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
|
// Copyright 2017 The TensorFlow Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
syntax = "proto2";
package toco;
// Supported I/O file formats. Some formats may be input-only or output-only.
enum FileFormat {
FILE_FORMAT_UNKNOWN = 0;
// GraphDef, third_party/tensorflow/core/framework/graph.proto
TENSORFLOW_GRAPHDEF = 1;
// Tensorflow's mobile inference model.
// third_party/tensorflow/contrib/tflite/schema.fbs
TFLITE = 2;
// GraphViz
// Export-only.
GRAPHVIZ_DOT = 3;
}
// IODataType describes the numeric data types to be used by the output format.
// See input_type and inference_type below.
enum IODataType {
IO_DATA_TYPE_UNKNOWN = 0;
// Float32, not quantized
FLOAT = 1;
// Uint8, quantized
QUANTIZED_UINT8 = 2;
// Int32, not quantized
INT32 = 3;
// Int64, not quantized
INT64 = 4;
// String, not quantized
STRING = 5;
}
// TocoFlags encodes extra parameters that drive tooling operations, that
// are not normally encoded in model files and in general may not be thought
// of as properties of models, instead describing how models are to be
// processed in the context of the present tooling job.
// Next Id: 11
message TocoFlags {
// Input file format
optional FileFormat input_format = 1;
// Output file format
optional FileFormat output_format = 2;
// Numeric data types of the input arrays in the output format.
// This controls what input types the output file will be expecting.
// This is not a description of the input types of the input file.
// For example, the input file may have a float input placeholder,
// but we may want to generate a quantized TFLite file from it,
// or a float TFLite file taking a quantized input.
//
// The length of this list should match the length of the input_arrays
// list in ModelFlags.
repeated IODataType input_types = 9;
// Numeric data type of the internal activations array and output array.
//
// As a matter of implementation detail, most model
// parameter arrays (weights, etc) will tend to also use this data type.
// Not all will, though: for instance, bias vectors will typically
// get quantized as int32 when weights and activations get quantized as uint8.
optional IODataType inference_type = 4;
// default_ranges_min and default_ranges_max are helpers to experiment
// with quantization of models. Normally, quantization requires the input
// model to have (min, max) range information for every activations array.
// This is needed in order to know how to quantize arrays and still achieve
// satisfactory accuracy. However, in some circumstances one would just like
// to estimate the performance of quantized inference, without caring about
// accuracy. That is what default_ranges_min and default_ranges_max are for:
// when specified, they will be used as default (min, max) range boundaries
// for all activation arrays that lack (min, max) range information, thus
// allowing for quantization to proceed.
//
// It should be clear from the above explanation that these parameters are
// for experimentation purposes only and should not be used in production:
// they make it easy to quantize models, but the resulting quantized model
// will be inaccurate.
optional float default_ranges_min = 5;
optional float default_ranges_max = 6;
// Ignore and discard FakeQuant nodes. For instance, that can be used to
// generate plain float code without fake-quantization from a quantized
// graph.
optional bool drop_fake_quant = 7;
// Normally, FakeQuant nodes must be strict boundaries for graph
// transformations, in order to ensure that quantized inference has the
// exact same arithmetic behavior as quantized training --- which is the
// whole point of quantized training and of FakeQuant nodes in the first
// place. However, that entails subtle requirements on where exactly
// FakeQuant nodes must be placed in the graph. Some quantized graphs
// have FakeQuant nodes at unexpected locations, that prevent graph
// transformations that are necessary in order to generate inference
// code for these graphs. Such graphs should be fixed, but as a
// temporary work-around, setting this reorder_across_fake_quant flag
// allows toco to perform necessary graph transformaitons on them,
// at the cost of no longer faithfully matching inference and training
// arithmetic.
optional bool reorder_across_fake_quant = 8;
// If true, allow TOCO to create TF Lite Custom operators for all the
// unsupported Tensorflow ops.
optional bool allow_custom_ops = 10;
}
|
