Question

Caffe有两个数据类Datum类和Blob。

(1)Could somebody explain what is the difference and advantages upon each other?

我查询的原因是

我正在使用caffe库构建两个网络。一个网络将通过输入图像并提取特征。

然后第二个网络将该功能作为输入并向前进行检测。

令我困惑的是，我是否应该使用Blob格式的第一个网络或Datum来提取要素以输入到第二个网络中。因为caffe库中的feature_extraction示例将Blob数据更改为Datum以保存数据。请查看以下代码。

Datum datum;
  std::vector<int> image_indices(num_features, 0);
  for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index) {
    feature_extraction_net->Forward();
    for (int i = 0; i < num_features; ++i) {
      const boost::shared_ptr<Blob<Dtype> > feature_blob =
        feature_extraction_net->blob_by_name(blob_names[i]);
      int batch_size = feature_blob->num();
      int dim_features = feature_blob->count() / batch_size;
      const Dtype* feature_blob_data;
      for (int n = 0; n < batch_size; ++n) {
        datum.set_height(feature_blob->height());
        datum.set_width(feature_blob->width());
        datum.set_channels(feature_blob->channels());
        datum.clear_data();
        datum.clear_float_data();
        feature_blob_data = feature_blob->cpu_data() +
            feature_blob->offset(n);
        for (int d = 0; d < dim_features; ++d) {
          datum.add_float_data(feature_blob_data[d]);
        }
        string key_str = caffe::format_int(image_indices[i], 10);

        string out;
        CHECK(datum.SerializeToString(&out));
        txns.at(i)->Put(key_str, out);
        ++image_indices[i];
        if (image_indices[i] % 1000 == 0) {
          txns.at(i)->Commit();
          txns.at(i).reset(feature_dbs.at(i)->NewTransaction());
          LOG(ERROR)<< "Extracted features of " << image_indices[i] <<
              " query images for feature blob " << blob_names[i];
        }
      }  // for (int n = 0; n < batch_size; ++n)
    }  // for (int i = 0; i < num_features; ++i)
  }  // for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index)

在代码中，num_mini_batches为10，batch_size为50，dim_features为4096. dim_features清除输出，因此它是输出卷的深度。

(2)What do batch_size 50 and num_mini_batches 10 mean for? Why we need to run through 10 times to have fc7 features in the image?

有人可以解释我这两个问题吗？

caffe库

0 个答案: