This repository has been archived by the owner on Aug 5, 2022. It is now read-only.
/
caffe.proto
executable file
·2262 lines (2017 loc) · 86.6 KB
/
caffe.proto
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
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
syntax = "proto2";
package caffe;
// Specifies the shape (dimensions) of a Blob.
message BlobShape {
repeated int64 dim = 1 [packed = true];
}
message BlobProto {
optional BlobShape shape = 7;
repeated float data = 5 [packed = true];
repeated float diff = 6 [packed = true];
repeated double double_data = 8 [packed = true];
repeated double double_diff = 9 [packed = true];
// 4D dimensions -- deprecated. Use "shape" instead.
optional int32 num = 1 [default = 0];
optional int32 channels = 2 [default = 0];
optional int32 height = 3 [default = 0];
optional int32 width = 4 [default = 0];
}
// The BlobProtoVector is simply a way to pass multiple blobproto instances
// around.
message BlobProtoVector {
repeated BlobProto blobs = 1;
}
message Datum {
optional int32 channels = 1;
optional int32 height = 2;
optional int32 width = 3;
// the actual image data, in bytes
optional bytes data = 4;
optional int32 label = 5;
// Optionally, the datum could also hold float data.
repeated float float_data = 6;
// If true data contains an encoded image that need to be decoded
optional bool encoded = 7 [default = false];
}
// The label (display) name and label id.
message LabelMapItem {
// Both name and label are required.
optional string name = 1;
optional int32 label = 2;
// display_name is optional.
optional string display_name = 3;
}
message LabelMap {
repeated LabelMapItem item = 1;
}
// Sample a bbox in the normalized space [0, 1] with provided constraints.
message Sampler {
// Minimum scale of the sampled bbox.
optional float min_scale = 1 [default = 1.];
// Maximum scale of the sampled bbox.
optional float max_scale = 2 [default = 1.];
// Minimum aspect ratio of the sampled bbox.
optional float min_aspect_ratio = 3 [default = 1.];
// Maximum aspect ratio of the sampled bbox.
optional float max_aspect_ratio = 4 [default = 1.];
}
// Constraints for selecting sampled bbox.
message SampleConstraint {
// Minimum Jaccard overlap between sampled bbox and all bboxes in
// AnnotationGroup.
optional float min_jaccard_overlap = 1;
// Maximum Jaccard overlap between sampled bbox and all bboxes in
// AnnotationGroup.
optional float max_jaccard_overlap = 2;
// Minimum coverage of sampled bbox by all bboxes in AnnotationGroup.
optional float min_sample_coverage = 3;
// Maximum coverage of sampled bbox by all bboxes in AnnotationGroup.
optional float max_sample_coverage = 4;
// Minimum coverage of all bboxes in AnnotationGroup by sampled bbox.
optional float min_object_coverage = 5;
// Maximum coverage of all bboxes in AnnotationGroup by sampled bbox.
optional float max_object_coverage = 6;
}
// Sample a batch of bboxes with provided constraints.
message BatchSampler {
// Use original image as the source for sampling.
optional bool use_original_image = 1 [default = true];
// Constraints for sampling bbox.
optional Sampler sampler = 2;
// Constraints for determining if a sampled bbox is positive or negative.
optional SampleConstraint sample_constraint = 3;
// If provided, break when found certain number of samples satisfing the
// sample_constraint.
optional uint32 max_sample = 4;
// Maximum number of trials for sampling to avoid infinite loop.
optional uint32 max_trials = 5 [default = 100];
}
// Condition for emitting annotations.
message EmitConstraint {
enum EmitType {
CENTER = 0;
MIN_OVERLAP = 1;
}
optional EmitType emit_type = 1 [default = CENTER];
// If emit_type is MIN_OVERLAP, provide the emit_overlap.
optional float emit_overlap = 2;
}
// The normalized bounding box [0, 1] w.r.t. the input image size.
message NormalizedBBox {
optional float xmin = 1;
optional float ymin = 2;
optional float xmax = 3;
optional float ymax = 4;
optional int32 label = 5;
optional bool difficult = 6;
optional float score = 7;
optional float size = 8;
}
// Annotation for each object instance.
message Annotation {
optional int32 instance_id = 1 [default = 0];
optional NormalizedBBox bbox = 2;
}
// Group of annotations for a particular label.
message AnnotationGroup {
optional int32 group_label = 1;
repeated Annotation annotation = 2;
}
// An extension of Datum which contains "rich" annotations.
message AnnotatedDatum {
enum AnnotationType {
BBOX = 0;
}
optional Datum datum = 1;
// If there are "rich" annotations, specify the type of annotation.
// Currently it only supports bounding box.
// If there are no "rich" annotations, use label in datum instead.
optional AnnotationType type = 2;
// Each group contains annotation for a particular class.
repeated AnnotationGroup annotation_group = 3;
}
message FillerParameter {
// The filler type.
optional string type = 1 [default = 'constant'];
optional float value = 2 [default = 0]; // the value in constant filler
optional float min = 3 [default = 0]; // the min value in uniform filler
optional float max = 4 [default = 1]; // the max value in uniform filler
optional float mean = 5 [default = 0]; // the mean value in Gaussian filler
optional float std = 6 [default = 1]; // the std value in Gaussian filler
optional float scale = 9 [default = 1]; // the scale value in MSRA filler
// The expected number of non-zero output weights for a given input in
// Gaussian filler -- the default -1 means don't perform sparsification.
optional int32 sparse = 7 [default = -1];
// Normalize the filler variance by fan_in, fan_out, or their average.
// Applies to 'xavier' and 'msra' fillers.
enum VarianceNorm {
FAN_IN = 0;
FAN_OUT = 1;
AVERAGE = 2;
}
optional VarianceNorm variance_norm = 8 [default = FAN_IN];
}
message NetParameter {
optional string name = 1; // consider giving the network a name
// DEPRECATED. See InputParameter. The input blobs to the network.
repeated string input = 3;
// DEPRECATED. See InputParameter. The shape of the input blobs.
repeated BlobShape input_shape = 8;
// 4D input dimensions -- deprecated. Use "input_shape" instead.
// If specified, for each input blob there should be four
// values specifying the num, channels, height and width of the input blob.
// Thus, there should be a total of (4 * #input) numbers.
repeated int32 input_dim = 4;
// Whether the network will force every layer to carry out backward operation.
// If set False, then whether to carry out backward is determined
// automatically according to the net structure and learning rates.
optional bool force_backward = 5 [default = false];
// The current "state" of the network, including the phase, level, and stage.
// Some layers may be included/excluded depending on this state and the states
// specified in the layers' include and exclude fields.
optional NetState state = 6;
//The CompileNet will do some layer-fusion optimization to current network if it
//finds something can be optimized, compile_net_state records which Compilation Rule
//really works.
optional CompileNetState compile_net_state = 10;
// Print debugging information about results while running Net::Forward,
// Net::Backward, and Net::Update.
optional bool debug_info = 7 [default = false];
optional string engine = 9 [default = ""];
// Batch size used for BatchNorm statistics, 0 would use the batch size of bottom blob
optional uint32 bn_stats_batch_size = 11 [default = 0];
// The layers that make up the net. Each of their configurations, including
// connectivity and behavior, is specified as a LayerParameter.
repeated LayerParameter layer = 100; // ID 100 so layers are printed last.
// DEPRECATED: use 'layer' instead.
repeated V1LayerParameter layers = 2;
// Multinode settings
optional MultinodeParameter multinode = 101;
}
message CompileNetState {
optional bool is_init = 1 [default = true];
optional bool bn_scale_remove = 2 [default = false];
optional bool bn_scale_merge = 3 [default = false];
repeated string kept_bn_layers = 4;
repeated string negative_conv_names = 5;
repeated uint32 negative_conv_indexes = 6;
}
message MultinodeParameter {
repeated MnModelParallelParameter model_parallel = 1;
optional MnParamGradCompressLayerTypeList compress_layer_type_list = 2;
}
message MnModelParallelParameter {
required string layer_from = 1;
optional string layer_to = 2;
optional uint32 num_nodes = 3; // 0 means all nodes
optional uint32 model_parts = 4; // 0 or >= num_nodes, means all nodes
}
message MnParamGradCompressLayerTypeList {
repeated string layer_type = 1;
}
message MultiPhaseSolverParameter {
repeated SolverBatchSizePair params_pair = 1;
}
message SolverBatchSizePair {
optional SolverParameter solver_params = 1;
optional uint32 batch_size = 2;
}
// NOTE
// Update the next available ID when you add a new SolverParameter field.
//
// SolverParameter next available ID: 53 (last added: test_offset)
message SolverParameter {
//////////////////////////////////////////////////////////////////////////////
// Specifying the train and test networks
//
// Exactly one train net must be specified using one of the following fields:
// train_net_param, train_net, net_param, net
// One or more test nets may be specified using any of the following fields:
// test_net_param, test_net, net_param, net
// If more than one test net field is specified (e.g., both net and
// test_net are specified), they will be evaluated in the field order given
// above: (1) test_net_param, (2) test_net, (3) net_param/net.
// A test_iter must be specified for each test_net.
// A test_level and/or a test_stage may also be specified for each test_net.
//////////////////////////////////////////////////////////////////////////////
// Proto filename for the train net, possibly combined with one or more
// test nets.
optional string net = 24;
// Inline train net param, possibly combined with one or more test nets.
optional NetParameter net_param = 25;
optional string train_net = 1; // Proto filename for the train net.
repeated string test_net = 2; // Proto filenames for the test nets.
optional NetParameter train_net_param = 21; // Inline train net params.
repeated NetParameter test_net_param = 22; // Inline test net params.
// The states for the train/test nets. Must be unspecified or
// specified once per net.
//
// By default, all states will have solver = true;
// train_state will have phase = TRAIN,
// and all test_state's will have phase = TEST.
// Other defaults are set according to the NetState defaults.
optional NetState train_state = 26;
repeated NetState test_state = 27;
// Evaluation type.
optional string eval_type = 41 [default = "classification"];
// ap_version: different ways of computing Average Precision.
// Check https://sanchom.wordpress.com/tag/average-precision/ for details.
// 11point: the 11-point interpolated average precision. Used in VOC2007.
// MaxIntegral: maximally interpolated AP. Used in VOC2012/ILSVRC.
// Integral: the natural integral of the precision-recall curve.
optional string ap_version = 42 [default = "Integral"];
// If true, display per class result.
optional bool show_per_class_result = 43 [default = false];
// The number of iterations for each test net.
repeated int32 test_iter = 3;
// The number of iterations between two testing phases.
optional int32 test_interval = 4 [default = 0];
optional bool test_compute_loss = 19 [default = false];
// If true, run an initial test pass before the first iteration,
// ensuring memory availability and printing the starting value of the loss.
optional bool test_initialization = 32 [default = true];
optional float base_lr = 5; // The base learning rate
// the number of iterations between displaying info. If display = 0, no info
// will be displayed.
optional int32 display = 6;
// Display the loss averaged over the last average_loss iterations
optional int32 average_loss = 33 [default = 1];
optional int32 max_iter = 7; // the maximum number of iterations
// accumulate gradients over `iter_size` x `batch_size` instances
optional int32 iter_size = 36 [default = 1];
// The learning rate decay policy. The currently implemented learning rate
// policies are as follows:
// - fixed: always return base_lr.
// - step: return base_lr * gamma ^ (floor(iter / step))
// - exp: return base_lr * gamma ^ iter
// - inv: return base_lr * (1 + gamma * iter) ^ (- power)
// - multistep: similar to step but it allows non uniform steps defined by
// stepvalue
// - poly: the effective learning rate follows a polynomial decay, to be
// zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
// - sigmoid: the effective learning rate follows a sigmod decay
// return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
// - plateau: decreases lr
// if the minimum loss isn't updated for 'plateau_winsize' iters
//
// where base_lr, max_iter, gamma, step, stepvalue and power are defined
// in the solver parameter protocol buffer, and iter is the current iteration.
optional string lr_policy = 8;
optional float gamma = 9; // The parameter to compute the learning rate.
optional float power = 10; // The parameter to compute the learning rate.
optional float momentum = 11; // The momentum value.
optional float weight_decay = 12; // The weight decay.
// regularization types supported: L1 and L2
// controlled by weight_decay
optional string regularization_type = 29 [default = "L2"];
// the stepsize for learning rate policy "step"
optional int32 stepsize = 13;
// the stepsize for learning rate policy "multistep"
repeated int32 stepvalue = 34;
// the stepsize for learning rate policy "plateau"
repeated int32 plateau_winsize = 44;
// for rate policy "multifixed"
repeated float stagelr = 150;
repeated int32 stageiter = 151;
// Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm,
// whenever their actual L2 norm is larger.
optional float clip_gradients = 35 [default = -1];
optional int32 snapshot = 14 [default = 0]; // The snapshot interval
optional string snapshot_prefix = 15; // The prefix for the snapshot.
// whether to snapshot diff in the results or not. Snapshotting diff will help
// debugging but the final protocol buffer size will be much larger.
optional bool snapshot_diff = 16 [default = false];
enum SnapshotFormat {
HDF5 = 0;
BINARYPROTO = 1;
}
optional SnapshotFormat snapshot_format = 37 [default = BINARYPROTO];
// the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.
enum SolverMode {
CPU = 0;
GPU = 1;
}
optional SolverMode solver_mode = 17 [default = GPU];
// the device_id will that be used in GPU mode. Use device_id = 0 in default.
optional int32 device_id = 18 [default = 0];
// If non-negative, the seed with which the Solver will initialize the Caffe
// random number generator -- useful for reproducible results. Otherwise,
// (and by default) initialize using a seed derived from the system clock.
optional int64 random_seed = 20 [default = -1];
// type of the solver
optional string type = 40 [default = "SGD"];
// numerical stability for RMSProp, AdaGrad and AdaDelta and Adam
optional float delta = 31 [default = 1e-8];
// parameters for the Adam solver
optional float momentum2 = 39 [default = 0.999];
// RMSProp decay value
// MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
optional float rms_decay = 38 [default = 0.99];
// If true, print information about the state of the net that may help with
// debugging learning problems.
optional bool debug_info = 23 [default = false];
// If false, don't save a snapshot after training finishes.
optional bool snapshot_after_train = 28 [default = true];
// DEPRECATED: old solver enum types, use string instead
enum SolverType {
SGD = 0;
NESTEROV = 1;
ADAGRAD = 2;
RMSPROP = 3;
ADADELTA = 4;
ADAM = 5;
}
// DEPRECATED: use type instead of solver_type
optional SolverType solver_type = 30 [default = SGD];
optional bool disabled_update = 46 [default = false];
optional string engine = 47 [default = ""];
optional int32 warmup_iter = 48 [default = 0];
optional float warmup_start_lr = 49 [default = 0];
optional bool local_lr_auto = 50 [default = false];
optional float local_gw_ratio = 51 [default = 0.001];
// Number of iterations before starting the first test run
optional int32 test_offset = 52 [default = 0];
}
// A message that stores the solver snapshots
message SolverState {
optional int32 iter = 1; // The current iteration
optional string learned_net = 2; // The file that stores the learned net.
repeated BlobProto history = 3; // The history for sgd solvers
optional int32 current_step = 4 [default = 0]; // The current step for learning rate
optional float minimum_loss = 5 [default = 1E38]; // Historical minimum loss
optional int32 iter_last_event = 6 [default = 0]; // The iteration when last lr-update or min_loss-update happend
}
enum Phase {
TRAIN = 0;
TEST = 1;
}
message NetState {
optional Phase phase = 1 [default = TEST];
optional int32 level = 2 [default = 0];
repeated string stage = 3;
}
message NetStateRule {
// Set phase to require the NetState have a particular phase (TRAIN or TEST)
// to meet this rule.
optional Phase phase = 1;
// Set the minimum and/or maximum levels in which the layer should be used.
// Leave undefined to meet the rule regardless of level.
optional int32 min_level = 2;
optional int32 max_level = 3;
// Customizable sets of stages to include or exclude.
// The net must have ALL of the specified stages and NONE of the specified
// "not_stage"s to meet the rule.
// (Use multiple NetStateRules to specify conjunctions of stages.)
repeated string stage = 4;
repeated string not_stage = 5;
}
// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
message ParamSpec {
// The names of the parameter blobs -- useful for sharing parameters among
// layers, but never required otherwise. To share a parameter between two
// layers, give it a (non-empty) name.
optional string name = 1;
// Whether to require shared weights to have the same shape, or just the same
// count -- defaults to STRICT if unspecified.
optional DimCheckMode share_mode = 2;
enum DimCheckMode {
// STRICT (default) requires that num, channels, height, width each match.
STRICT = 0;
// PERMISSIVE requires only the count (num*channels*height*width) to match.
PERMISSIVE = 1;
}
// The multiplier on the global learning rate for this parameter.
optional float lr_mult = 3 [default = 1.0];
// The multiplier on the global weight decay for this parameter.
optional float decay_mult = 4 [default = 1.0];
}
// NOTE
// Update the next available ID when you add a new LayerParameter field.
//
// LayerParameter next available layer-specific ID: 157 (last added: mn_grad_compress_param)
message LayerParameter {
optional string name = 1; // the layer name
optional string type = 2; // the layer type
repeated string bottom = 3; // the name of each bottom blob
repeated string top = 4; // the name of each top blob
// The train / test phase for computation.
optional Phase phase = 10;
// The amount of weight to assign each top blob in the objective.
// Each layer assigns a default value, usually of either 0 or 1,
// to each top blob.
repeated float loss_weight = 5;
// Specifies training parameters (multipliers on global learning constants,
// and the name and other settings used for weight sharing).
repeated ParamSpec param = 6;
// The blobs containing the numeric parameters of the layer.
repeated BlobProto blobs = 7;
// Specifies whether to backpropagate to each bottom. If unspecified,
// Caffe will automatically infer whether each input needs backpropagation
// to compute parameter gradients. If set to true for some inputs,
// backpropagation to those inputs is forced; if set false for some inputs,
// backpropagation to those inputs is skipped.
//
// The size must be either 0 or equal to the number of bottoms.
repeated bool propagate_down = 11;
// Rules controlling whether and when a layer is included in the network,
// based on the current NetState. You may specify a non-zero number of rules
// to include OR exclude, but not both. If no include or exclude rules are
// specified, the layer is always included. If the current NetState meets
// ANY (i.e., one or more) of the specified rules, the layer is
// included/excluded.
repeated NetStateRule include = 8;
repeated NetStateRule exclude = 9;
// Parameters for data pre-processing.
optional TransformationParameter transform_param = 100;
// Parameters shared by loss layers.
optional LossParameter loss_param = 101;
// Layer type-specific parameters.
//
// Note: certain layers may have more than one computational engine
// for their implementation. These layers include an Engine type and
// engine parameter for selecting the implementation.
// The default for the engine is set by the ENGINE switch at compile-time.
optional AccuracyParameter accuracy_param = 102;
optional AnnotatedDataParameter annotated_data_param = 200;
optional ArgMaxParameter argmax_param = 103;
optional BatchNormParameter batch_norm_param = 139;
optional BoxAnnotatorOHEMParameter box_annotator_ohem_param = 152;
optional BiasParameter bias_param = 141;
optional ConcatParameter concat_param = 104;
optional ContrastiveLossParameter contrastive_loss_param = 105;
optional ConvolutionParameter convolution_param = 106;
optional CropParameter crop_param = 144;
optional DataParameter data_param = 107;
optional DetectionEvaluateParameter detection_evaluate_param = 205;
optional DetectionOutputParameter detection_output_param = 204;
optional DropoutParameter dropout_param = 108;
optional DummyDataParameter dummy_data_param = 109;
optional EltwiseParameter eltwise_param = 110;
optional ELUParameter elu_param = 140;
optional EmbedParameter embed_param = 137;
optional ExpParameter exp_param = 111;
optional FlattenParameter flatten_param = 135;
optional HDF5DataParameter hdf5_data_param = 112;
optional HDF5OutputParameter hdf5_output_param = 113;
optional HingeLossParameter hinge_loss_param = 114;
optional ImageDataParameter image_data_param = 115;
optional InfogainLossParameter infogain_loss_param = 116;
optional InnerProductParameter inner_product_param = 117;
optional InputParameter input_param = 143;
optional LogParameter log_param = 134;
optional LRNParameter lrn_param = 118;
optional MemoryDataParameter memory_data_param = 119;
optional MultiBoxLossParameter multibox_loss_param = 201;
optional MVNParameter mvn_param = 120;
optional NormalizeParameter norm_param = 206;
optional ParameterParameter parameter_param = 145;
optional PermuteParameter permute_param = 202;
optional PoolingParameter pooling_param = 121;
optional PowerParameter power_param = 122;
optional PReLUParameter prelu_param = 131;
optional PSROIPoolingParameter psroi_pooling_param = 153;
optional PriorBoxParameter prior_box_param = 203;
optional PythonParameter python_param = 130;
optional RecurrentParameter recurrent_param = 146;
optional ReductionParameter reduction_param = 136;
optional ReLUParameter relu_param = 123;
optional ReshapeParameter reshape_param = 133;
optional ROIPoolingParameter roi_pooling_param = 154;
optional ScaleParameter scale_param = 142;
optional SigmoidParameter sigmoid_param = 124;
optional SmoothL1LossParameter smooth_l1_loss_param = 148;
optional SoftmaxParameter softmax_param = 125;
optional SPPParameter spp_param = 132;
optional SplitParameter split_param = 208;
optional SliceParameter slice_param = 126;
optional SwishParameter swish_param = 147;
optional TanHParameter tanh_param = 127;
optional ThresholdParameter threshold_param = 128;
optional TileParameter tile_param = 138;
optional VideoDataParameter video_data_param = 207;
optional WindowDataParameter window_data_param = 129;
optional SpatialDropoutParameter spatial_dropout_param = 155;
optional string engine = 149 [default = ""];
optional MultinodeLayerParameter multinode = 150;
optional MnActivationParameter mn_activation_param = 151;
optional MnParamGradCompressParameter mn_grad_compress_param = 156;
optional QuantizationParameter quantization_param = 158;
optional ReorgParameter reorg_param = 159;
optional RegionLossParameter region_loss_param = 209;
// Yolo detection evaluation layer
optional EvalDetectionParameter eval_detection_param = 301;
}
message RegionLossParameter{
//Yolo 9000
optional uint32 side = 1 [default = 13];
optional uint32 num_class = 2 [default = 20];
optional uint32 bias_match = 3 [default = 1];
optional uint32 coords = 4 [default = 4];
optional uint32 num = 5 [default = 5];
optional uint32 softmax = 6 [default = 1];
optional float jitter = 7 [default = 0.2];
optional uint32 rescore = 8 [default = 1];
optional float object_scale = 9 [default = 1.0];
optional float class_scale = 10 [default = 1.0];
optional float noobject_scale = 11 [default = 0.5];
optional float coord_scale = 12 [default = 5.0];
optional uint32 absolute = 13 [default = 1];
optional float thresh = 14 [default = 0.2];
optional uint32 random = 15 [default = 1];
repeated float biases = 16;
optional string softmax_tree = 17;
optional string class_map = 18;
}
message EvalDetectionParameter {
enum ScoreType {
OBJ = 0;
PROB = 1;
MULTIPLY = 2;
}
// Yolo detection evaluation layer
optional uint32 side = 1 [default = 7];
optional uint32 num_class = 2 [default = 20];
optional uint32 num_object = 3 [default = 2];
optional float threshold = 4 [default = 0.5];
optional bool sqrt = 5 [default = true];
optional bool constriant = 6 [default = true];
optional ScoreType score_type = 7 [default = MULTIPLY];
optional float nms = 8 [default = -1];
repeated float biases = 9;
}
message MultinodeLayerParameter {
// 0 means all nodes
optional uint32 num_nodes = 1;
// 0 or > num_nodes, means all nodes
optional uint32 model_parts = 2 [default = 1];
}
message MnActivationParameter {
// 0 means all nodes
optional uint32 num_nodes_in = 1;
// 0 means all nodes
optional uint32 num_nodes_out = 2;
// 0 or > num_nodes, means all nodes
optional uint32 model_parts_in = 3 [default = 1];
// 0 or > num_nodes, means all nodes
optional uint32 model_parts_out = 4 [default = 1];
optional bool need_reduce = 5 [default = true];
}
// Message for layers with reduced word with arithmetic
message QuantizationParameter{
enum Precision {
DYNAMIC_FIXED_POINT = 0;
}
optional Precision precision = 1 [default = DYNAMIC_FIXED_POINT];
enum Rounding {
NEAREST = 0;
}
optional Rounding rounding_scheme = 2 [default = NEAREST];
// Dynamic fixed point word width
optional uint32 bw_layer_in = 3 [default = 32];
optional uint32 bw_layer_out = 4 [default = 32];
optional uint32 bw_params = 5 [default = 32];
repeated int32 fl_layer_in = 6;
repeated int32 fl_layer_out = 7;
repeated int32 fl_params = 8;
repeated float scale_in = 20;
repeated float scale_out = 21;
repeated float scale_params = 22;
optional bool is_negative_input = 23 [default = false];
optional bool force_u8_input = 24 [default = false];
}
message MnParamGradCompressParameter {
repeated bool param_grad_compress_enable = 1;
}
// Message that stores parameters used to apply transformation
// to the data layer's data
message TransformationParameter {
// For data pre-processing, we can do simple scaling and subtracting the
// data mean, if provided. Note that the mean subtraction is always carried
// out before scaling.
optional float scale = 1 [default = 1];
// Specify if we want to randomly mirror data.
optional bool mirror = 2 [default = false];
// Specify if we would like to randomly crop an image.
optional uint32 crop_size = 3 [default = 0];
optional uint32 crop_h = 11 [default = 0];
optional uint32 crop_w = 12 [default = 0];
// mean_file and mean_value cannot be specified at the same time
optional string mean_file = 4;
// if specified can be repeated once (would substract it from all the channels)
// or can be repeated the same number of times as channels
// (would subtract them from the corresponding channel)
repeated float mean_value = 5;
// Force the decoded image to have 3 color channels.
optional bool force_color = 6 [default = false];
// Force the decoded image to have 1 color channels.
optional bool force_gray = 7 [default = false];
// Resize policy
optional ResizeParameter resize_param = 8;
// Noise policy
optional NoiseParameter noise_param = 9;
// Distortion policy
optional DistortionParameter distort_param = 13;
// Expand policy
optional ExpansionParameter expand_param = 14;
// Constraint for emitting the annotation after transformation.
optional EmitConstraint emit_constraint = 10;
// Resize the input randomly
optional RandomResizeParameter random_resize_param = 15;
optional RandomAspectRatioParameter random_aspect_ratio_param = 16;
//will flip x flow if flow image input
optional bool flow = 17 [default = false];
optional bool bgr2rgb = 18 [ default = false ];
optional uint32 pad = 19 [default = 0];
}
message RandomResizeParameter {
optional uint32 min_size = 1 [default = 0];
optional uint32 max_size = 2 [default = 0];
optional ResizeParameter resize_param = 3;
}
message RandomAspectRatioParameter {
optional float min_area_ratio = 1 [default = 0.5];
optional float max_area_ratio = 2 [default = 1];
optional float aspect_ratio_change = 3 [default = 1];
optional uint32 max_attempt = 4 [default = 10];
optional ResizeParameter resize_param = 5;
}
// Message that stores parameters used by data transformer for resize policy
message ResizeParameter {
//Probability of using this resize policy
optional float prob = 1 [default = 1];
enum Resize_mode {
WARP = 1;
FIT_SMALL_SIZE = 2;
FIT_LARGE_SIZE_AND_PAD = 3;
}
optional Resize_mode resize_mode = 2 [default = WARP];
optional uint32 height = 3 [default = 0];
optional uint32 width = 4 [default = 0];
// A parameter used to update bbox in FIT_SMALL_SIZE mode.
optional uint32 height_scale = 8 [default = 0];
optional uint32 width_scale = 9 [default = 0];
enum Pad_mode {
CONSTANT = 1;
MIRRORED = 2;
REPEAT_NEAREST = 3;
}
// Padding mode for BE_SMALL_SIZE_AND_PAD mode and object centering
optional Pad_mode pad_mode = 5 [default = CONSTANT];
// if specified can be repeated once (would fill all the channels)
// or can be repeated the same number of times as channels
// (would use it them to the corresponding channel)
repeated float pad_value = 6;
enum Interp_mode { //Same as in OpenCV
LINEAR = 1;
AREA = 2;
NEAREST = 3;
CUBIC = 4;
LANCZOS4 = 5;
}
//interpolation for for resizing
repeated Interp_mode interp_mode = 7;
}
message SaltPepperParameter {
//Percentage of pixels
optional float fraction = 1 [default = 0];
repeated float value = 2;
}
// Message that stores parameters used by data transformer for transformation
// policy
message NoiseParameter {
//Probability of using this resize policy
optional float prob = 1 [default = 0];
// Histogram equalized
optional bool hist_eq = 2 [default = false];
// Color inversion
optional bool inverse = 3 [default = false];
// Grayscale
optional bool decolorize = 4 [default = false];
// Gaussian blur
optional bool gauss_blur = 5 [default = false];
// JPEG compression quality (-1 = no compression)
optional float jpeg = 6 [default = -1];
// Posterization
optional bool posterize = 7 [default = false];
// Erosion
optional bool erode = 8 [default = false];
// Salt-and-pepper noise
optional bool saltpepper = 9 [default = false];
optional SaltPepperParameter saltpepper_param = 10;
// Local histogram equalization
optional bool clahe = 11 [default = false];
// Color space conversion
optional bool convert_to_hsv = 12 [default = false];
// Color space conversion
optional bool convert_to_lab = 13 [default = false];
}
// Message that stores parameters used by data transformer for distortion policy
message DistortionParameter {
// The probability of adjusting brightness.
optional float brightness_prob = 1 [default = 0.0];
// Amount to add to the pixel values within [-delta, delta].
// The possible value is within [0, 255]. Recommend 32.
optional float brightness_delta = 2 [default = 0.0];
// The probability of adjusting contrast.
optional float contrast_prob = 3 [default = 0.0];
// Lower bound for random contrast factor. Recommend 0.5.
optional float contrast_lower = 4 [default = 0.0];
// Upper bound for random contrast factor. Recommend 1.5.
optional float contrast_upper = 5 [default = 0.0];
// The probability of adjusting hue.
optional float hue_prob = 6 [default = 0.0];
// Amount to add to the hue channel within [-delta, delta].
// The possible value is within [0, 180]. Recommend 36.
optional float hue_delta = 7 [default = 0.0];
// The probability of adjusting saturation.
optional float saturation_prob = 8 [default = 0.0];
// Lower bound for the random saturation factor. Recommend 0.5.
optional float saturation_lower = 9 [default = 0.0];
// Upper bound for the random saturation factor. Recommend 1.5.
optional float saturation_upper = 10 [default = 0.0];
// The probability of randomly order the image channels.
optional float random_order_prob = 11 [default = 0.0];
}
// Message that stores parameters used by data transformer for expansion policy
message ExpansionParameter {
//Probability of using this expansion policy
optional float prob = 1 [default = 1];
// The ratio to expand the image.
optional float max_expand_ratio = 2 [default = 1.];
}
// Message that stores parameters shared by loss layers
message LossParameter {
// If specified, ignore instances with the given label.
optional int32 ignore_label = 1;
// How to normalize the loss for loss layers that aggregate across batches,
// spatial dimensions, or other dimensions. Currently only implemented in
// SoftmaxWithLoss and SigmoidCrossEntropyLoss layers.
enum NormalizationMode {
// Divide by the number of examples in the batch times spatial dimensions.
// Outputs that receive the ignore label will NOT be ignored in computing
// the normalization factor.
FULL = 0;
// Divide by the total number of output locations that do not take the
// ignore_label. If ignore_label is not set, this behaves like FULL.
VALID = 1;
// Divide by the batch size.
BATCH_SIZE = 2;
// Divide by pre-fixed normalizer
PRE_FIXED = 3;
// Do not normalize the loss.
NONE = 4;
}
// For historical reasons, the default normalization for
// SigmoidCrossEntropyLoss is BATCH_SIZE and *not* VALID.
optional NormalizationMode normalization = 3 [default = VALID];
// Deprecated. Ignored if normalization is specified. If normalization
// is not specified, then setting this to false will be equivalent to
// normalization = BATCH_SIZE to be consistent with previous behavior.
optional bool normalize = 2;
// pre-fixed normalizer
optional float pre_fixed_normalizer = 4 [default = 1];
optional float label_smoothing = 5 [default = 0.0];
}
// Messages that store parameters used by individual layer types follow, in
// alphabetical order.
message AccuracyParameter {
// When computing accuracy, count as correct by comparing the true label to
// the top k scoring classes. By default, only compare to the top scoring
// class (i.e. argmax).
optional uint32 top_k = 1 [default = 1];
// The "label" axis of the prediction blob, whose argmax corresponds to the
// predicted label -- may be negative to index from the end (e.g., -1 for the
// last axis). For example, if axis == 1 and the predictions are
// (N x C x H x W), the label blob is expected to contain N*H*W ground truth
// labels with integer values in {0, 1, ..., C-1}.
optional int32 axis = 2 [default = 1];
// If specified, ignore instances with the given label.
optional int32 ignore_label = 3;
}
message AnnotatedDataParameter {
// Define the sampler.
repeated BatchSampler batch_sampler = 1;
// Store label name and label id in LabelMap format.
optional string label_map_file = 2;
// If provided, it will replace the AnnotationType stored in each
// AnnotatedDatum.
optional AnnotatedDatum.AnnotationType anno_type = 3;
}
message ArgMaxParameter {
// If true produce pairs (argmax, maxval)
optional bool out_max_val = 1 [default = false];
optional uint32 top_k = 2 [default = 1];
// The axis along which to maximise -- may be negative to index from the
// end (e.g., -1 for the last axis).
// By default ArgMaxLayer maximizes over the flattened trailing dimensions
// for each index of the first / num dimension.
optional int32 axis = 3;
}
message ConcatParameter {
// The axis along which to concatenate -- may be negative to index from the
// end (e.g., -1 for the last axis). Other axes must have the
// same dimension for all the bottom blobs.
// By default, ConcatLayer concatenates blobs along the "channels" axis (1).
optional int32 axis = 2 [default = 1];
// DEPRECATED: alias for "axis" -- does not support negative indexing.
optional uint32 concat_dim = 1 [default = 1];
// For permute and flatten fuse in SSD-VGG16
optional bool per_fla_fuse = 4 [default = false];
enum Engine {
DEFAULT = 0;
CAFFE = 1;
MKL2017 = 3;
MKLDNN = 4;
}
optional Engine engine = 3 [default = DEFAULT];
}
message BatchNormParameter {