* Returns the indices of the maximum values along an `axis`. * * The result has the same shape as `input` with the dimension along `axis` * removed

* Returns the indices of the minimum values along an `axis`. * * The result has the same shape as `input` with the dimension along `axis` * removed

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

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

* Checks compatibility between the layer and provided inputs. * * This checks that the tensor(s) `input` * verify the input assumptions of th

* Computes arctangent of `tf.Tensor`s a / b element-wise: `atan2(a, b)`. * Supports broadcasting. * * ```js * const a = tf.tensor1d([1.0, 1.0, -1.

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

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

Generate the output formats for given input format. Args: ansowers: user selected parameter dict.

Generate the available saved model signatures from the proto file and selected tags. Args: ansowers: user selected parameter dict.

Generate the available saved model tags from the proto file. Args: ansowers: user selected parameter dict.

* Computes the backprop of a 3d avg pool. * * @param dy The dy error, of rank 5 of shape * [batchSize, depth, height, width, channels]. * assu

* Computes the 3D average pooling. * * ```js * const x = tf.tensor5d([1, 2, 3, 4, 5, 6, 7, 8], [1, 2, 2, 2, 1]); * const result = tf.avgPool3d(x,

* Computes the backprop of an 2D avg pool. * * @param dy The dy error, of rank 4 or rank 3 of shape * [batchSize, height, width, channels]. If

* Computes the 2D average pooling of an image. * * @param x The input tensor, of rank 4 or rank 3 of shape * `[batch, height, width, inChannels

* A `LayersModel` instance providing the backbone submodel.

* Copy a tensor setting everything outside a central band in each innermost * matrix to zero. * * The band part is computed as follows: Assume inpu

* Computes the next state and output of a BasicLSTMCell. * * Returns `[newC, newH]`. * * Derived from tf.contrib.rnn.BasicLSTMCell. * * @param f

* Groups elements into batches. * * It is assumed that each of the incoming dataset elements has the same * structure -- i.e. the same set of

* Batch normalization, strictly for 2D. For the more relaxed version, see * `tf.batchNorm`. * * @param x The input Tensor. * @param mean A mean Te

* Batch normalization, strictly for 3D. For the more relaxed version, see * `tf.batchNorm`. * * @param x The input Tensor. * @param mean A mean Te

* Batch normalization, strictly for 4D. For the more relaxed version, see * `tf.batchNorm`. * * @param x The input Tensor. * @param mean A mean Te

* Batch normalization. * * As described in * [http://arxiv.org/abs/1502.03167](http://arxiv.org/abs/1502.03167). * * Mean, variance, scale, and o

* This operation reshapes the "batch" dimension 0 into `M + 1` dimensions of * shape `blockShape + [batch]`, interleaves these blocks back into the g

* Creates and runs benchmark configurations for each model-backend pairing. * * @param browsers The target browsers to run benchmark. * @param {{ba

* 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

* Bitwise `AND` operation for input tensors. * * Given two input tensors, returns a new tensor * with the `AND` calculated values. * * The method

* Apply boolean mask to tensor. * * ```js * const tensor = tf.tensor2d([1, 2, 3, 4, 5, 6], [3, 2]); * const mask = tf.tensor1d([1, 0, 1], 'bool');