电商网站开发框架女装标题优化关键词

安装

提前安装好 CUDA 和 CUDNN，登录 NVIDIA 官方网站下载和主机 CUDA 版本适配的 TensorRT 压缩包即可。

以 CUDA 版本是 10.2 为例，选择适配 CUDA 10.2 的 tar 包，然后执行类似如下的命令安装并测试：

#安装c++版本
cd /the/path/of/tensorrt/tar/gz/file 
tar -zxvf TensorRT-8.2.5.1.linux.x86_64-gnu.cuda-10.2.cudnn8.2.tar.gz 
export TENSORRT_DIR=$(pwd)/TensorRT-8.2.5.1 
export LD_LIBRARY_PATH=$TENSORRT_DIR/lib:$LD_LIBRARY_PATH #安装python版本
pip install TensorRT-8.2.5.1/python/tensorrt-8.2.5.1-cp37-none-linux_x86_64.whl 
python -c "import tensorrt;print(tensorrt.__version__)" #打印8.2.5.1，则说明安装成功

构建trt模型

手动搭建

使用python接口

import tensorrt as trt verbose = True 
IN_NAME = 'input' 
OUT_NAME = 'output' 
IN_H = 224 
IN_W = 224 
BATCH_SIZE = 1 EXPLICIT_BATCH = 1 << (int)( trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH) TRT_LOGGER = trt.Logger(trt.Logger.VERBOSE) if verbose else trt.Logger() 
with trt.Builder(TRT_LOGGER) as builder, builder.create_builder_config( 
) as config, builder.create_network(EXPLICIT_BATCH) as network: # define network input_tensor = network.add_input( name=IN_NAME, dtype=trt.float32, shape=(BATCH_SIZE, 3, IN_H, IN_W)) pool = network.add_pooling( input=input_tensor, type=trt.PoolingType.MAX, window_size=(2, 2)) pool.stride = (2, 2) pool.get_output(0).name = OUT_NAME network.mark_output(pool.get_output(0)) # serialize the model to engine file profile = builder.create_optimization_profile() profile.set_shape_input('input', *[[BATCH_SIZE, 3, IN_H, IN_W]]*3)  builder.max_batch_size = 1 config.max_workspace_size = 1 << 30 engine = builder.build_engine(network, config) with open('model_python_trt.engine', mode='wb') as f: f.write(bytearray(engine.serialize())) print("generating file done!")

使用c++接口

#include <fstream> 
#include <iostream> #include <NvInfer.h> 
#include <../samples/common/logger.h> using namespace nvinfer1; 
using namespace sample; const char* IN_NAME = "input"; 
const char* OUT_NAME = "output"; 
static const int IN_H = 224; 
static const int IN_W = 224; 
static const int BATCH_SIZE = 1; 
static const int EXPLICIT_BATCH = 1 << (int)(NetworkDefinitionCreationFlag::kEXPLICIT_BATCH); int main(int argc, char** argv) 
{ // Create builder Logger m_logger; IBuilder* builder = createInferBuilder(m_logger); IBuilderConfig* config = builder->createBuilderConfig(); // Create model to populate the network INetworkDefinition* network = builder->createNetworkV2(EXPLICIT_BATCH); ITensor* input_tensor = network->addInput(IN_NAME, DataType::kFLOAT, Dims4{ BATCH_SIZE, 3, IN_H, IN_W }); IPoolingLayer* pool = network->addPoolingNd(*input_tensor, PoolingType::kMAX, DimsHW{ 2, 2 }); pool->setStrideNd(DimsHW{ 2, 2 }); pool->getOutput(0)->setName(OUT_NAME); network->markOutput(*pool->getOutput(0)); // Build engine IOptimizationProfile* profile = builder->createOptimizationProfile(); profile->setDimensions(IN_NAME, OptProfileSelector::kMIN, Dims4(BATCH_SIZE, 3, IN_H, IN_W)); profile->setDimensions(IN_NAME, OptProfileSelector::kOPT, Dims4(BATCH_SIZE, 3, IN_H, IN_W)); profile->setDimensions(IN_NAME, OptProfileSelector::kMAX, Dims4(BATCH_SIZE, 3, IN_H, IN_W)); config->setMaxWorkspaceSize(1 << 20); ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config); // Serialize the model to engine file IHostMemory* modelStream{ nullptr }; assert(engine != nullptr); modelStream = engine->serialize(); std::ofstream p("model.engine", std::ios::binary); if (!p) { std::cerr << "could not open output file to save model" << std::endl; return -1; } p.write(reinterpret_cast<const char*>(modelStream->data()), modelStream->size()); std::cout << "generating file done!" << std::endl; // Release resources modelStream->destroy(); network->destroy(); engine->destroy(); builder->destroy(); config->destroy(); return 0; 
} 

onnx模型转换

trtexec

使用python接口

import torch 
import onnx 
import tensorrt as trt onnx_model = 'model.onnx' class NaiveModel(torch.nn.Module): def __init__(self): super().__init__() self.pool = torch.nn.MaxPool2d(2, 2) def forward(self, x): return self.pool(x) device = torch.device('cuda:0') # generate ONNX model 
torch.onnx.export(NaiveModel(), torch.randn(1, 3, 224, 224), onnx_model, input_names=['input'], output_names=['output'], opset_version=11) 
onnx_model = onnx.load(onnx_model) # create builder and network 
logger = trt.Logger(trt.Logger.ERROR) 
builder = trt.Builder(logger) 
EXPLICIT_BATCH = 1 << (int)( trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH) 
network = builder.create_network(EXPLICIT_BATCH) # parse onnx 
parser = trt.OnnxParser(network, logger) if not parser.parse(onnx_model.SerializeToString()): error_msgs = '' for error in range(parser.num_errors): error_msgs += f'{parser.get_error(error)}\n' raise RuntimeError(f'Failed to parse onnx, {error_msgs}') config = builder.create_builder_config() 
config.max_workspace_size = 1<<20 
profile = builder.create_optimization_profile() profile.set_shape('input', [1,3 ,224 ,224], [1,3,224, 224], [1,3 ,224 ,224]) 
config.add_optimization_profile(profile) 
# create engine 
with torch.cuda.device(device): engine = builder.build_engine(network, config) with open('model.engine', mode='wb') as f: f.write(bytearray(engine.serialize())) print("generating file done!") 

使用c++接口

#include <fstream> 
#include <iostream> #include <NvInfer.h> 
#include <NvOnnxParser.h> 
#include <../samples/common/logger.h> using namespace nvinfer1; 
using namespace nvonnxparser; 
using namespace sample; int main(int argc, char** argv) 
{ // Create builder Logger m_logger; IBuilder* builder = createInferBuilder(m_logger); const auto explicitBatch = 1U << static_cast<uint32_t>(NetworkDefinitionCreationFlag::kEXPLICIT_BATCH); IBuilderConfig* config = builder->createBuilderConfig(); // Create model to populate the network INetworkDefinition* network = builder->createNetworkV2(explicitBatch); // Parse ONNX file IParser* parser = nvonnxparser::createParser(*network, m_logger); bool parser_status = parser->parseFromFile("model.onnx", static_cast<int>(ILogger::Severity::kWARNING)); // Get the name of network input Dims dim = network->getInput(0)->getDimensions(); if (dim.d[0] == -1)  // -1 means it is a dynamic model { const char* name = network->getInput(0)->getName(); IOptimizationProfile* profile = builder->createOptimizationProfile(); profile->setDimensions(name, OptProfileSelector::kMIN, Dims4(1, dim.d[1], dim.d[2], dim.d[3])); profile->setDimensions(name, OptProfileSelector::kOPT, Dims4(1, dim.d[1], dim.d[2], dim.d[3])); profile->setDimensions(name, OptProfileSelector::kMAX, Dims4(1, dim.d[1], dim.d[2], dim.d[3])); config->addOptimizationProfile(profile); } // Build engine config->setMaxWorkspaceSize(1 << 20); ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config); // Serialize the model to engine file IHostMemory* modelStream{ nullptr }; assert(engine != nullptr); modelStream = engine->serialize(); std::ofstream p("model.engine", std::ios::binary); if (!p) { std::cerr << "could not open output file to save model" << std::endl; return -1; } p.write(reinterpret_cast<const char*>(modelStream->data()), modelStream->size()); std::cout << "generate file success!" << std::endl; // Release resources modelStream->destroy(); network->destroy(); engine->destroy(); builder->destroy(); config->destroy(); return 0; 
} 

模型推理

使用python接口

#输入一个 1x3x224x224 的张量，输出一个 1x3x112x112 的张量
from typing import Union, Optional, Sequence,Dict,Any import torch 
import tensorrt as trt class TRTWrapper(torch.nn.Module): def __init__(self,engine: Union[str, trt.ICudaEngine], output_names: Optional[Sequence[str]] = None) -> None: super().__init__() self.engine = engine if isinstance(self.engine, str): with trt.Logger() as logger, trt.Runtime(logger) as runtime: with open(self.engine, mode='rb') as f: engine_bytes = f.read() self.engine = runtime.deserialize_cuda_engine(engine_bytes) self.context = self.engine.create_execution_context() names = [_ for _ in self.engine] input_names = list(filter(self.engine.binding_is_input, names)) self._input_names = input_names self._output_names = output_names if self._output_names is None: output_names = list(set(names) - set(input_names)) self._output_names = output_names def forward(self, inputs: Dict[str, torch.Tensor]): assert self._input_names is not None assert self._output_names is not None bindings = [None] * (len(self._input_names) + len(self._output_names)) profile_id = 0 for input_name, input_tensor in inputs.items(): # check if input shape is valid profile = self.engine.get_profile_shape(profile_id, input_name) assert input_tensor.dim() == len( profile[0]), 'Input dim is different from engine profile.' for s_min, s_input, s_max in zip(profile[0], input_tensor.shape, profile[2]): assert s_min <= s_input <= s_max, \ 'Input shape should be between ' \ + f'{profile[0]} and {profile[2]}' \ + f' but get {tuple(input_tensor.shape)}.' idx = self.engine.get_binding_index(input_name) # All input tensors must be gpu variables assert 'cuda' in input_tensor.device.type input_tensor = input_tensor.contiguous() if input_tensor.dtype == torch.long: input_tensor = input_tensor.int() self.context.set_binding_shape(idx, tuple(input_tensor.shape)) bindings[idx] = input_tensor.contiguous().data_ptr() # create output tensors outputs = {} for output_name in self._output_names: idx = self.engine.get_binding_index(output_name) dtype = torch.float32 shape = tuple(self.context.get_binding_shape(idx)) device = torch.device('cuda') output = torch.empty(size=shape, dtype=dtype, device=device) outputs[output_name] = output bindings[idx] = output.data_ptr() self.context.execute_async_v2(bindings, torch.cuda.current_stream().cuda_stream) return outputs model = TRTWrapper('model.engine', ['output']) 
output = model(dict(input = torch.randn(1, 3, 224, 224).cuda())) 
print(output) 

c++接口

#include <fstream> 
#include <iostream> #include <NvInfer.h> 
#include <../samples/common/logger.h> #define CHECK(status) \ do\ {\ auto ret = (status);\ if (ret != 0)\ {\ std::cerr << "Cuda failure: " << ret << std::endl;\ abort();\ }\ } while (0) using namespace nvinfer1; 
using namespace sample; const char* IN_NAME = "input"; 
const char* OUT_NAME = "output"; 
static const int IN_H = 224; 
static const int IN_W = 224; 
static const int BATCH_SIZE = 1; 
static const int EXPLICIT_BATCH = 1 << (int)(NetworkDefinitionCreationFlag::kEXPLICIT_BATCH); void doInference(IExecutionContext& context, float* input, float* output, int batchSize) 
{ const ICudaEngine& engine = context.getEngine(); // Pointers to input and output device buffers to pass to engine. // Engine requires exactly IEngine::getNbBindings() number of buffers. assert(engine.getNbBindings() == 2); void* buffers[2]; // In order to bind the buffers, we need to know the names of the input and output tensors. // Note that indices are guaranteed to be less than IEngine::getNbBindings() const int inputIndex = engine.getBindingIndex(IN_NAME); const int outputIndex = engine.getBindingIndex(OUT_NAME); // Create GPU buffers on device CHECK(cudaMalloc(&buffers[inputIndex], batchSize * 3 * IN_H * IN_W * sizeof(float))); CHECK(cudaMalloc(&buffers[outputIndex], batchSize * 3 * IN_H * IN_W /4 * sizeof(float))); // Create stream cudaStream_t stream; CHECK(cudaStreamCreate(&stream)); // DMA input batch data to device, infer on the batch asynchronously, and DMA output back to host CHECK(cudaMemcpyAsync(buffers[inputIndex], input, batchSize * 3 * IN_H * IN_W * sizeof(float), cudaMemcpyHostToDevice, stream)); context.enqueue(batchSize, buffers, stream, nullptr); CHECK(cudaMemcpyAsync(output, buffers[outputIndex], batchSize * 3 * IN_H * IN_W / 4 * sizeof(float), cudaMemcpyDeviceToHost, stream)); cudaStreamSynchronize(stream); // Release stream and buffers cudaStreamDestroy(stream); CHECK(cudaFree(buffers[inputIndex])); CHECK(cudaFree(buffers[outputIndex])); 
} int main(int argc, char** argv) 
{ // create a model using the API directly and serialize it to a stream char *trtModelStream{ nullptr }; size_t size{ 0 }; std::ifstream file("model.engine", std::ios::binary); if (file.good()) { file.seekg(0, file.end); size = file.tellg(); file.seekg(0, file.beg); trtModelStream = new char[size]; assert(trtModelStream); file.read(trtModelStream, size); file.close(); } Logger m_logger; IRuntime* runtime = createInferRuntime(m_logger); assert(runtime != nullptr); ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size, nullptr); assert(engine != nullptr); IExecutionContext* context = engine->createExecutionContext(); assert(context != nullptr); // generate input data float data[BATCH_SIZE * 3 * IN_H * IN_W]; for (int i = 0; i < BATCH_SIZE * 3 * IN_H * IN_W; i++) data[i] = 1; // Run inference float prob[BATCH_SIZE * 3 * IN_H * IN_W /4]; doInference(*context, data, prob, BATCH_SIZE); // Destroy the engine context->destroy(); engine->destroy(); runtime->destroy(); return 0; 
}