神经网络的 Python 实时图像分类问题

Question

我正在尝试使用 caffe 和 python 进行实时图像分类。我在一个进程中使用 OpenCV 从我的网络摄像头流式传输，在一个单独的进程中，使用 caffe 对从网络摄像头拉取的帧执行图像分类。然后我将分类结果传回主线程，为网络摄像头流添加字幕。

问题是，即使我有一个 NVIDIA GPU 并且正在 GPU 上执行 caffe 预测，主线程也会变慢。通常不做任何预测，我的网络摄像头流以 30 fps 运行；但是，根据预测，我的网络摄像头流最多可以达到 15 fps。

我已验证 caffe 在执行预测时确实使用了 GPU，并且我的 GPU 或 GPU 内存没有达到最大值。我还验证了我的 CPU 内核在程序期间的任何时候都没有达到最大值。我想知道我是否做错了什么，或者是否没有办法让这两个过程真正分开。任何建议表示赞赏。这是我的引用代码

class Consumer(multiprocessing.Process):

    def __init__(self, task_queue, result_queue):
        multiprocessing.Process.__init__(self)
        self.task_queue = task_queue
        self.result_queue = result_queue
        #other initialization stuff

    def run(self):
        caffe.set_mode_gpu()
        caffe.set_device(0)
        #Load caffe net -- code omitted 
        while True:
            image = self.task_queue.get()
            #crop image -- code omitted
            text = net.predict(image)
            self.result_queue.put(text)

        return

import cv2
import caffe
import multiprocessing
import Queue 

tasks = multiprocessing.Queue()
results = multiprocessing.Queue()
consumer = Consumer(tasks,results)
consumer.start()

#Creating window and starting video capturer from camera
cv2.namedWindow("preview")
vc = cv2.VideoCapture(0)
#Try to get the first frame
if vc.isOpened():
    rval, frame = vc.read()
else:
    rval = False
frame_copy[:] = frame
task_empty = True
while rval:
    if task_empty:
       tasks.put(frame_copy)
       task_empty = False
    if not results.empty():
       text = results.get()
       #Add text to frame
       cv2.putText(frame,text)
       task_empty = True

    #Showing the frame with all the applied modifications
    cv2.imshow("preview", frame)

    #Getting next frame from camera
    rval, frame = vc.read()
    frame_copy[:] = frame
    #Getting keyboard input 
    key = cv2.waitKey(1)
    #exit on ESC
    if key == 27:
        break

我很确定是 caffe 预测减慢了一切，因为当我注释掉预测并在进程之间来回传递虚拟文本时，我再次获得 30 fps。

class Consumer(multiprocessing.Process):

    def __init__(self, task_queue, result_queue):
        multiprocessing.Process.__init__(self)
        self.task_queue = task_queue
        self.result_queue = result_queue
        #other initialization stuff

    def run(self):
        caffe.set_mode_gpu()
        caffe.set_device(0)
        #Load caffe net -- code omitted
        while True:
            image = self.task_queue.get()
            #crop image -- code omitted
            #text = net.predict(image)
            text = "dummy text"
            self.result_queue.put(text)

        return

import cv2
import caffe
import multiprocessing
import Queue 

tasks = multiprocessing.Queue()
results = multiprocessing.Queue()
consumer = Consumer(tasks,results)
consumer.start()

#Creating window and starting video capturer from camera
cv2.namedWindow("preview")
vc = cv2.VideoCapture(0)
#Try to get the first frame
if vc.isOpened():
    rval, frame = vc.read()
else:
    rval = False
frame_copy[:] = frame
task_empty = True
while rval:
    if task_empty:
       tasks.put(frame_copy)
       task_empty = False
    if not results.empty():
       text = results.get()
       #Add text to frame
       cv2.putText(frame,text)
       task_empty = True

    #Showing the frame with all the applied modifications
    cv2.imshow("preview", frame)

    #Getting next frame from camera
    rval, frame = vc.read()
    frame_copy[:] = frame
    #Getting keyboard input 
    key = cv2.waitKey(1)
    #exit on ESC
    if key == 27:
        break

Answer 1

一些解释和一些反射(reflection):

1. 我在具有 Intel Core i5-6300HQ @2.3GHz cpu、8 GB RAM 和 NVIDIA GeForce GTX 的笔记本电脑上运行了下面的代码960M gpu(2GB memory)，结果是:

   我是否在运行 caffe 的情况下运行代码(通过注释掉 net_output = this->net_->Forward(net_input) 以及 void Consumer::中的一些必要内容entry())，我总能在主线程中获得大约 30 fps。

   在具有 Intel Core i5-4440 cpu、8 GB RAM、NVIDIA GeForce GT 630 gpu 的 PC 上得到了类似的结果(1GB 内存)。

2. 我运行了@user3543300的代码在同一台笔记本电脑上的问题中，结果是:

   无论 caffe 是否在运行(在 gpu 上)，我也可以达到 30 fps 左右。

3. 根据@user3543300的反馈，使用上面提到的 2 个版本的代码，@user3543300 在运行 caffe 时只能获得大约 15 fps(在 Nvidia GeForce 940MX GPU 和 Intel® Core™ i7-6500U CPU @ 2.50GHz × 4笔记本电脑)。并且当 caffe 作为独立程序在 gpu 上运行时，网络摄像头的帧率也会有所下降。

所以我仍然认为问题很可能出在硬件 I/O 限制上，例如 DMA 带宽(这个关于 DMA 的帖子可能会暗示。)或 RAM 带宽。希望 @user3543300可以检查一下或者找出我没有意识到的真正问题。

如果问题确实是我上面的想法，那么一个明智的想法是减少 CNN 网络引入的内存 I/O 开销。事实上，为了解决硬件资源有限的嵌入式系统上的类似问题，已经有一些关于这个主题的研究，例如Qautization Structurally Sparse Deep Neural Networks , SqueezeNet , Deep-Compression .因此，希望通过应用这些技巧也有助于提高问题中网络摄像头的帧率。

---

原答案:

试试这个 c++ 解决方案。它为 I/O overhead 使用线程。在您的任务中，我使用 bvlc_alexnet.caffemodel 对其进行了测试, deploy.prototxt进行图像分类并且在 caffe 运行时(在 GPU 上)没有看到主线程(网络摄像头流)明显变慢:

#include <stdio.h>
#include <iostream>
#include <string>
#include <boost/thread.hpp>
#include <boost/shared_ptr.hpp>
#include "caffe/caffe.hpp"
#include "caffe/util/blocking_queue.hpp"
#include "caffe/data_transformer.hpp"
#include "opencv2/opencv.hpp"

using namespace cv;

//Queue pair for sharing image/results between webcam and caffe threads
template<typename T>
class QueuePair {
  public:
    explicit QueuePair(int size);
    ~QueuePair();

    caffe::BlockingQueue<T*> free_;
    caffe::BlockingQueue<T*> full_;

  DISABLE_COPY_AND_ASSIGN(QueuePair);
};
template<typename T>
QueuePair<T>::QueuePair(int size) {
  // Initialize the free queue
  for (int i = 0; i < size; ++i) {
    free_.push(new T);
  }
}
template<typename T>
QueuePair<T>::~QueuePair(){
  T *data;
  while (free_.try_pop(&data)){
    delete data;
  }
  while (full_.try_pop(&data)){
    delete data;
  }
}
template class QueuePair<Mat>;
template class QueuePair<std::string>;

//Do image classification(caffe predict) using a subthread
class Consumer{
  public:
    Consumer(boost::shared_ptr<QueuePair<Mat>> task
           , boost::shared_ptr<QueuePair<std::string>> result);
    ~Consumer();
    void Run();
    void Stop();
    void entry(boost::shared_ptr<QueuePair<Mat>> task
             , boost::shared_ptr<QueuePair<std::string>> result);

  private:
    bool must_stop();

    boost::shared_ptr<QueuePair<Mat> > task_q_;
    boost::shared_ptr<QueuePair<std::string> > result_q_;

    //caffe::Blob<float> *net_input_blob_;
    boost::shared_ptr<caffe::DataTransformer<float> > data_transformer_;
    boost::shared_ptr<caffe::Net<float> > net_;
    std::vector<std::string> synset_words_;
    boost::shared_ptr<boost::thread> thread_;
};
Consumer::Consumer(boost::shared_ptr<QueuePair<Mat>> task
                 , boost::shared_ptr<QueuePair<std::string>> result) :
 task_q_(task), result_q_(result), thread_(){

  //for data preprocess
  caffe::TransformationParameter trans_para;
  //set mean
  trans_para.set_mean_file("/path/to/imagenet_mean.binaryproto");
  //set crop size, here is cropping 227x227 from 256x256
  trans_para.set_crop_size(227);
  //instantiate a DataTransformer using trans_para for image preprocess
  data_transformer_.reset(new caffe::DataTransformer<float>(trans_para
                        , caffe::TEST));

  //initialize a caffe net
  net_.reset(new caffe::Net<float>(std::string("/path/to/deploy.prototxt")
           , caffe::TEST));
  //net parameter
  net_->CopyTrainedLayersFrom(std::string("/path/to/bvlc_alexnet.caffemodel"));

  std::fstream synset_word("path/to/caffe/data/ilsvrc12/synset_words.txt");
  std::string line;
  if (!synset_word.good()){
    std::cerr << "synset words open failed!" << std::endl;
  }
  while (std::getline(synset_word, line)){
    synset_words_.push_back(line.substr(line.find_first_of(' '), line.length()));
  }
  //a container for net input, holds data converted from cv::Mat
  //net_input_blob_ = new caffe::Blob<float>(1, 3, 227, 227);
}
Consumer::~Consumer(){
  Stop();
  //delete net_input_blob_;
}
void Consumer::entry(boost::shared_ptr<QueuePair<Mat>> task
    , boost::shared_ptr<QueuePair<std::string>> result){

  caffe::Caffe::set_mode(caffe::Caffe::GPU);
  caffe::Caffe::SetDevice(0);

  cv::Mat *frame;
  cv::Mat resized_image(256, 256, CV_8UC3);
  cv::Size re_size(resized_image.cols, resized_image.rows);

  //for caffe input and output
  const std::vector<caffe::Blob<float> *> net_input = this->net_->input_blobs();
  std::vector<caffe::Blob<float> *> net_output;

  //net_input.push_back(net_input_blob_);
  std::string *res;

  int pre_num = 1;
  while (!must_stop()){
    std::stringstream result_strm;
    frame = task->full_.pop();
    cv::resize(*frame, resized_image, re_size, 0, 0, CV_INTER_LINEAR);
    this->data_transformer_->Transform(resized_image, *net_input[0]);
    net_output = this->net_->Forward();
    task->free_.push(frame);

    res = result->free_.pop();
    //Process results here
    for (int i = 0; i < pre_num; ++i){
      result_strm << synset_words_[net_output[0]->cpu_data()[i]] << " " 
                  << net_output[0]->cpu_data()[i + pre_num] << "\n";
    }
    *res = result_strm.str();
    result->full_.push(res);
  }
}

void Consumer::Run(){
  if (!thread_){
    try{
      thread_.reset(new boost::thread(&Consumer::entry, this, task_q_, result_q_));
    }
    catch (std::exception& e) {
      std::cerr << "Thread exception: " << e.what() << std::endl;
    }
  }
  else
    std::cout << "Consumer thread may have been running!" << std::endl;
};
void Consumer::Stop(){
  if (thread_ && thread_->joinable()){
    thread_->interrupt();
    try {
      thread_->join();
    }
    catch (boost::thread_interrupted&) {
    }
    catch (std::exception& e) {
      std::cerr << "Thread exception: " << e.what() << std::endl;
    }
  }
}
bool Consumer::must_stop(){
  return thread_ && thread_->interruption_requested();
}


int main(void)
{
  int max_queue_size = 1000;
  boost::shared_ptr<QueuePair<Mat>> tasks(new QueuePair<Mat>(max_queue_size));
  boost::shared_ptr<QueuePair<std::string>> results(new QueuePair<std::string>(max_queue_size));

  char str[100], info_str[100] = " results: ";
  VideoCapture vc(0);
  if (!vc.isOpened())
    return -1;

  Consumer consumer(tasks, results);
  consumer.Run();

  Mat frame, *frame_copy;
  namedWindow("preview");
  double t, fps;

  while (true){
    t = (double)getTickCount();
    vc.read(frame);

    if (waitKey(1) >= 0){
      consuer.Stop();
      break;
    }

    if (tasks->free_.try_peek(&frame_copy)){
      frame_copy = tasks->free_.pop();
      *frame_copy = frame.clone();
      tasks->full_.push(frame_copy);
    }
    std::string *res;
    std::string frame_info("");
    if (results->full_.try_peek(&res)){
      res = results->full_.pop();
      frame_info = frame_info + info_str;
      frame_info = frame_info + *res;
      results->free_.push(res);
    }    

    t = ((double)getTickCount() - t) / getTickFrequency();
    fps = 1.0 / t;

    sprintf(str, " fps: %.2f", fps);
    frame_info = frame_info + str;

    putText(frame, frame_info, Point(5, 20)
         , FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
    imshow("preview", frame);
  }
}

在 src/caffe/util/blocking_queue.cpp ，在下面稍作改动并重建 caffe:

...//Other stuff
template class BlockingQueue<Batch<float>*>;
template class BlockingQueue<Batch<double>*>;
template class BlockingQueue<Datum*>;
template class BlockingQueue<shared_ptr<DataReader::QueuePair> >;
template class BlockingQueue<P2PSync<float>*>;
template class BlockingQueue<P2PSync<double>*>;
//add these 2 lines below
template class BlockingQueue<cv::Mat*>;
template class BlockingQueue<std::string*>;