haotian/duan8
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

give retinaface TRT8 support (#698)

Browse Source 
* give retinaface TRT8 support

* add macros.h to retinaface conversion

* add macros.h to retinaface conversion
This commit is contained in:
FamousDirector 2021-08-31 08:05:43 -03:00 committed by GitHub
parent 7c4476f23c
commit 9f9109fdc9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 76 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
retinaface/calibrator.cpp
View File

@ -26,12 +26,12 @@ Int8EntropyCalibrator2::~Int8EntropyCalibrator2()
CHECK(cudaFree(device_input_));
}
int Int8EntropyCalibrator2::getBatchSize() const
int Int8EntropyCalibrator2::getBatchSize() const TRT_NOEXCEPT
{
return batchsize_;
}
bool Int8EntropyCalibrator2::getBatch(void* bindings[], const char* names[], int nbBindings)
bool Int8EntropyCalibrator2::getBatch(void* bindings[], const char* names[], int nbBindings) TRT_NOEXCEPT
{
if (img_idx_ + batchsize_ > (int)img_files_.size()) {
return false;
@ -57,7 +57,7 @@ bool Int8EntropyCalibrator2::getBatch(void* bindings[], const char* names[], int
return true;
}
const void* Int8EntropyCalibrator2::readCalibrationCache(size_t& length)
const void* Int8EntropyCalibrator2::readCalibrationCache(size_t& length) TRT_NOEXCEPT
{
std::cout << "reading calib cache: " << calib_table_name_ << std::endl;
calib_cache_.clear();
@ -71,7 +71,7 @@ const void* Int8EntropyCalibrator2::readCalibrationCache(size_t& length)
return length ? calib_cache_.data() : nullptr;
}
void Int8EntropyCalibrator2::writeCalibrationCache(const void* cache, size_t length)
void Int8EntropyCalibrator2::writeCalibrationCache(const void* cache, size_t length) TRT_NOEXCEPT
{
std::cout << "writing calib cache: " << calib_table_name_ << " size: " << length << std::endl;
std::ofstream output(calib_table_name_, std::ios::binary);

9
retinaface/calibrator.h
View File

@ -4,6 +4,7 @@
#include "NvInfer.h"
#include <string>
#include <vector>
#include "macros.h"
//! \class Int8EntropyCalibrator2
//!
@ -16,10 +17,10 @@ public:
Int8EntropyCalibrator2(int batchsize, int input_w, int input_h, const char* img_dir, const char* calib_table_name, const char* input_blob_name, bool read_cache = true);
virtual ~Int8EntropyCalibrator2();
int getBatchSize() const override;
bool getBatch(void* bindings[], const char* names[], int nbBindings) override;
const void* readCalibrationCache(size_t& length) override;
void writeCalibrationCache(const void* cache, size_t length) override;
int getBatchSize() const TRT_NOEXCEPT override;
bool getBatch(void* bindings[], const char* names[], int nbBindings) TRT_NOEXCEPT override;
const void* readCalibrationCache(size_t& length) TRT_NOEXCEPT override;
void writeCalibrationCache(const void* cache, size_t length) TRT_NOEXCEPT override;
private:
int batchsize_;

46
retinaface/decode.cu
View File

@ -16,21 +16,21 @@ namespace nvinfer1
{
}
void DecodePlugin::serialize(void* buffer) const
void DecodePlugin::serialize(void* buffer) const TRT_NOEXCEPT
{
}
size_t DecodePlugin::getSerializationSize() const
{
size_t DecodePlugin::getSerializationSize() const TRT_NOEXCEPT
{
return 0;
}
int DecodePlugin::initialize()
int DecodePlugin::initialize() TRT_NOEXCEPT
{
return 0;
}
Dims DecodePlugin::getOutputDimensions(int index, const Dims* inputs, int nbInputDims)
Dims DecodePlugin::getOutputDimensions(int index, const Dims* inputs, int nbInputDims) TRT_NOEXCEPT
{
//output the result to channel
int totalCount = 0;
@ -42,63 +42,63 @@ namespace nvinfer1
}
// Set plugin namespace
void DecodePlugin::setPluginNamespace(const char* pluginNamespace)
void DecodePlugin::setPluginNamespace(const char* pluginNamespace) TRT_NOEXCEPT
{
mPluginNamespace = pluginNamespace;
}
const char* DecodePlugin::getPluginNamespace() const
const char* DecodePlugin::getPluginNamespace() const TRT_NOEXCEPT
{
return mPluginNamespace;
}
// Return the DataType of the plugin output at the requested index
DataType DecodePlugin::getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const
DataType DecodePlugin::getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const TRT_NOEXCEPT
{
return DataType::kFLOAT;
}
// Return true if output tensor is broadcast across a batch.
bool DecodePlugin::isOutputBroadcastAcrossBatch(int outputIndex, const bool* inputIsBroadcasted, int nbInputs) const
bool DecodePlugin::isOutputBroadcastAcrossBatch(int outputIndex, const bool* inputIsBroadcasted, int nbInputs) const TRT_NOEXCEPT
{
return false;
}
// Return true if plugin can use input that is broadcast across batch without replication.
bool DecodePlugin::canBroadcastInputAcrossBatch(int inputIndex) const
bool DecodePlugin::canBroadcastInputAcrossBatch(int inputIndex) const TRT_NOEXCEPT
{
return false;
}
void DecodePlugin::configurePlugin(const PluginTensorDesc* in, int nbInput, const PluginTensorDesc* out, int nbOutput)
void DecodePlugin::configurePlugin(const PluginTensorDesc* in, int nbInput, const PluginTensorDesc* out, int nbOutput) TRT_NOEXCEPT
{
}
// Attach the plugin object to an execution context and grant the plugin the access to some context resource.
void DecodePlugin::attachToContext(cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator)
void DecodePlugin::attachToContext(cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator) TRT_NOEXCEPT
{
}
// Detach the plugin object from its execution context.
void DecodePlugin::detachFromContext() {}
void DecodePlugin::detachFromContext() TRT_NOEXCEPT {}
const char* DecodePlugin::getPluginType() const
const char* DecodePlugin::getPluginType() const TRT_NOEXCEPT
{
return "Decode_TRT";
}
const char* DecodePlugin::getPluginVersion() const
const char* DecodePlugin::getPluginVersion() const TRT_NOEXCEPT
{
return "1";
}
void DecodePlugin::destroy()
void DecodePlugin::destroy() TRT_NOEXCEPT
{
delete this;
}
// Clone the plugin
IPluginV2IOExt* DecodePlugin::clone() const
IPluginV2IOExt* DecodePlugin::clone() const TRT_NOEXCEPT
{
DecodePlugin *p = new DecodePlugin();
p->setPluginNamespace(mPluginNamespace);
@ -190,7 +190,7 @@ namespace nvinfer1
}
}
int DecodePlugin::enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream)
int DecodePlugin::enqueue(int batchSize, const void*const * inputs, void*TRT_CONST_ENQUEUE* outputs, void* workspace, cudaStream_t stream) TRT_NOEXCEPT
{
//GPU
//CUDA_CHECK(cudaStreamSynchronize(stream));
@ -209,29 +209,29 @@ namespace nvinfer1
mFC.fields = mPluginAttributes.data();
}
const char* DecodePluginCreator::getPluginName() const
const char* DecodePluginCreator::getPluginName() const TRT_NOEXCEPT
{
return "Decode_TRT";
}
const char* DecodePluginCreator::getPluginVersion() const
const char* DecodePluginCreator::getPluginVersion() const TRT_NOEXCEPT
{
return "1";
}
const PluginFieldCollection* DecodePluginCreator::getFieldNames()
const PluginFieldCollection* DecodePluginCreator::getFieldNames() TRT_NOEXCEPT
{
return &mFC;
}
IPluginV2IOExt* DecodePluginCreator::createPlugin(const char* name, const PluginFieldCollection* fc)
IPluginV2IOExt* DecodePluginCreator::createPlugin(const char* name, const PluginFieldCollection* fc) TRT_NOEXCEPT
{
DecodePlugin* obj = new DecodePlugin();
obj->setPluginNamespace(mNamespace.c_str());
return obj;
}
IPluginV2IOExt* DecodePluginCreator::deserializePlugin(const char* name, const void* serialData, size_t serialLength)
IPluginV2IOExt* DecodePluginCreator::deserializePlugin(const char* name, const void* serialData, size_t serialLength) TRT_NOEXCEPT
{
// This object will be deleted when the network is destroyed, which will
// call PReluPlugin::destroy()

57
retinaface/decode.h
View File

@ -4,6 +4,7 @@
#include <string>
#include <vector>
#include "NvInfer.h"
#include "macros.h"
namespace decodeplugin
{
@ -26,53 +27,53 @@ namespace nvinfer1
~DecodePlugin();
int getNbOutputs() const override
int getNbOutputs() const TRT_NOEXCEPT override
{
return 1;
}
Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) override;
Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) TRT_NOEXCEPT override;
int initialize() override;
int initialize() TRT_NOEXCEPT override;
virtual void terminate() override {};
virtual void terminate() TRT_NOEXCEPT override {};
virtual size_t getWorkspaceSize(int maxBatchSize) const override { return 0;}
virtual size_t getWorkspaceSize(int maxBatchSize) const TRT_NOEXCEPT override { return 0;}
virtual int enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream) override;
virtual int enqueue(int batchSize, const void*const * inputs, void*TRT_CONST_ENQUEUE* outputs, void* workspace, cudaStream_t stream) TRT_NOEXCEPT override;
virtual size_t getSerializationSize() const override;
virtual size_t getSerializationSize() const TRT_NOEXCEPT override;
virtual void serialize(void* buffer) const override;
virtual void serialize(void* buffer) const TRT_NOEXCEPT override;
bool supportsFormatCombination(int pos, const PluginTensorDesc* inOut, int nbInputs, int nbOutputs) const override {
bool supportsFormatCombination(int pos, const PluginTensorDesc* inOut, int nbInputs, int nbOutputs) const TRT_NOEXCEPT override {
return inOut[pos].format == TensorFormat::kLINEAR && inOut[pos].type == DataType::kFLOAT;
}
const char* getPluginType() const override;
const char* getPluginType() const TRT_NOEXCEPT override;
const char* getPluginVersion() const override;
const char* getPluginVersion() const TRT_NOEXCEPT override;
void destroy() override;
void destroy() TRT_NOEXCEPT override;
IPluginV2IOExt* clone() const override;
IPluginV2IOExt* clone() const TRT_NOEXCEPT override;
void setPluginNamespace(const char* pluginNamespace) override;
void setPluginNamespace(const char* pluginNamespace) TRT_NOEXCEPT override;
const char* getPluginNamespace() const override;
const char* getPluginNamespace() const TRT_NOEXCEPT override;
DataType getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const override;
DataType getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const TRT_NOEXCEPT override;
bool isOutputBroadcastAcrossBatch(int outputIndex, const bool* inputIsBroadcasted, int nbInputs) const override;
bool isOutputBroadcastAcrossBatch(int outputIndex, const bool* inputIsBroadcasted, int nbInputs) const TRT_NOEXCEPT override;
bool canBroadcastInputAcrossBatch(int inputIndex) const override;
bool canBroadcastInputAcrossBatch(int inputIndex) const TRT_NOEXCEPT override;
void attachToContext(
cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator) override;
cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator) TRT_NOEXCEPT override;
void configurePlugin(const PluginTensorDesc* in, int nbInput, const PluginTensorDesc* out, int nbOutput) override;
void configurePlugin(const PluginTensorDesc* in, int nbInput, const PluginTensorDesc* out, int nbOutput) TRT_NOEXCEPT override;
void detachFromContext() override;
void detachFromContext() TRT_NOEXCEPT override;
int input_size_;
private:
@ -88,22 +89,22 @@ namespace nvinfer1
~DecodePluginCreator() override = default;
const char* getPluginName() const override;
const char* getPluginName() const TRT_NOEXCEPT override;
const char* getPluginVersion() const override;
const char* getPluginVersion() const TRT_NOEXCEPT override;
const PluginFieldCollection* getFieldNames() override;
const PluginFieldCollection* getFieldNames() TRT_NOEXCEPT override;
IPluginV2IOExt* createPlugin(const char* name, const PluginFieldCollection* fc) override;
IPluginV2IOExt* createPlugin(const char* name, const PluginFieldCollection* fc) TRT_NOEXCEPT override;
IPluginV2IOExt* deserializePlugin(const char* name, const void* serialData, size_t serialLength) override;
IPluginV2IOExt* deserializePlugin(const char* name, const void* serialData, size_t serialLength) TRT_NOEXCEPT override;
void setPluginNamespace(const char* libNamespace) override
void setPluginNamespace(const char* libNamespace) TRT_NOEXCEPT override
{
mNamespace = libNamespace;
}
const char* getPluginNamespace() const override
const char* getPluginNamespace() const TRT_NOEXCEPT override
{
return mNamespace.c_str();
}

4
retinaface/logging.h
View File

@ -25,6 +25,8 @@
#include <ostream>
#include <sstream>
#include <string>
#include "macros.h"
using Severity = nvinfer1::ILogger::Severity;
@ -236,7 +238,7 @@ public:
//! Note samples should not be calling this function directly; it will eventually go away once we eliminate the
//! inheritance from nvinfer1::ILogger
//!
void log(Severity severity, const char* msg) override
void log(Severity severity, const char* msg) TRT_NOEXCEPT override
{
LogStreamConsumer(mReportableSeverity, severity) << "[TRT] " << std::string(msg) << std::endl;
}

12
retinaface/macros.h Normal file
View File

@ -0,0 +1,12 @@
#ifndef __MACROS_H
#define __MACROS_H
#if NV_TENSORRT_MAJOR >= 8
#define TRT_NOEXCEPT noexcept
#define TRT_CONST_ENQUEUE const
#else
#define TRT_NOEXCEPT
#define TRT_CONST_ENQUEUE
#endif
#endif // __MACROS_H