
            x1 = tf.keras.layers.Dense(8, activation='relu')(input1) #shape=(None, 8)
            input2 = tf.keras.layers.Input(shape=(32,))
            x2 = tf.keras.layers.Dense(8, activation='relu')(input2) #shape=(None, 8)
            max_inp=tf.keras.layers.maximum([x1,x2]) #shape=(None, 8)
            out = tf.keras.layers.Dense(4)(max_inp)
            model = tf.keras.models.Model(inputs=[input1, input2], outputs=out)

object minimum(IEnumerable<object> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Minimum` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the element-wise minimum of the inputs.

object minimum_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Minimum` layer.
Parameters
object inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the element-wise minimum of the inputs.

object multiply(IEnumerable<object> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Multiply` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the element-wise product of the inputs.

object multiply_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Multiply` layer.
Parameters
object inputs
A list of input tensors (at least 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the element-wise product of the inputs.

IDictionary<string, object> serialize(Layer layer)

object subtract(IEnumerable<object> inputs, IDictionary<string, object> kwargs)

Functional interface to the `Subtract` layer.
Parameters
IEnumerable<object> inputs
A list of input tensors (exactly 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the difference of the inputs.

Examples:

```python import keras

input1 = keras.layers.Input(shape=(16,)) x1 = keras.layers.Dense(8, activation='relu')(input1) input2 = keras.layers.Input(shape=(32,)) x2 = keras.layers.Dense(8, activation='relu')(input2) subtracted = keras.layers.subtract([x1, x2])

out = keras.layers.Dense(4)(subtracted) model = keras.models.Model(inputs=[input1, input2], outputs=out) ```

object subtract_dyn(object inputs, IDictionary<string, object> kwargs)

Functional interface to the `Subtract` layer.
Parameters
object inputs
A list of input tensors (exactly 2).
IDictionary<string, object> kwargs
Standard layer keyword arguments.
Returns
object
A tensor, the difference of the inputs.

Examples:

```python import keras

input1 = keras.layers.Input(shape=(16,)) x1 = keras.layers.Dense(8, activation='relu')(input1) input2 = keras.layers.Input(shape=(32,)) x2 = keras.layers.Dense(8, activation='relu')(input2) subtracted = keras.layers.subtract([x1, x2])

out = keras.layers.Dense(4)(subtracted) model = keras.models.Model(inputs=[input1, input2], outputs=out) ```

Public properties

PythonFunctionContainer average_fn get;

PythonFunctionContainer concatenate_fn get;

PythonFunctionContainer deserialize_fn get;

PythonFunctionContainer maximum_fn get;

PythonFunctionContainer minimum_fn get;

PythonFunctionContainer multiply_fn get;

PythonFunctionContainer serialize_fn get;

PythonFunctionContainer subtract_fn get;