Skip to content
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

Fix multi-batch problem in int8 quantization #1604

Merged
merged 3 commits into from
Dec 5, 2024
Merged

Fix multi-batch problem in int8 quantization #1604

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
63e437a
Use the configuration of FP16 by default.
mpj1234 Nov 28, 2024
1d91d1b
Merge branch 'wang-xinyu:master' into master
mpj1234 Dec 5, 2024
970781e
Fix multi-batch problem in int8 quantization
mpj1234 Dec 5, 2024
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
14 changes: 7 additions & 7 deletions yolo11/src/model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ nvinfer1::IHostMemory* buildEngineYolo11Cls(nvinfer1::IBuilder* builder, nvinfer
std::cout << "Your platform supports int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
assert(builder->platformHasFastInt8());
config->setFlag(nvinfer1::BuilderFlag::kINT8);
auto* calibrator = new Int8EntropyCalibrator2(1, kClsInputW, kClsInputH, kInputQuantizationFolder,
auto* calibrator = new Int8EntropyCalibrator2(kBatchSize, kClsInputW, kClsInputH, kInputQuantizationFolder,
"int8calib.table", kInputTensorName);
config->setInt8Calibrator(calibrator);
#endif
Expand Down Expand Up @@ -392,8 +392,8 @@ nvinfer1::IHostMemory* buildEngineYolo11Det(nvinfer1::IBuilder* builder, nvinfer
std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
assert(builder->platformHasFastInt8());
config->setFlag(nvinfer1::BuilderFlag::kINT8);
auto* calibrator = new Int8EntropyCalibrator2(1, kInputW, kInputH, kInputQuantizationFolder, "int8calib.table",
kInputTensorName);
auto* calibrator = new Int8EntropyCalibrator2(kBatchSize, kInputW, kInputH, kInputQuantizationFolder,
"int8calib.table", kInputTensorName);
config->setInt8Calibrator(calibrator);
#endif

Expand Down Expand Up @@ -775,8 +775,8 @@ nvinfer1::IHostMemory* buildEngineYolo11Seg(nvinfer1::IBuilder* builder, nvinfer
std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
assert(builder->platformHasFastInt8());
config->setFlag(nvinfer1::BuilderFlag::kINT8);
auto* calibrator = new Int8EntropyCalibrator2(1, kInputW, kInputH, kInputQuantizationFolder, "int8calib.table",
kInputTensorName);
auto* calibrator = new Int8EntropyCalibrator2(kBatchSize, kInputW, kInputH, kInputQuantizationFolder,
"int8calib.table", kInputTensorName);
config->setInt8Calibrator(calibrator);
#endif

Expand Down Expand Up @@ -1066,8 +1066,8 @@ nvinfer1::IHostMemory* buildEngineYolo11Pose(nvinfer1::IBuilder* builder, nvinfe
std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
assert(builder->platformHasFastInt8());
config->setFlag(nvinfer1::BuilderFlag::kINT8);
auto* calibrator = new Int8EntropyCalibrator2(1, kInputW, kInputH, kInputQuantizationFolder, "int8calib.table",
kInputTensorName);
auto* calibrator = new Int8EntropyCalibrator2(kBatchSize, kInputW, kInputH, kInputQuantizationFolder,
"int8calib.table", kInputTensorName);
config->setInt8Calibrator(calibrator);
#endif

Expand Down
Loading