1 /*
2 * Copyright (C) 2017 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17 #include "common/softmax.h"
18
19 #include <limits>
20
21 #include "common/fastexp.h"
22 #include "util/base/logging.h"
23
24 namespace libtextclassifier {
25 namespace nlp_core {
26
ComputeSoftmaxProbability(const std::vector<float> & scores,int label)27 float ComputeSoftmaxProbability(const std::vector<float> &scores, int label) {
28 if ((label < 0) || (label >= scores.size())) {
29 TC_LOG(ERROR) << "label " << label << " outside range "
30 << "[0, " << scores.size() << ")";
31 return 0.0f;
32 }
33
34 // Standard softmax formula for label's probability is
35 //
36 // exp(scores[label]) / sum_i exp(scores[i])
37 //
38 // We compute the mathematically equivalent
39 //
40 // 1 / (1 + sum_{i != label} exp(scores[i] - scores[label]))
41 //
42 // which saves two calls to exp().
43 const float label_score = scores[label];
44 float denominator = 1.0f; // Contribution of i == label.
45 for (int i = 0; i < scores.size(); ++i) {
46 if (i == label) continue;
47 const float delta_score = scores[i] - label_score;
48
49 // TODO(salcianu): one can optimize the test below, to avoid any float
50 // operation: extract exponent (via bit mask + shift) and check it's >= 4.
51 if (fabs(delta_score) >= 16.0f) {
52 if (delta_score > 0.0f) {
53 // If delta_score >= 16, the denominator (e^delta_score + other positive
54 // terms) is very big and its inverse can be approximated with 0.
55 return 0.0f;
56 } else {
57 // If delta_score <= -16, then e^delta_score < 1.2e-7. Even if we have
58 // 1000 such labels i, their sum is < 1.2e-4 (which gets summed with
59 // 1.0f for i == label). Hence, we can approximate each such label with
60 // 0 and skip the call to VeryFastExp and the update to denominator.
61 continue;
62 }
63 }
64
65 // At this point, delta_score is in (-16.0, 16.0). For such values, vfexp
66 // works fine: no under/overflows (we have tests for that in fastexp_test).
67 // Also, even for 1000 labels, denominator will not overflow.
68 denominator += VeryFastExp(delta_score);
69 }
70 return 1.0f / denominator;
71 }
72
ComputeSoftmax(const std::vector<float> & scores)73 std::vector<float> ComputeSoftmax(const std::vector<float> &scores) {
74 std::vector<float> softmax;
75 std::vector<float> exp_scores;
76 exp_scores.reserve(scores.size());
77 softmax.reserve(scores.size());
78
79 // Find max value in "scores" vector and rescale to avoid overflows.
80 float max = std::numeric_limits<float>::min();
81 for (const auto &score : scores) {
82 if (score > max) max = score;
83 }
84 float denominator = 0;
85 for (auto &score : scores) {
86 // See comments above in ComputeSoftmaxProbability for the reasoning behind
87 // this approximation.
88 const float exp_score = score - max < -16.0f ? 0 : VeryFastExp(score - max);
89 exp_scores.push_back(exp_score);
90 denominator += exp_score;
91 }
92
93 for (int i = 0; i < scores.size(); ++i) {
94 softmax.push_back(exp_scores[i] / denominator);
95 }
96 return softmax;
97 }
98
99 } // namespace nlp_core
100 } // namespace libtextclassifier
101