* Pads a `tf.Tensor1D` with a given value and paddings. See `pad` for details.

* Pads a `tf.Tensor2D` with a given value and paddings. See `pad` for details.

* Pads a `tf.Tensor3D` with a given value and paddings. See `pad` for details.

* Pads a `tf.Tensor4D` with a given value and paddings. See `pad` for details.

* Pads a `tf.Tensor` with a given value and paddings. * * This operation implements `CONSTANT` mode. For `REFLECT` and `SYMMETRIC`, * refer to `tf.

Entry point for pip-packaged binary. Note that pip-packaged binary calls the entry method without any arguments, which is why this method is need

Entry point for pip-packaged binary. Note that pip-packaged binary calls the entry method without any arguments, which is why this method is need

* Performs an N-D pooling operation * * @param input The input tensor, of rank 4 or rank 3 of shape * `[batch, height, width, inChannels]`. If

* Computes the power of one `tf.Tensor` to another. Supports broadcasting. * * Given a `tf.Tensor` x and a `tf.Tensor` y, this operation computes x^

Use tfjs binary to make inference and store output in file. Args: binary_path: Path to the nodejs binary. The path can be an absolute path

* Generates output predictions for the input samples. * * Computation is done in batches. * * Note: the "step" mode of predict() is curren

* Execute the inference for the input tensors. * * @param inputs The input tensors, when there is single input for the model, * inputs pa

* Execute the inference for the input tensors. * * @param input The input tensors, when there is single input for the model, * inputs param s

* Execute the inference for the input tensors. * * @param input The input tensors, when there is single input for the model, * inputs param s

* Infer through MobileNet. This does standard ImageNet pre-processing before * inferring through the model. This method returns named activations a

* Returns predictions for a single batch of samples. * * ```js * const model = tf.sequential({ * layers: [tf.layers.dense({units: 1, inp

* Creates a `Dataset` that prefetches elements from this dataset. * * @param bufferSize: An integer specifying the number of elements to be

* Prefetch the first `bufferSize` items in this stream. * * Note this prefetches Promises, but makes no guarantees about when those * Promise

* Computes leaky rectified linear element-wise with parametric alphas. * * `x < 0 ? alpha * x : f(x) = x` * * ```js * const x = tf.tensor1d([-1,

* An overridable function which preprocesses features.

* An overridable function which preprocesses labels.

* An overridable function which preprocesses entire samples.

* A `LayersModel` instance used to preprocess inputs.

* Prints the `tf.Tensor`. See `tf.print` for details. * * @param verbose Whether to print verbose information about the tensor, * includin

* Computes the product of elements across dimensions of a `tf.Tensor`. * * Reduces the input along the dimensions given in `axes`. Unless `keepDims`

* Compute QR decomposition of m-by-n matrix using Householder transformation. * * Implementation based on * [http://www.cs.cornell.edu/~bindel/cl

Quantizes the weights by linearly re-scaling across available bits. The weights are quantized by linearly re-scaling the values between the minim

* Returns a RaggedTensor result composed from rtDenseValues and rtNestedSplits, * such that result[i] = [starts[i], starts[i] + deltas[i], ..., limit

* Create a dense tensor from a ragged tensor, possibly altering its shape. * * The raggedTensorToTensor op creates a dense tensor from am array of r

* Creates a `tf.Tensor` with values sampled from a random number generator * function defined by the user. * * @param shape An array of integers de

* Creates a `tf.Tensor` with values sampled from a gamma distribution. * * ```js * tf.randomGamma([2, 2], 1).print(); * ``` * * @param shape An

* Creates a `tf.Tensor` with values sampled from a normal distribution. * * ```js * tf.randomNormal([2, 2]).print(); * ``` * * @param shape An a

* Creates a `tf.Tensor` with values sampled from a normal distribution. * * The generated values will have mean 0 and standard deviation 1. * * ``

* Creates a `tf.Tensor` with integers sampled from a uniform distribution. * * The generated values are uniform integers in the range [minval, maxva

* Creates a `tf.Tensor` with values sampled from a uniform distribution. * * The generated values follow a uniform distribution in the range [minval