package owl-base

  1. Overview
  2. Docs
package owl-base
Legend:
Page
Library
Module
Module type
Parameter
Class
Class type
Source

Source file owl_neural_graph.ml

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
# 1 "src/base/neural/owl_neural_graph.ml"
(*
 * OWL - OCaml Scientific Computing
 * Copyright (c) 2016-2022 Liang Wang <liang@ocaml.xyz>
 *)

(** Neural network: Graphical neural network *)

open Owl_types

(* Make functor starts *)

module Make (Neuron : Owl_neural_neuron_sig.Sig) = struct
  module Neuron = Neuron
  open Neuron
  open Neuron.Optimise.Algodiff

  (* graph network and node definition *)

  type node =
    { mutable name : string
    ; (* name of a node *)
      mutable prev : node array
    ; (* parents of a node *)
      mutable next : node array
    ; (* children of a node *)
      mutable neuron : neuron
    ; (* neuron contained in a node *)
      mutable output : t option
    ; (* output of a node *)
      mutable network : network
    ; (* network a node belongs to *)
      mutable train : bool (* specify if a node is only for training *)
    }

  and network =
    { mutable nnid : string
    ; (* name of the graph network *)
      mutable size : int
    ; (* size of the graph network *)
      mutable roots : node array
    ; (* roots of the graph network, i.e. inputs *)
      mutable outputs : node array
    ; (* outputs of the graph network *)
      mutable topo : node array (* nodes sorted in topological order *)
    }

  (* functions to manipulate the network *)

  let make_network ?nnid size roots topo =
    let nnid =
      match nnid with
      | Some s -> s
      | None   -> "Graphical network"
    in
    { nnid; size; roots; topo; outputs = [||] }


  let make_node ?name ?(train = false) prev next neuron output network =
    let name =
      match name with
      | Some s -> s
      | None   -> Printf.sprintf "%s_%i" (to_name neuron) network.size
    in
    { name; prev; next; neuron; output; network; train }


  let get_roots nn =
    match nn.roots with
    | [||] -> failwith "Owl_neural_graph:get_roots"
    | x    -> x


  let get_outputs nn = nn.outputs

  let get_node nn name =
    let x = Owl_utils.Array.filter (fun n -> n.name = name) nn.topo in
    if Array.length x = 0 then failwith "Owl_neural_graph:get_node" else x.(0)


  let get_network ?name n =
    let name =
      match name with
      | Some s -> s
      | None   -> Random.int 65535 |> string_of_int
    in
    n.network.nnid <- name;
    (* if run and run_inputs are merged, the next line is necessary. *)
    n.network.outputs <- [| n |];
    n.network


  let outputs ?name nodes =
    assert (Array.length nodes > 0);
    let name =
      match name with
      | Some s -> s
      | None   -> Random.int 65535 |> string_of_int
    in
    (* assumes that all the outputs are part of the same network *)
    let nn = nodes.(0).network in
    nn.nnid <- name;
    nn.outputs <- nodes;
    nn


  let get_network_name n = n.nnid

  let set_network_name n name = n.nnid <- name

  let input_shape n = (get_roots n).(0).neuron |> Neuron.get_in_shape

  let input_shapes n = Array.map (fun r -> r.neuron |> Neuron.get_in_shape) (get_roots n)

  (* collect the outputs of a given set of nodes *)
  let collect_output nodes =
    Array.map
      (fun n ->
        match n.output with
        | Some o -> o
        | None   -> failwith "Owl_neural_graph:collect_output")
      nodes


  let connect_pair prev next =
    if Array.mem prev next.prev = false
    then next.prev <- Array.append next.prev [| prev |];
    if Array.mem next prev.next = false
    then prev.next <- Array.append prev.next [| next |]


  let connect_to_parents parents child =
    (* update the child's input and output shape *)
    if Array.length parents > 0
    then (
      let out_shapes = Array.map (fun n -> n.neuron |> get_out_shape) parents in
      connect out_shapes child.neuron);
    (* connect the child to the parents *)
    Array.iter (fun p -> connect_pair p child) parents


  (* add child node to nn and connect to parents *)
  let rec add_node ?act_typ nn parents child =
    nn.size <- nn.size + 1;
    connect_to_parents parents child;
    nn.topo <- Array.append nn.topo [| child |];
    child.network <- nn;
    (* if activation is specified, recursively add_node *)
    match act_typ with
    | Some act ->
      let neuron = Activation (Activation.create act) in
      let child_of_child = make_node [||] [||] neuron None nn in
      add_node nn [| child |] child_of_child
    | None     -> child


  (* functions to interface to optimisation engine *)

  let init nn = Array.iter (fun n -> init n.neuron) nn.topo

  let reset nn = Array.iter (fun n -> reset n.neuron) nn.topo

  let mktag t nn = Array.iter (fun n -> mktag t n.neuron) nn.topo

  let mkpar nn = Array.map (fun n -> mkpar n.neuron) nn.topo

  let mkpri nn = Array.map (fun n -> mkpri n.neuron) nn.topo

  let mkadj nn = Array.map (fun n -> mkadj n.neuron) nn.topo

  let update nn us = Array.iter2 (fun n u -> update n.neuron u) nn.topo us

  let run_inputs inputs nn =
    assert (Array.(length inputs = length (get_roots nn)));
    Array.iter
      (fun n ->
        (* collect the inputs from parents' output *)
        let input =
          match n.neuron with
          | Input _ ->
            let index =
              Owl_utils.Array.index_of (Array.map (fun r -> r.name) (get_roots nn)) n.name
            in
            [| inputs.(index) |]
          | _       -> collect_output n.prev
        in
        (* process the current neuron, save output *)
        let output = run input n.neuron in
        n.output <- Some output)
      nn.topo;
    (* collect the final outputs *)
    collect_output nn.outputs


  let run x nn =
    Array.iter
      (fun n ->
        (* collect the inputs from parents' output *)
        let input =
          match n.neuron with
          | Input _ -> [| x |]
          | _       -> collect_output n.prev
        in
        (* process the current neuron, save output *)
        let output = run input n.neuron in
        n.output <- Some output)
      nn.topo;
    (* collect the final output from the tail *)
    let sink = [| nn.topo.(Array.length nn.topo - 1) |] in
    (collect_output sink).(0)


  let forward nn x =
    mktag (tag ()) nn;
    run x nn, mkpar nn


  let forward_inputs nn x =
    mktag (tag ()) nn;
    run_inputs x nn, mkpar nn


  let backward nn y =
    reverse_prop (_f 1.) y;
    mkpri nn, mkadj nn


  let copy nn =
    let nn' = make_network ~nnid:nn.nnid nn.size [||] [||] in
    (* first iteration to copy the neurons *)
    nn'.topo
      <- Array.map
           (fun node ->
             let neuron' = copy node.neuron in
             make_node ~name:node.name ~train:node.train [||] [||] neuron' None nn')
           nn.topo;
    (* second iteration to re-construct the structure and infer the shape *)
    Array.iter2
      (fun node node' ->
        node'.prev <- Array.map (fun n -> get_node nn' n.name) node.prev;
        node'.next <- Array.map (fun n -> get_node nn' n.name) node.next;
        connect_to_parents node'.prev node')
      nn.topo
      nn'.topo;
    (* set roots and outputs to finalise the structure *)
    nn'.roots <- Array.map (fun n -> get_node nn' n.name) (get_roots nn);
    nn'.outputs <- Array.map (fun n -> get_node nn' n.name) (get_outputs nn);
    nn'


  let _remove_training_nodes nn =
    let topo' =
      Owl_utils.Array.filter
        (fun n ->
          if n.train = true
          then (
            (* remove myself from my parents *)
            Array.iter
              (fun m ->
                let next' = Owl_utils.Array.filter (fun x -> x.name <> n.name) m.next in
                m.next <- next')
              n.prev;
            (* remove myself from my children *)
            Array.iter
              (fun m ->
                let prev' = Owl_utils.Array.filter (fun x -> x.name <> n.name) m.prev in
                m.prev <- prev')
              n.next;
            (* connect my parents and my children *)
            Array.iter (connect_to_parents n.prev) n.next);
          not n.train)
        nn.topo
    in
    nn.topo <- topo'


  let model nn =
    if Array.length nn.roots > 1
    then failwith "Owl_neural_graph:model Did you mean to use model_inputs?";
    let nn = copy nn in
    _remove_training_nodes nn;
    let inference x =
      match run (Arr x) nn with
      | Arr y -> y
      | _     -> failwith "Owl_neural_graph:model"
    in
    inference


  let model_inputs nn =
    let nn = copy nn in
    _remove_training_nodes nn;
    let inference inputs =
      let outputs = run_inputs (Array.map (fun x -> Arr x) inputs) nn in
      Array.map unpack_arr outputs
    in
    inference


  (* functions to create functional nodes *)

  let input ?name inputs =
    let neuron = Input (Input.create inputs) in
    let nn = make_network 0 [||] [||] in
    let n = make_node ?name [||] [||] neuron None nn in
    nn.roots <- [| n |];
    add_node nn [||] n


  let inputs ?names input_shapes =
    let names =
      match names with
      | Some x ->
        assert (Array.(length x = length input_shapes));
        Array.map (fun name -> Some name) x
      | None   -> Array.(make (length input_shapes) None)
    in
    let neurons = Array.map (fun s -> Input (Input.create s)) input_shapes in
    let nn = make_network 0 [||] [||] in
    let ns =
      Array.map2
        (fun n name -> make_node ?name [||] [||] n None nn |> add_node nn [||])
        neurons
        names
    in
    nn.roots <- ns;
    ns


  let activation ?name act_typ input_node =
    let neuron = Activation (Activation.create act_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let linear ?name ?(init_typ = Init.Standard) ?act_typ outputs input_node =
    let neuron = Linear (Linear.create outputs init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let linear_nobias ?name ?(init_typ = Init.Standard) ?act_typ outputs input_node =
    let neuron = LinearNoBias (LinearNoBias.create outputs init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let embedding ?name ?(init_typ = Init.Standard) ?act_typ in_dim out_dim input_node =
    let neuron = Embedding (Embedding.create in_dim out_dim init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let recurrent ?name ?(init_typ = Init.Standard) ~act_typ outputs hiddens input_node =
    let neuron = Recurrent (Recurrent.create hiddens outputs act_typ init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let lstm ?name ?(init_typ = Init.Tanh) cells input_node =
    let neuron = LSTM (LSTM.create cells init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let gru ?name ?(init_typ = Init.Tanh) cells input_node =
    let neuron = GRU (GRU.create cells init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let conv1d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron = Conv1D (Conv1D.create padding kernel stride init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let conv2d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron = Conv2D (Conv2D.create padding kernel stride init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let conv3d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron = Conv3D (Conv3D.create padding kernel stride init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let dilated_conv1d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      rate
      input_node
    =
    let neuron =
      DilatedConv1D (DilatedConv1D.create padding kernel stride rate init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let dilated_conv2d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      rate
      input_node
    =
    let neuron =
      DilatedConv2D (DilatedConv2D.create padding kernel stride rate init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let dilated_conv3d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      rate
      input_node
    =
    let neuron =
      DilatedConv3D (DilatedConv3D.create padding kernel stride rate init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let transpose_conv1d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron =
      TransposeConv1D (TransposeConv1D.create padding kernel stride init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let transpose_conv2d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron =
      TransposeConv2D (TransposeConv2D.create padding kernel stride init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let transpose_conv3d
      ?name
      ?(padding = SAME)
      ?(init_typ = Init.Tanh)
      ?act_typ
      kernel
      stride
      input_node
    =
    let neuron =
      TransposeConv3D (TransposeConv3D.create padding kernel stride init_typ)
    in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let fully_connected ?name ?(init_typ = Init.Standard) ?act_typ outputs input_node =
    let neuron = FullyConnected (FullyConnected.create outputs init_typ) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let max_pool1d ?name ?(padding = SAME) ?act_typ kernel stride input_node =
    let neuron = MaxPool1D (MaxPool1D.create padding kernel stride) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let max_pool2d ?name ?(padding = SAME) ?act_typ kernel stride input_node =
    let neuron = MaxPool2D (MaxPool2D.create padding kernel stride) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let avg_pool1d ?name ?(padding = SAME) ?act_typ kernel stride input_node =
    let neuron = AvgPool1D (AvgPool1D.create padding kernel stride) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let avg_pool2d ?name ?(padding = SAME) ?act_typ kernel stride input_node =
    let neuron = AvgPool2D (AvgPool2D.create padding kernel stride) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let global_max_pool1d ?name ?act_typ input_node =
    let neuron = GlobalMaxPool1D (GlobalMaxPool1D.create ()) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let global_max_pool2d ?name ?act_typ input_node =
    let neuron = GlobalMaxPool2D (GlobalMaxPool2D.create ()) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let global_avg_pool1d ?name ?act_typ input_node =
    let neuron = GlobalAvgPool1D (GlobalAvgPool1D.create ()) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let global_avg_pool2d ?name ?act_typ input_node =
    let neuron = GlobalAvgPool2D (GlobalAvgPool2D.create ()) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let upsampling2d ?name ?act_typ size input_node =
    let neuron = UpSampling2D (UpSampling2D.create size) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let padding2d ?name ?act_typ padding input_node =
    let neuron = Padding2D (Padding2D.create padding) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let dropout ?name rate input_node =
    let neuron = Dropout (Dropout.create rate) in
    let nn = get_network input_node in
    let n = make_node ?name ~train:true [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let gaussian_noise ?name sigma input_node =
    let neuron = GaussianNoise (GaussianNoise.create sigma) in
    let nn = get_network input_node in
    let n = make_node ?name ~train:true [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let gaussian_dropout ?name rate input_node =
    let neuron = GaussianDropout (GaussianDropout.create rate) in
    let nn = get_network input_node in
    let n = make_node ?name ~train:true [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let alpha_dropout ?name rate input_node =
    let neuron = AlphaDropout (AlphaDropout.create rate) in
    let nn = get_network input_node in
    let n = make_node ?name ~train:true [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let normalisation ?name ?(axis = -1) ?training ?decay ?mu ?var input_node =
    let neuron = Normalisation (Normalisation.create ?training ?decay ?mu ?var axis) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let reshape ?name outputs input_node =
    let neuron = Reshape (Reshape.create outputs) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let flatten ?name input_node =
    let neuron = Flatten (Flatten.create ()) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let slice ?name slice input_node =
    let neuron = Slice (Slice.create slice) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node nn [| input_node |] n


  let lambda ?name ?act_typ ?out_shape lambda input_node =
    let neuron = Lambda (Lambda.create ?out_shape lambda) in
    let nn = get_network input_node in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn [| input_node |] n


  let lambda_array ?name ?act_typ out_shape lambda input_node =
    let neuron = LambdaArray (LambdaArray.create out_shape lambda) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let add ?name ?act_typ input_node =
    let neuron = Add (Add.create ()) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let mul ?name ?act_typ input_node =
    let neuron = Mul (Mul.create ()) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let dot ?name ?act_typ input_node =
    let neuron = Dot (Dot.create ()) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let max ?name ?act_typ input_node =
    let neuron = Max (Max.create ()) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let average ?name ?act_typ input_node =
    let neuron = Average (Average.create ()) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  let concatenate ?name ?act_typ axis input_node =
    let neuron = Concatenate (Concatenate.create axis) in
    let nn = get_network input_node.(0) in
    let n = make_node ?name [||] [||] neuron None nn in
    add_node ?act_typ nn input_node n


  (* I/O functions *)

  let to_string nn =
    let s = ref (nn.nnid ^ "\n\n") in
    Array.iter
      (fun n ->
        let prev =
          Array.map (fun n -> n.name) n.prev |> Owl_utils_array.to_string (fun s -> s)
        in
        let next =
          Array.map (fun n -> n.name) n.next |> Owl_utils_array.to_string (fun s -> s)
        in
        s
          := !s
             ^ Printf.sprintf "\x1b[31m[ Node %s ]:\x1b[0m\n" n.name
             ^ Printf.sprintf "%s" (to_string n.neuron)
             ^ Printf.sprintf "    prev:[%s] next:[%s]\n\n" prev next)
      nn.topo;
    !s


  let pp_network formatter nn =
    Format.open_box 0;
    Format.fprintf formatter "%s" (to_string nn);
    Format.close_box ()


  let print nn = pp_network Format.std_formatter nn

  let save ?(unsafe = false) nn f =
    if unsafe = true
    then (
      Owl_log.warn
        "Unsafely saved network can only be loaded back in exactly the same version of \
         OCaml and Owl.";
      Owl_io.marshal_to_file ~flags:[ Marshal.Closures ] (copy nn) f)
    else Owl_io.marshal_to_file (copy nn) f


  let load f : network = Owl_io.marshal_from_file f

  let save_weights nn f =
    let h = Hashtbl.create nn.size in
    Array.iter
      (fun n ->
        let ws = Neuron.save_weights n.neuron in
        Hashtbl.add h n.name ws)
      nn.topo;
    Owl_io.marshal_to_file h f


  let load_weights nn f =
    let h = Owl_io.marshal_from_file f in
    Array.iter
      (fun n ->
        let ws = Hashtbl.find h n.name in
        Neuron.load_weights n.neuron ws)
      nn.topo


  let make_subnetwork ?(copy = true) ?(make_inputs = [||]) nn output_names =
    let subnn = make_network 0 [||] [||] in
    let in_nodes = ref [] in
    (* collect neurons belonging to subnetwork *)
    let rec collect_subnn_nodes n acc =
      if List.exists (fun in_acc -> in_acc.name = n.name) acc
      then acc
      else if Array.mem n.name make_inputs
      then (
        let shape = get_out_shape n.neuron in
        let in_neur = Input (Input.create shape) in
        let new_in = make_node ~name:n.name [||] [||] in_neur None subnn in
        in_nodes := new_in :: !in_nodes;
        new_in :: acc)
      else (
        let neur = if copy then Neuron.copy n.neuron else n.neuron in
        let new_node = make_node ~name:n.name ~train:n.train [||] [||] neur None subnn in
        match neur with
        | Input _ ->
          in_nodes := new_node :: !in_nodes;
          new_node :: acc
        | _       ->
          let acc = new_node :: acc in
          Array.fold_left (fun a prev -> collect_subnn_nodes prev a) acc n.prev)
    in
    let new_nodes =
      Array.fold_left
        (fun acc name -> collect_subnn_nodes (get_node nn name) acc)
        []
        output_names
    in
    (* sorts the new topology *)
    let new_topo =
      Array.fold_left
        (fun acc n ->
          match List.find_opt (fun n' -> n'.name = n.name) new_nodes with
          | Some n' -> n' :: acc
          | None    -> acc)
        []
        nn.topo
      |> List.rev
      |> Array.of_list
    in
    subnn.topo <- new_topo;
    (* re-construct network structure *)
    Array.iter
      (fun node' ->
        let node = get_node nn node'.name in
        if not (List.memq node' !in_nodes)
        then node'.prev <- Array.map (fun n -> get_node subnn n.name) node.prev;
        if not (Array.mem node.name output_names)
        then (
          (* only process nodes that are part of the subnetwork *)
          let next =
            Owl_utils_array.filter
              (fun n -> Array.exists (fun n' -> n'.name = n.name) subnn.topo)
              node.next
          in
          (* With custom input nodes, next could contain an input node. *)
          node'.next <- Array.map (fun n -> get_node subnn n.name) next);
        connect_to_parents node'.prev node')
      subnn.topo;
    (* TODO: Warn if not all names in in_names were used? *)
    subnn.roots <- Array.of_list !in_nodes;
    subnn.outputs <- Array.map (fun name -> get_node subnn name) output_names;
    subnn


  (* training functions *)

  (* generic minimisation functions
     forward: function to run the forward pass
     backward: function to run the backward pass
     update: function to update the weights according to the gradient
     save: function to save the model for checkpoint
  *)
  let train_generic ?state ?params ?(init_model = true) nn x y =
    if init_model = true then init nn;
    let f = forward nn in
    let b = backward nn in
    let u = update nn in
    let s = save nn in
    let p =
      match params with
      | Some p -> p
      | None   -> Optimise.Params.default ()
    in
    Optimise.minimise_network ?state p f b u s x y


  let train ?state ?params ?init_model nn x y =
    train_generic ?state ?params ?init_model nn (Arr x) (Arr y)
end

(* Make functor ends *)
OCaml

Innovation. Community. Security.

GitHub Discord Twitter Peertube RSS
About
Changelog Releases Industrial Users Academic Users Why OCaml
Ecosystem
Packages Community Events OCaml Planet Jobs
Resources
Install OCaml Get Started Platform Tools Language Manual Standard Library API Books Exercises Papers OCaml Playground Logo
Policies
Carbon Footprint Governance Privacy Code of Conduct