* @param modelUrl url for the model, or an `io.IOHandler`. * @param weightManifestUrl url for the weight file generated by * scripts/convert.py

* Constructor of HashTable. Creates a hash table. * * @param keyDType `dtype` of the table keys. * @param valueDType `dtype` of the table val

* Computes a 1D convolution over the input x. * * @param x The input tensor, of rank 3 or rank 2, of shape * `[batch, width, inChannels]`. If r

* Computes the derivative of the filter of a 2D convolution. * * @param x The input tensor, of rank 4 or rank 3 of shape * [batch, height, widt

* Computes the derivative of the input of a 2D convolution. * * @param xShape The shape of the input: [batch, height, width, inDepth]. * If length

* Computes the transposed 2D convolution of an image, also known as a * deconvolution. * * @param x The input image, of rank 4 or rank 3, of shape

* Computes a 2D convolution over the input x. * * @param x The input tensor, of rank 4 or rank 3, of shape * `[batch, height, width, inChannels

* Computes the derivative of the filter of a 3D convolution. * * @param x The input tensor, of rank 5 or rank 4 of shape * [batch, depth, heigh

* Computes the derivative of the input of a 3D convolution. * * @param xShape The shape of the input: [batch, depth, height, width, * in_channels].

* Computes the transposed 3D convolution of a volume, also known as a * deconvolution. * * @param x The input image, of rank 5 or rank 4, of shape

* Computes a 3D convolution over the input x. * * @param x The input tensor, of rank 5 or rank 4, of shape * `[batch, depth, height, width, cha

Converts a JAX function `jax_apply_fn` and model parameters to a TensorflowJS model. Example usage for a Flax Module: ``` import numpy as np

Convert an in-memory keras model to Tensorflow.js graph model format. Args: keras_model: Keras Model object. output_dir: string The name of

Convert frozen model and check the model compatibility with Tensorflow.js. Optimize and convert the model to Tensorflow.js format, when the model pa

Conversion for TF Hub modules V1 and V2. See convert_tf_hub_module and convert_tf_saved_model. Args: module_path: string Path to the module.

* Copy a model from one URL to another. * * This function supports: * * 1. Copying within a storage medium, e.g., * `tf.io.copyModel('localsto

* Computes cos of the input `tf.Tensor` element-wise: `cos(x)` * * ```js * const x = tf.tensor1d([0, Math.PI / 2, Math.PI * 3 / 4]); * * x.cos().

* Computes hyperbolic cos of the input `tf.Tensor` element-wise: `cosh(x)` * * ```js * const x = tf.tensor1d([0, 1, -1, .7]); * * x.cosh().print(

* Computes the cosine distance loss between two tensors. * * @param labels The ground truth output tensor, same dimensions as * 'predictions'.

* Counts the total number of numbers (e.g., float32, int32) in the * weights. * * @returns An integer count. * @throws RuntimeError: If th

* The factory function to create an ImageClassifier instance. * * @param model The path to load the TFLite model from, or the model content *

* The factory function to create a NLClassifier instance. * * @param model The path to load the TFLite model from, or the model content *

* The factory function to create a TFLiteWebModelRunner instance. * * @param model The path to load the TFLite model from, or the model content

* The factory function to create an ImageSegmenter instance. * * @param model The path to load the TFLite model from, or the model content *

* The factory function to create an ImageClassifier instance. * * @param model The path to load the TFLite model from, or the model content *

* The factory function to create an ImageClassifier instance. * * @param model The path to load the TFLite model from, or the model content *

* Create a TF.js tensor out of an existing WebGPU buffer.

* Create a TF.js tensor out of an existing WebGL texture. A new texture will * be created.

* Extracts crops from the input image tensor and resizes them using bilinear * sampling or nearest neighbor sampling (possibly with aspect ratio chan