* Computes exponential of the input `tf.Tensor` element-wise. `e ^ x` * * ```js * const x = tf.tensor1d([1, 2, -3]); * * x.exp().print(); // or

* Returns a `tf.Tensor` that has expanded rank, by inserting a dimension * into the tensor's shape. * * ```js * const x = tf.tensor1d([1, 2, 3, 4]

Expand the relative input path to absolute path, and add layers model file name to the end if input format is `tfjs_layers_model`. Args: input

* Computes exponential of the input `tf.Tensor` minus one element-wise. * `e ^ x - 1` * * ```js * const x = tf.tensor1d([1, 2, -3]); * * x.expm1

* Extract the first element of the weight values and set it * as the iterations counter variable of this instance of optimizer. * * @param we

* Create an identity matrix. * * @param numRows Number of rows. * @param numColumns Number of columns. Defaults to `numRows`. * @param batchShape

* Makes an HTTP request. * * see @fetch docs above.

* Fast Fourier transform. * * Computes the 1-dimensional discrete Fourier transform over the inner-most * dimension of input. * * ```js * const

* Filters this dataset according to `predicate`. * * ```js * const a = tf.data.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10]) * .filter(x => x%2

* Filters this stream according to `predicate`. * * @param predicate A function mapping a stream element to a boolean or a * `Promise` for on

* Maps this stream through a 1-to-many transform. * * @param transform A function mapping a stream element to an array of * transformed ele

@doc {heading: 'Operations', subheading: 'Images', namespace: 'image'}

* Divides two `tf.Tensor`s element-wise, A / B. Supports broadcasting. * The result is rounded with floor function. * * * ```js * const a = tf.te

* Computes floor of input `tf.Tensor` element-wise: `floor(x)`. * * ```js * const x = tf.tensor1d([.6, 1.1, -3.3]); * * x.floor().print(); // or

Removes batch normalization ops by folding them into convolutions. Batch normalization during training has multiple dynamic parameters that are u

* Apply a function to every element of the dataset. * * After the function is applied to a dataset element, any Tensors contained * within th

* Apply a function to every element of the stream. * * @param f A function to apply to each stream element.

* Expands input into frames of frameLength. * Slides a window size with frameStep. * * ```js * tf.signal.frame([1, 2, 3], 2, 1).print(); * ``` *

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse

@nocollapse