Skip to content

add logger for total distance #351

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MaggieQi merged 1 commit into from
Jan 6, 2023
Merged

add logger for total distance #351

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 15 additions & 3 deletions AnnService/src/BalancedDataPartition/main.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
// Copyright (c) Microsoft Corporation. All rights reserved.
// Licensed under the MIT License.
// Copyright (c) Microsoft Corporation. All rights reserved.
// Licensed under the MIT License.

#include <mpi.h>
#include <thread>
Expand Down Expand Up @@ -156,6 +156,8 @@ inline float MultipleClustersAssign(const COMMON::Dataset<T>& data,
for (int k = 0; k < args._K; k++) avgCount += args.counts[k];
avgCount /= args._K;

std::vector<float> dist_total(args._K * args._T, 0);

auto func = [&](int tid)
{
SizeType istart = first + tid * subsize;
Expand All @@ -165,6 +167,7 @@ inline float MultipleClustersAssign(const COMMON::Dataset<T>& data,
float* inewCenters = args.newCenters + tid * args._K * args._D;
SizeType* iclusterIdx = args.clusterIdx + tid * args._K;
float* iclusterDist = args.clusterDist + tid * args._K;
float* idist_total = dist_total.data() + tid * args._K;
float idist = 0;
std::vector<SPTAG::NodeDistPair> centerDist(args._K, SPTAG::NodeDistPair());
for (SizeType i = istart; i < iend; i++) {
Expand All @@ -184,6 +187,7 @@ inline float MultipleClustersAssign(const COMMON::Dataset<T>& data,
inewCounts[centerDist[k].node]++;
inewWeightedCounts[centerDist[k].node] += weights[indices[i]];
idist += centerDist[k].distance;
idist_total[centerDist[k].node] += centerDist[k].distance;

if (updateCenters) {
const T* v = (const T*)data[indices[i]];
Expand Down Expand Up @@ -217,9 +221,15 @@ inline float MultipleClustersAssign(const COMMON::Dataset<T>& data,
for (int k = 0; k < args._K; k++) {
args.newCounts[k] += args.newCounts[i*args._K + k];
args.newWeightedCounts[k] += args.newWeightedCounts[i*args._K + k];
dist_total[k] += dist_total[i * args._K + k];
}
}

LOG(Helper::LogLevel::LL_Info, "start printing dist_total\n");
for (int k = 0; k < args._K; k++) {
LOG(Helper::LogLevel::LL_Info, "cluster %d: dist_total:%f \n", k, dist_total[k]);
}

if (updateCenters) {
for (int i = 1; i < args._T; i++) {
float* currCenter = args.newCenters + i*args._K*args._D;
Expand Down Expand Up @@ -768,7 +778,9 @@ void ProcessWithoutMPI() {
COMMON::KmeansArgs<T> args(options.m_clusterNum, vectors->Dimension(), vectors->Count(), options.m_threadNum, options.m_distMethod);
COMMON::Dataset<LabelType> label(vectors->Count(), options.m_clusterassign, vectors->Count(), vectors->Count());
std::vector<SizeType> localindices(data.R(), 0);
for (SizeType i = 0; i < data.R(); i++) localindices[i] = i;
for (SizeType i = 0; i < data.R(); i++) {
localindices[i] = i;
}
args.ClearCounts();

unsigned long long totalCount;
Expand Down