Skip to content

[Tools] MlResponse: bugfix assure equality of number of checked features to that in the .onnx file #16722

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
fmazzasc merged 1 commit into from
Jun 18, 2026
+7 −6
Merged

[Tools] MlResponse: bugfix assure equality of number of checked features to that in the .onnx file #16722

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
13 changes: 7 additions & 6 deletions Tools/ML/MlResponse.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,14 +151,8 @@ class MlResponse
void init(bool enableOptimizations = false, int threads = 0)
{
uint8_t counterModel{0};
const int numCachedIndices = static_cast<int>(mCachedIndices.size());
for (const auto& path : mPaths) {
mModels[counterModel].initModel(path, enableOptimizations, threads);
const int numInputNodes = mModels[counterModel].getNumInputNodes();
if (numInputNodes != numCachedIndices) {
LOG(fatal) << "Number of input nodes in the model " << path << " is different from the number of input features indices (" << numInputNodes << " vs " << numCachedIndices << ")";
return;
}
++counterModel;
}
}
Expand Down Expand Up @@ -188,6 +182,13 @@ class MlResponse
LOG(fatal) << "Model index " << nModel << " is out of range! The number of initialised models is " << mModels.size() << ". Please check your configurables.";
}

const int numInputNodes = mModels[nModel].getNumInputNodes();
const int numInputFeatures = static_cast<int>(input.size());

if (numInputNodes != numInputFeatures) {
LOG(fatal) << "Number of input nodes in the model " << mPaths[nModel] << " is different from the number of input features to be tested (" << numInputNodes << " vs " << numInputFeatures << ")";
}

TypeOutputScore* outputPtr = mModels[nModel].template evalModel<TypeOutputScore>(input);
return std::vector<TypeOutputScore>{outputPtr, outputPtr + mNClasses};
}
Expand Down
Loading