* Computes the cumulative product of a `tf.Tensor` along `axis`. * * ```js * const x = tf.tensor([1, 2, 3, 4]); * x.cumprod().print(); * ``` * `

* Computes the cumulative sum of a `tf.Tensor` along `axis`. * * ```js * const x = tf.tensor([1, 2, 3, 4]); * x.cumsum().print(); * ``` * ```js

* Set the current context * @param contexts: ExecutionContextInfo[] the current path of execution * frames

* Returns the current context in string format.

* Returns the current context and all parent contexts in string format. * This allow access to the nodes in the current and parent frames.

* Copy the tensor's data to a new GPU resource. Comparing to the `dataSync()` * and `data()`, this method prevents data from being downloaded to CP

Decrease refCount of a `TensorData`.

Decrease refCount of a `TensorData`.

Decrease refCount of a `TextureData`.

Decode the provided bytes into a string using the provided encoding.

* Decode a stream of UTF8-encoded byte arrays to a stream of strings. * * The byte arrays producetd from the ByteChunkIterator on which this is

* Compares its two arguments for order. * @param a The first element to be compared. * @param b The second element to be compared. * @return A nega

* Outputs a vector with length `size` and the same dtype as `weights`. * * If `weights` are empty, then index `i` stores the number of times the val

* Rearranges data from depth into blocks of spatial data. More specifically, * this op outputs a copy of the input tensor where values from the `dept

* Depthwise 2D convolution. * * Given a 4D `input` array and a `filter` array of shape * `[filterHeight, filterWidth, inChannels, channelMultiplier

Deserialize a Keras Model from buffers or file-like objects. Args: config: content of the JSON containing model topology and weights manifest,

* Transform tokens back into strings. * * @param inputs Input tensor. * @param kwargs Additional keyword arguments.