后训练量化Post Training Quantization (PTQ)
量化过程仅仅通过离线推理一些sample数据对权重和激活值进行量化,无需要进行训练微调。
量化感知训练Quantization Aware Training (QAT)
在量化的过程中,对网络进行训练,从而让网络参数能更好地适应量化带来的信息损失。这种方式更加灵活,因此准确性普遍比后训练量化要高。缺点是操作起来不太方便。大多数情况下比训练后量化精度更高,部分场景不一定比部分/混合精度量化好很多。
(1)int8量化
trtexec --onnx=XX.onnx --saveEngine=model.plan --int8 --workspace=4096
如果使用int8量化;量化需要设置calib文件夹;
trtexec
--onnx=model.onnx
--minShapes=input:1x1x224x224
--optShapes=input:2x1x224x224
--maxShapes=input:10x1x224x224
--workspace=4096
--int8
--best
--calib=D:\images
--saveEngine=model.engine
--buildOnly
精度损失很大,不建议直接采用。
trtexec 有提供 --calib=接口进行校正,但需要对中间特征进行cache文件保存,比较麻烦,官方文档也是采用上述方式进行int8量化;与fp16的模型在测试集上测试指标,可以看到精度下降非常严重;
(2)int8 fp16混合量化
trtexec --onnx=XX.onnx --saveEngine=model.plan --int8 --fp16 --workspace=4096
测试集上统计指标:相比纯int8量化,效果要好,但是相比fp16,精度下降依然非常严重
engine序列化时执行
操作流程:
按照常规方案导出onnx,onnx序列化为tensorrt engine之前打开int8量化模式并采用校正数据集进行校正;
优点:
1.导出onnx之前的所有操作都为常规操作;2. 相比在pytorch中进行PTQ int8量化,所需显存小;
缺点:
1.量化过程为黑盒子,无法看到中间过程;
2.校正过程需在实际运行的tensorrt版本中进行并保存tensorrt engine;
3.量化过程中发现,即使模型为动态输入,校正数据集使用时也必须与推理时的输入shape[N, C, H, W]完全一致,否则,效果非常非常差,动态模型慎用。
操作示例参看onnx2trt_ptq.py
操作流程:
按照常规方案导出onnx,onnx序列化为tensorrt engine之前打开int8量化模式并采用校正数据集进行校正;
优点: 1. 相较于1.1,代码量更少,只需完成校正数据的处理代码;
缺点: 1. 同上所有; 2. 动态尺寸时,校正数据需与–trt-opt-shapes相同;3.内部默认最多校正20个epoch;
安装polygraphy
pip install colored polygraphy --extra-index-url https://pypi.ngc.nvidia.com
量化
polygraphy convert XX.onnx --int8 --data-loader-script loader_data.py --calibration-cache XX.cache -o XX.pl
注:在pytorch中执行导出的onnx将产生一个明确量化的模型,属于显式量化
操作流程:
安装pytorch_quantization库->加载训练数据->加载模型(在加载模型之前,启用quant_modules.initialize() 以保证原始模型层替换为量化层)->训练->导出onnx;
优点:
1.模型量化参数重新训练,训练较好时,精度下降较少; 2. 通过导出的onnx能够看到每层量化的过程;2. onnx导出为tensort engine时可以采用trtexec(注:命令行需加–int8,需要fp16和int8混合精度时,再添加–fp16),比较简单;3.训练过程可在任意设备中进行;
缺点:
1.导出onnx时,显存占用非常大;2.最终精度取决于训练好坏;3. QAT训练shape需与推理shape一致才能获得好的推理结果;4. 导出onnx时需采用真实的图片输入作为输入设置
操作示例参看yolov5_pytorch_qat.py感知训练,参看export_onnx_qat.py
该方式则是利用TensorRT的API将onnx转换engine文件的过程中进行量化,其中需要校准数据(准备一个存放几百张图像的文件夹即可)。为了读取校正图像,需要写一个Int8校正类,如下所示:
calibrator.h
#pragma once
#include
#include
#include
class Calibrator : public nvinfer1::IInt8EntropyCalibrator2 {
public:
Calibrator(int batchsize, int input_w, int input_h, std::string img_dir, const char* calib_table_name, bool read_cache = true);
virtual ~Calibrator();
int getBatchSize() const noexcept override;
bool getBatch(void* bindings[], const char* names[], int nbBindings) noexcept override;
const void* readCalibrationCache(size_t& length) noexcept override;
void writeCalibrationCache(const void* cache, size_t length) noexcept override;
private:
int BATCHSIZE;
int WIDTH;
int HEIGHT;
int INDEX;
std::string IMAGEDIR;
std::vector<std::string> IMAGEFILES;
size_t INPUTSIZE;
std::string CALIBRATORTABLE;
bool READCACHE;
void* DEVICEINPUT;
std::vector<char> CALIBRATORCACHE;
cv::Mat preprocess_img(cv::Mat& img, int input_w, int input_h);
void getFiles(std::string path, std::vector<std::string>& files);
};
calibrator.cpp
#include
#include
#include "calibrator.h"
cv::Mat Calibrator::preprocess_img(cv::Mat& img, int input_w, int input_h) {
int w, h, x, y;
float r_w = input_w / (img.cols * 1.0);
float r_h = input_h / (img.rows * 1.0);
if (r_h > r_w) {
w = input_w;
h = r_w * img.rows;
x = 0;
y = (input_h - h) / 2;
}
else {
w = r_h * img.cols;
h = input_h;
x = (input_w - w) / 2;
y = 0;
}
cv::Mat re(h, w, CV_8UC3);
cv::resize(img, re, re.size(), 0, 0, cv::INTER_LINEAR);
cv::Mat out(input_h, input_w, CV_8UC3, cv::Scalar(128, 128, 128));
re.copyTo(out(cv::Rect(x, y, re.cols, re.rows)));
return out;
}
void Calibrator::getFiles(std::string path, std::vector<std::string>& files){
intptr_t Handle;
struct _finddata_t FileInfo;
std::string p;
Handle = _findfirst(p.assign(path).append("\\*").c_str(), &FileInfo);
while (_findnext(Handle, &FileInfo) == 0) {
if (strcmp(FileInfo.name, ".") != 0 && strcmp(FileInfo.name, "..") != 0) {
files.push_back(FileInfo.name);
}
}
}
Calibrator::Calibrator(int batchsize, int input_w, int input_h, std::string img_dir, const char* calib_table_name, bool read_cache){
BATCHSIZE = batchsize;
WIDTH = input_w;
HEIGHT = input_h;
INDEX = 0;
IMAGEDIR = img_dir;
CALIBRATORTABLE = calib_table_name;
READCACHE = read_cache;
INPUTSIZE = BATCHSIZE * 3 * WIDTH * HEIGHT;
cudaMalloc(&DEVICEINPUT, INPUTSIZE * sizeof(float));
getFiles(IMAGEDIR, IMAGEFILES);
}
Calibrator::~Calibrator() {
cudaFree(DEVICEINPUT);
}
int Calibrator::getBatchSize() const noexcept {
return BATCHSIZE;
}
bool Calibrator::getBatch(void* bindings[], const char* names[], int nbBindings) noexcept {
if (INDEX + BATCHSIZE > (int)IMAGEFILES.size()) return false;
std::vector<cv::Mat> input_imgs;
for (int i = INDEX; i < INDEX + BATCHSIZE; i++) {
cv::Mat temp = cv::imread(IMAGEDIR + IMAGEFILES[i]);
if (temp.empty()) {
std::cerr << "Image cannot open!" << std::endl;
return false;
}
cv::Mat pr_img = preprocess_img(temp, WIDTH, HEIGHT);
input_imgs.push_back(pr_img);
}
INDEX += BATCHSIZE;
cv::Mat blob = cv::dnn::blobFromImages(input_imgs, 1.0 / 255.0, cv::Size(WIDTH, HEIGHT), cv::Scalar(0, 0, 0), true, false);
cudaMemcpy(DEVICEINPUT, blob.ptr<float>(0), INPUTSIZE * sizeof(float), cudaMemcpyHostToDevice);
bindings[0] = DEVICEINPUT;
return true;
}
const void* Calibrator::readCalibrationCache(size_t& length) noexcept {
std::cout << "reading calib cache: " << CALIBRATORTABLE << std::endl;
CALIBRATORCACHE.clear();
std::ifstream input(CALIBRATORTABLE, std::ios::binary);
input >> std::noskipws;
if (READCACHE && input.good()) {
std::copy(std::istream_iterator<char>(input), std::istream_iterator<char>(), std::back_inserter(CALIBRATORCACHE));
}
length = CALIBRATORCACHE.size();
return length ? CALIBRATORCACHE.data() : nullptr;
}
void Calibrator::writeCalibrationCache(const void* cache, size_t length) noexcept {
std::cout << "writing calib cache: " << CALIBRATORTABLE << std::endl;
std::ofstream output(CALIBRATORTABLE, std::ios::binary);
output.write(reinterpret_cast<const char*>(cache), length);
}
最后,通过以下代码将onnx量化转换为engine文件。
#include
#include
#include "calibrator.h"
#include "NvInfer.h"
#include "NvOnnxParser.h"
// 实例化记录器界面,捕获所有警告性信息,但忽略信息性消息
class Logger : public nvinfer1::ILogger {
void log(Severity severity, const char* msg) noexcept override {
if (severity <= Severity::kWARNING) {
std::cout << msg << std::endl;
}
}
}logger;
void ONNX2TensorRT(const char* ONNX_file, std::string& Engine_file, bool& FP16, bool& INT8, std::string& image_dir, const char*& calib_table) {
std::cout << "Load ONNX file form: " << ONNX_file << "\nStart export..." << std::endl;
// 1.创建构建器的实例
nvinfer1::IBuilder* builder = nvinfer1::createInferBuilder(logger);
// 2.创建网络定义
uint32_t flag = 1U << static_cast<uint32_t>(nvinfer1::NetworkDefinitionCreationFlag::kEXPLICIT_BATCH);
nvinfer1::INetworkDefinition* network = builder->createNetworkV2(flag);
// 3.创建一个 ONNX 解析器来填充网络
nvonnxparser::IParser* parser = nvonnxparser::createParser(*network, logger);
// 4.读取模型文件并处理任何错误
parser->parseFromFile(ONNX_file, static_cast<int32_t>(nvinfer1::ILogger::Severity::kWARNING));
for (int32_t i = 0; i < parser->getNbErrors(); ++i)
std::cout << parser->getError(i)->desc() << std::endl;
// 5.创建构建配置,指定TensorRT如何优化模型
nvinfer1::IBuilderConfig* config = builder->createBuilderConfig();
// 如果是动态模型,则需要设置大小
/*
auto profile = builder->createOptimizationProfile();
auto input_tensor = network->getInput(0);
auto input_dims = input_tensor->getDimensions();
// 配置最小允许batch
input_dims.d[0] = 1;
profile->setDimensions(input_tensor->getName(), nvinfer1::OptProfileSelector::kMIN, input_dims);
profile->setDimensions(input_tensor->getName(), nvinfer1::OptProfileSelector::kOPT, input_dims);
// 配置最大允许batch
// if networkDims.d[i] != -1, then minDims.d[i] == optDims.d[i] == maxDims.d[i] == networkDims.d[i]
input_dims.d[0] = maxBatchSize;
profile->setDimensions(input_tensor->getName(), nvinfer1::OptProfileSelector::kMAX, input_dims);
config->addOptimizationProfile(profile);
*/
// 6.设置属性来控制 TensorRT 如何优化网络
// 设置内存池的空间
config->setMemoryPoolLimit(nvinfer1::MemoryPoolType::kWORKSPACE, 16 * (1 << 20));
if (FP16) {
// 判断硬件是否支持FP16
if (!builder->platformHasFastFp16()) {
std::cout << "不支持FP16量化!" << std::endl;
system("pause");
return;
}
config->setFlag(nvinfer1::BuilderFlag::kFP16);
}
else if (INT8) {
if (!builder->platformHasFastInt8()) {
std::cout << "不支持INT8量化!" << std::endl;
system("pause");
return;
}
config->setFlag(nvinfer1::BuilderFlag::kINT8);
nvinfer1::IInt8EntropyCalibrator2* calibrator = new Calibrator(1, 640, 640, image_dir, calib_table);
config->setInt8Calibrator(calibrator);
}
// 7.指定配置后,构建引擎
nvinfer1::IHostMemory* serializeModel = builder->buildSerializedNetwork(*network, *config);
// 8.保存TensorRT模型
std::ofstream engine(Engine_file, std::ios::binary);
engine.write(reinterpret_cast<const char*>(serializeModel->data()), serializeModel->size());
// 9.序列化引擎包含权重的必要副本,因此不再需要解析器、网络定义、构建器配置和构建器,可以安全地删除
delete parser;
delete network;
delete config;
delete builder;
// 10.将引擎保存到磁盘后 ,并且可以删除它被序列化到的缓冲区
delete serializeModel;
std::cout << "Export success, Save as: " << Engine_file << std::endl;
}
int main(int argc, char** argv) {
// ONNX 文件路径
const char* ONNX_file = "../weights/yolov8s.onnx";
// ENGINE 文件保存路径
std::string Engine_file = "../weights/yolov8s.engine";
// 当量化为INT8时,图片路径
std::string image_dir = "../images/";
// 当量化为INT8时,校准表路径(存在读取,不存在创建)
const char* calib_table = "../weights/calibrator.table";
// 选择量化方式,若两个都为false,使用FP32生成 ENGINE文件
bool FP16 = false;
bool INT8 = true;
std::ifstream file(ONNX_file, std::ios::binary);
if (!file.good()) {
std::cout << "Load ONNX file failed!" << std::endl;
}
ONNX2TensorRT(ONNX_file, Engine_file, FP16, INT8, image_dir, calib_table);
return 0;
}
流程C++版本的一样,这个没进行测试,以下版本是别人量化yolov5的代码,感兴趣的朋友可以尝试一下。
import tensorrt as trt
import os
import numpy as np
import pycuda.driver as cuda
import pycuda.autoinit
import cv2
def get_crop_bbox(img, crop_size):
"""Randomly get a crop bounding box."""
margin_h = max(img.shape[0] - crop_size[0], 0)
margin_w = max(img.shape[1] - crop_size[1], 0)
offset_h = np.random.randint(0, margin_h + 1)
offset_w = np.random.randint(0, margin_w + 1)
crop_y1, crop_y2 = offset_h, offset_h + crop_size[0]
crop_x1, crop_x2 = offset_w, offset_w + crop_size[1]
return crop_x1, crop_y1, crop_x2, crop_y2
def crop(img, crop_bbox):
"""Crop from ``img``"""
crop_x1, crop_y1, crop_x2, crop_y2 = crop_bbox
img = img[crop_y1:crop_y2, crop_x1:crop_x2, ...]
return img
class yolov5EntropyCalibrator(trt.IInt8EntropyCalibrator2):
def __init__(self, imgpath, batch_size, channel, inputsize=[384, 1280]):
trt.IInt8EntropyCalibrator2.__init__(self)
self.cache_file = 'yolov5.cache'
self.batch_size = batch_size
self.Channel = channel
self.height = inputsize[0]
self.width = inputsize[1]
self.imgs = [os.path.join(imgpath, file) for file in os.listdir(imgpath) if file.endswith('jpg')]
np.random.shuffle(self.imgs)
self.imgs = self.imgs[:2000]
self.batch_idx = 0
self.max_batch_idx = len(self.imgs) // self.batch_size
self.calibration_data = np.zeros((self.batch_size, 3, self.height, self.width), dtype=np.float32)
# self.data_size = trt.volume([self.batch_size, self.Channel, self.height, self.width]) * trt.float32.itemsize
self.data_size = self.calibration_data.nbytes
self.device_input = cuda.mem_alloc(self.data_size)
# self.device_input = cuda.mem_alloc(self.calibration_data.nbytes)
def free(self):
self.device_input.free()
def get_batch_size(self):
return self.batch_size
def get_batch(self, names, p_str=None):
try:
batch_imgs = self.next_batch()
if batch_imgs.size == 0 or batch_imgs.size != self.batch_size * self.Channel * self.height * self.width:
return None
cuda.memcpy_htod(self.device_input, batch_imgs)
return [self.device_input]
except:
print('wrong')
return None
def next_batch(self):
if self.batch_idx < self.max_batch_idx:
batch_files = self.imgs[self.batch_idx * self.batch_size: \
(self.batch_idx + 1) * self.batch_size]
batch_imgs = np.zeros((self.batch_size, self.Channel, self.height, self.width),
dtype=np.float32)
for i, f in enumerate(batch_files):
img = cv2.imread(f) # BGR
crop_size = [self.height, self.width]
crop_bbox = get_crop_bbox(img, crop_size)
# crop the image
img = crop(img, crop_bbox)
img = img.transpose((2, 0, 1))[::-1, :, :] # BHWC to BCHW ,BGR to RGB
img = np.ascontiguousarray(img)
img = img.astype(np.float32) / 255.
assert (img.nbytes == self.data_size / self.batch_size), 'not valid img!' + f
batch_imgs[i] = img
self.batch_idx += 1
print("batch:[{}/{}]".format(self.batch_idx, self.max_batch_idx))
return np.ascontiguousarray(batch_imgs)
else:
return np.array([])
def read_calibration_cache(self):
# If there is a cache, use it instead of calibrating again. Otherwise, implicitly return None.
if os.path.exists(self.cache_file):
with open(self.cache_file, "rb") as f:
return f.read()
def write_calibration_cache(self, cache):
with open(self.cache_file, "wb") as f:
f.write(cache)
f.flush()
# os.fsync(f)
def get_engine(onnx_file_path, engine_file_path, cali_img, mode='FP32', workspace_size=4096):
"""Attempts to load a serialized engine if available, otherwise builds a new TensorRT engine and saves it."""
TRT_LOGGER = trt.Logger(trt.Logger.WARNING)
def build_engine():
assert mode.lower() in ['fp32', 'fp16', 'int8'], "mode should be in ['fp32', 'fp16', 'int8']"
explicit_batch_flag = 1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)
with trt.Builder(TRT_LOGGER) as builder, builder.create_network(
explicit_batch_flag
) as network, builder.create_builder_config() as config, trt.OnnxParser(
network, TRT_LOGGER
) as parser:
with open(onnx_file_path, "rb") as model:
print("Beginning ONNX file parsing")
if not parser.parse(model.read()):
print("ERROR: Failed to parse the ONNX file.")
for error in range(parser.num_errors):
print(parser.get_error(error))
return None
config.max_workspace_size = workspace_size * (1024 * 1024) # workspace_sizeMiB
# 构建精度
if mode.lower() == 'fp16':
config.flags |= 1 << int(trt.BuilderFlag.FP16)
if mode.lower() == 'int8':
print('trt.DataType.INT8')
config.flags |= 1 << int(trt.BuilderFlag.INT8)
config.flags |= 1 << int(trt.BuilderFlag.FP16)
calibrator = yolov5EntropyCalibrator(cali_img, 26, 3, [384, 1280])
# config.set_quantization_flag(trt.QuantizationFlag.CALIBRATE_BEFORE_FUSION)
config.int8_calibrator = calibrator
# if True:
# config.profiling_verbosity = trt.ProfilingVerbosity.DETAILED
profile = builder.create_optimization_profile()
profile.set_shape(network.get_input(0).name, min=(1, 3, 384, 1280), opt=(12, 3, 384, 1280), max=(26, 3, 384, 1280))
config.add_optimization_profile(profile)
# config.set_calibration_profile(profile)
print("Completed parsing of ONNX file")
print("Building an engine from file {}; this may take a while...".format(onnx_file_path))
# plan = builder.build_serialized_network(network, config)
# engine = runtime.deserialize_cuda_engine(plan)
engine = builder.build_engine(network,config)
print("Completed creating Engine")
with open(engine_file_path, "wb") as f:
# f.write(plan)
f.write(engine.serialize())
return engine
if os.path.exists(engine_file_path):
# If a serialized engine exists, use it instead of building an engine.
print("Reading engine from file {}".format(engine_file_path))
with open(engine_file_path, "rb") as f, trt.Runtime(TRT_LOGGER) as runtime:
return runtime.deserialize_cuda_engine(f.read())
else:
return build_engine()
def main(onnx_file_path, engine_file_path, cali_img_path, mode='FP32'):
"""Create a TensorRT engine for ONNX-based YOLOv3-608 and run inference."""
# Try to load a previously generated YOLOv3-608 network graph in ONNX format:
get_engine(onnx_file_path, engine_file_path, cali_img_path, mode)
if __name__ == "__main__":
onnx_file_path = '/home/models/boatdetect_yolov5/last_nms_dynamic.onnx'
engine_file_path = "/home/models/boatdetect_yolov5/last_nms_dynamic_onnx2trtptq.plan"
cali_img_path = '/home/data/frontview/test'
main(onnx_file_path, engine_file_path, cali_img_path, mode='int8')
tensorrt官方int8量化方法汇总
深度学习模型量化基础
模型量化5:onnx模型的静态量化和动态量化
有用的 模型量化!ONNX转TensorRT(FP32, FP16, INT8)
TensorRT-Int8量化详解
TensorRT中的INT 8 优化
TensorRT——INT8推理
TensorRT模型,INT8量化Python实践教程