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

Update YOLOv3-tiny for TRT8 (#1064)

Browse Source 
* Update YOLOv3-tiny for TRT8
Changes from #967

* Also apply fixes to utils

* Remove redundant macro definition in logging.g
This commit is contained in:
Dominic D 2022-08-02 05:33:13 +00:00 committed by GitHub
parent 0f944b8975
commit 46dccf11ea
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 69 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
yolov3-tiny/logging.h
View File

@ -25,6 +25,7 @@
#include <ostream>
#include <sstream>
#include <string>
#include "macros.h"
using Severity = nvinfer1::ILogger::Severity;
@ -236,7 +237,7 @@ 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
yolov3-tiny/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

5
yolov3-tiny/utils.h
View File

@ -5,6 +5,7 @@
#include <vector>
#include <algorithm>
#include <cudnn.h>
#include "macros.h"
#ifndef CUDA_CHECK
@ -38,7 +39,7 @@ namespace Tn
typedef std::pair<std::string, float> Record;
std::vector<Record> mProfile;
virtual void reportLayerTime(const char* layerName, float ms)
virtual void reportLayerTime(const char* layerName, float ms) TRT_NOEXCEPT
{
auto record = std::find_if(mProfile.begin(), mProfile.end(), [&](const Record& r){ return r.first == layerName; });
if (record == mProfile.end())
@ -57,7 +58,7 @@ namespace Tn
Logger(Severity severity): reportableSeverity(severity) {}
void log(Severity severity, const char* msg) override
void log(Severity severity, const char* msg) TRT_NOEXCEPT override
{
// suppress messages with severity enum value greater than the reportable
if (severity > reportableSeverity) return;

44
yolov3-tiny/yololayer.cu
View File

@ -36,7 +36,7 @@ namespace nvinfer1
assert(d == a + length);
}
void YoloLayerPlugin::serialize(void* buffer) const
void YoloLayerPlugin::serialize(void* buffer) const TRT_NOEXCEPT
{
using namespace Tn;
char* d = static_cast<char*>(buffer), *a = d;
@ -50,17 +50,17 @@ namespace nvinfer1
assert(d == a + getSerializationSize());
}
size_t YoloLayerPlugin::getSerializationSize() const
size_t YoloLayerPlugin::getSerializationSize() const TRT_NOEXCEPT
{
return sizeof(mClassCount) + sizeof(mThreadCount) + sizeof(mKernelCount) + sizeof(Yolo::YoloKernel) * mYoloKernel.size();
}
int YoloLayerPlugin::initialize()
int YoloLayerPlugin::initialize() TRT_NOEXCEPT
{
return 0;
}
Dims YoloLayerPlugin::getOutputDimensions(int index, const Dims* inputs, int nbInputDims)
Dims YoloLayerPlugin::getOutputDimensions(int index, const Dims* inputs, int nbInputDims) TRT_NOEXCEPT
{
//output the result to channel
int totalsize = MAX_OUTPUT_BBOX_COUNT * sizeof(Detection) / sizeof(float);
@ -69,63 +69,63 @@ namespace nvinfer1
}
// Set plugin namespace
void YoloLayerPlugin::setPluginNamespace(const char* pluginNamespace)
void YoloLayerPlugin::setPluginNamespace(const char* pluginNamespace) TRT_NOEXCEPT
{
mPluginNamespace = pluginNamespace;
}
const char* YoloLayerPlugin::getPluginNamespace() const
const char* YoloLayerPlugin::getPluginNamespace() const TRT_NOEXCEPT
{
return mPluginNamespace;
}
// Return the DataType of the plugin output at the requested index
DataType YoloLayerPlugin::getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const
DataType YoloLayerPlugin::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 YoloLayerPlugin::isOutputBroadcastAcrossBatch(int outputIndex, const bool* inputIsBroadcasted, int nbInputs) const
bool YoloLayerPlugin::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 YoloLayerPlugin::canBroadcastInputAcrossBatch(int inputIndex) const
bool YoloLayerPlugin::canBroadcastInputAcrossBatch(int inputIndex) const TRT_NOEXCEPT
{
return false;
}
void YoloLayerPlugin::configurePlugin(const PluginTensorDesc* in, int nbInput, const PluginTensorDesc* out, int nbOutput)
void YoloLayerPlugin::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 YoloLayerPlugin::attachToContext(cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator)
void YoloLayerPlugin::attachToContext(cudnnContext* cudnnContext, cublasContext* cublasContext, IGpuAllocator* gpuAllocator) TRT_NOEXCEPT
{
}
// Detach the plugin object from its execution context.
void YoloLayerPlugin::detachFromContext() {}
void YoloLayerPlugin::detachFromContext() TRT_NOEXCEPT {}
const char* YoloLayerPlugin::getPluginType() const
const char* YoloLayerPlugin::getPluginType() const TRT_NOEXCEPT
{
return "YoloLayer_TRT";
}
const char* YoloLayerPlugin::getPluginVersion() const
const char* YoloLayerPlugin::getPluginVersion() const TRT_NOEXCEPT
{
return "1";
}
void YoloLayerPlugin::destroy()
void YoloLayerPlugin::destroy() TRT_NOEXCEPT
{
delete this;
}
// Clone the plugin
IPluginV2IOExt* YoloLayerPlugin::clone() const
IPluginV2IOExt* YoloLayerPlugin::clone() const TRT_NOEXCEPT
{
YoloLayerPlugin *p = new YoloLayerPlugin();
p->setPluginNamespace(mPluginNamespace);
@ -205,7 +205,7 @@ namespace nvinfer1
}
int YoloLayerPlugin::enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream)
int YoloLayerPlugin::enqueue(int batchSize, const void*const * inputs, void*TRT_CONST_ENQUEUE* outputs, void* workspace, cudaStream_t stream) TRT_NOEXCEPT
{
//assert(batchSize == 1);
//GPU
@ -226,29 +226,29 @@ namespace nvinfer1
mFC.fields = mPluginAttributes.data();
}
const char* YoloPluginCreator::getPluginName() const
const char* YoloPluginCreator::getPluginName() const TRT_NOEXCEPT
{
return "YoloLayer_TRT";
}
const char* YoloPluginCreator::getPluginVersion() const
const char* YoloPluginCreator::getPluginVersion() const TRT_NOEXCEPT
{
return "1";
}
const PluginFieldCollection* YoloPluginCreator::getFieldNames()
const PluginFieldCollection* YoloPluginCreator::getFieldNames() TRT_NOEXCEPT
{
return &mFC;
}
IPluginV2IOExt* YoloPluginCreator::createPlugin(const char* name, const PluginFieldCollection* fc)
IPluginV2IOExt* YoloPluginCreator::createPlugin(const char* name, const PluginFieldCollection* fc) TRT_NOEXCEPT
{
YoloLayerPlugin* obj = new YoloLayerPlugin();
obj->setPluginNamespace(mNamespace.c_str());
return obj;
}
IPluginV2IOExt* YoloPluginCreator::deserializePlugin(const char* name, const void* serialData, size_t serialLength)
IPluginV2IOExt* YoloPluginCreator::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 MishPlugin::destroy()

58
yolov3-tiny/yololayer.h
View File

@ -4,6 +4,8 @@
#include <vector>
#include <string>
#include "NvInfer.h"
#include "macros.h"
namespace Yolo
{
@ -53,53 +55,53 @@ namespace nvinfer1
~YoloLayerPlugin();
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;
private:
void forwardGpu(const float *const * inputs,float * output, cudaStream_t stream,int batchSize = 1);
@ -117,22 +119,22 @@ namespace nvinfer1
~YoloPluginCreator() 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();
}