Contains type-agnostic deep neural networks (DNN) functions.

### Examples

The [Deep Learning for Programmers](https://aiprobook.com/deep-learning-for-programmers) book
contains very detailed examples and explanations. Please check it out.

The most up-to-date examples can be found in the
[comprehensive test suite](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond),
[full examples](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/functional),
[core tensor examples](https://github.com/uncomplicate/deep-diamond/blob/master/test/uncomplicate/diamond/tensor_test.clj)
[core DNN examples](https://github.com/uncomplicate/deep-diamond/blob/master/test/uncomplicate/diamond/dnn_test.clj)
[internal CPU engine tests](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/internal/dnnl),
[internal GPU engine tests](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/internal/cudnn),

### Cheat Sheet

* Basic dense layers: [[activation]], [[inner-product]], [[fully-connected]], [[dense]].

* Convolutional layers: [[convolution]], [[convo]].

* Recurrent layers [[rnn-op]], [[rnn]], [[abbreviate]].

* Training optimizations: [[pooling]], [[dropout-mask]], [[dropout]], [[batch-norm]].

* [[concatenate]], [[conc]], [[branch]], [[split]], [[sum]].

* Training and using the network: [[cost]], [[network]], [[init!]], [[train]], [[train-shuffle]], [[infer]].

Internal Deep Diamond API mostly relevant to programmers who write tools, extensions
and additional backend engines.

When implementing your own backend, in addition to the light documentation provided in this
namespace, please refer to the DNNL implementation and its tests. It is currently the most
complete one. Next, see the cuDNN GPU backend to see how it solves differences in general
approach to computation. There are countless small and not so small gotchas with these
complex technologies, so expect lots of debugging.

Classification evaluation functions.

Entry point to Deep Diamond's CPU engine (currently based on Intel's OneDNNL).
By evaluating this namespace, you're altering [[uncomplicate.diamond.tensor/*diamond-factory*]]
var root to the engine produced by [[uncomplicate.diamond.internal.dnnl.factory/dnnl-factory]].

(ns test
  (:require [uncomplicate.diamond
             [tensor :refer :all]
             [native :refer :all]]))

Contains type-agnostic general tensor functions. Does not contain functions related
to deep neural networks (DNN); see the [[dnn]] namespace for these.

### How to use

    (ns test
      (:require [uncomplicate.diamond
                 [tensor :refer :all]
                 [native :refer :all]]))

### Examples

The best and most accurate examples can be found in the
[comprehensive test suite](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond),
[full examples](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/functional),
[core tensor examples](https://github.com/uncomplicate/deep-diamond/blob/master/test/uncomplicate/diamond/tensor_test.clj)
[core DNN examples](https://github.com/uncomplicate/deep-diamond/blob/master/test/uncomplicate/diamond/dnn_test.clj)
[internal CPU engine tests](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/internal/dnnl),
[internal GPU engine tests](https://github.com/uncomplicate/deep-diamond/tree/master/test/uncomplicate/diamond/internal/cudnn),


There are quite a few tutorials [on my blog dragan.rocks](http://dragan.rocks).

For the comprehensive real-world examples, with detailed tutorials and guides, see the
[Interactive Programming for Artificial intelligence book series](aiprobook.com), and specifically
the [Deep Learning for Programmers](https://aiprobook.com/deep-learning-for-programmers) book.

  ### Cheat Sheet

* Default engine (factory) binding: [[*diamond-factory*]], [[with-diamond]]. All functions can also receive
  engine through parameters.

* Tensor descriptor: [[desc]], [[shape]], [[layout]], [[data-type]],

* Create : [[tensor]], [[transformer]], [[batcher]], [[shuffler]]

* Inspect, transform, and manage tensors: [[view-tz]], [[revert]], [[input]], [[output]],
[[connector]], [[batch-size]], [[offset!]].


Tensors support typical core Fluokitten functions.