Caffe源码解读（二）

                                                数据传入

一、data层

1、DataLayer类是最终的数据传输类，由于继承自BasePrefetchingDataLayer类，所以数据层运行时会调用LayerSetUp函数（DataLayer类内新定义的DataLayerSetUp函数主要用于转换数据transformed_data_、top[0]、top[1]的Reshape）。

2、LayerSetUp函数中调用了InternalThread类中的StartInternalThread()函数，该函数中的语句

  try {
    thread_.reset(new boost::thread(&InternalThread::entry, this, device, mode,
          rand_seed, solver_count, root_solver));
  } catch (std::exception& e) {
    LOG(FATAL) << "Thread exception: " << e.what();
  }

会通过thread类来创建一个线程并运行，该线程调用了entry函数

void InternalThread::entry(int device, Caffe::Brew mode, int rand_seed,
    int solver_count, bool root_solver) {
#ifndef CPU_ONLY
  CUDA_CHECK(cudaSetDevice(device));
#endif
  Caffe::set_mode(mode);
  Caffe::set_random_seed(rand_seed);
  Caffe::set_solver_count(solver_count);
  Caffe::set_root_solver(root_solver);

  InternalThreadEntry();
}

entry函数会继续调用InternalThreadEntry函数，该函数是InternalThread类中的一个虚函数，被BasePrefetchingDataLayer类继承后，在该类中进行了实例化。

template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::InternalThreadEntry() {
#ifndef CPU_ONLY
  cudaStream_t stream;
  if (Caffe::mode() == Caffe::GPU) {
    CUDA_CHECK(cudaStreamCreateWithFlags(&stream, cudaStreamNonBlocking));
  }
#endif

  try {
    while (!must_stop()) {
      Batch<Dtype>* batch = prefetch_free_.pop();
      load_batch(batch);
#ifndef CPU_ONLY
      if (Caffe::mode() == Caffe::GPU) {
        batch->data_.data().get()->async_gpu_push(stream);
        CUDA_CHECK(cudaStreamSynchronize(stream));
      }
#endif
      prefetch_full_.push(batch);
    }
  } catch (boost::thread_interrupted&) {
    // Interrupted exception is expected on shutdown
  }
#ifndef CPU_ONLY
  if (Caffe::mode() == Caffe::GPU) {
    CUDA_CHECK(cudaStreamDestroy(stream));
  }
#endif
}

在BasePrefetchingDataLayer类中定义了三个用于缓存数据的阻塞队列变量

  Batch<Dtype> prefetch_[PREFETCH_COUNT];
  BlockingQueue<Batch<Dtype>*> prefetch_free_;
  BlockingQueue<Batch<Dtype>*> prefetch_full_;

而在InternalThreadEntry函数中，判断prefetch_free_中是否还有空间，若有就会取出一个空间用于load_batch函数中数据的加载，并推入prefetch_full_中，若prefetch_free_中没有空闲位置，则会通知线程进入等待状态。must_stop()是当整个程序运行结束后会发送中断请求来中断该线程。

队列中的数据batch通过load_batch函数来加载

template<typename Dtype>
void DataLayer<Dtype>::load_batch(Batch<Dtype>* batch) {
  CPUTimer batch_timer;
  batch_timer.Start();
  double read_time = 0;
  double trans_time = 0;
  CPUTimer timer;
  CHECK(batch->data_.count());
  CHECK(this->transformed_data_.count());

  // Reshape according to the first datum of each batch
  // on single input batches allows for inputs of varying dimension.
  const int batch_size = this->layer_param_.data_param().batch_size();
  Datum& datum = *(reader_.full().peek());
  // Use data_transformer to infer the expected blob shape from datum.
  vector<int> top_shape = this->data_transformer_->InferBlobShape(datum);
  this->transformed_data_.Reshape(top_shape);
  // Reshape batch according to the batch_size.
  top_shape[0] = batch_size;
  batch->data_.Reshape(top_shape);

  Dtype* top_data = batch->data_.mutable_cpu_data();
  Dtype* top_label = NULL;  // suppress warnings about uninitialized variables

  if (this->output_labels_) {
    top_label = batch->label_.mutable_cpu_data();
  }
  for (int item_id = 0; item_id < batch_size; ++item_id) {
    timer.Start();
    // get a datum
    Datum& datum = *(reader_.full().pop("Waiting for data"));
    read_time += timer.MicroSeconds();
    timer.Start();
    // Apply data transformations (mirror, scale, crop...)
    int offset = batch->data_.offset(item_id);
    this->transformed_data_.set_cpu_data(top_data + offset);
    this->data_transformer_->Transform(datum, &(this->transformed_data_));
    // Copy label.
    if (this->output_labels_) {
      top_label[item_id] = datum.label();
    }
    trans_time += timer.MicroSeconds();

    reader_.free().push(const_cast<Datum*>(&datum));
  }
  timer.Stop();
  batch_timer.Stop();
  DLOG(INFO) << "Prefetch batch: " << batch_timer.MilliSeconds() << " ms.";
  DLOG(INFO) << "     Read time: " << read_time / 1000 << " ms.";
  DLOG(INFO) << "Transform time: " << trans_time / 1000 << " ms.";
}

3、 在BasePrefetchingDataLayer类中的Forward_cpu函数中，最终会将prefetch_full_队列中的batch（data和label）取出后送给data层的top（top[0]和top[1]）

template <typename Dtype>
void BasePrefetchingDataLayer<Dtype>::Forward_cpu(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  Batch<Dtype>* batch = prefetch_full_.pop("Data layer prefetch queue empty");
  // Reshape to loaded data.
  top[0]->ReshapeLike(batch->data_);
  // Copy the data
  caffe_copy(batch->data_.count(), batch->data_.cpu_data(),
             top[0]->mutable_cpu_data());
  DLOG(INFO) << "Prefetch copied";
  if (this->output_labels_) {
    // Reshape to loaded labels.
    top[1]->ReshapeLike(batch->label_);
    // Copy the labels.
    caffe_copy(batch->label_.count(), batch->label_.cpu_data(),
        top[1]->mutable_cpu_data());
  }

  prefetch_free_.push(batch);
}

总结： DataLayer在执行继承的LayerSetUp函数时，开辟多线程向prefetch_full_阻塞队列push数据，同时data层将该队列中的数据（data和label）取出后送到层的top。