如何在caffe中提取图层的blob信息？

Question

我在 C++.

中使用 caffe 进行机器学习

作为net_->Forward();通过网络后，我喜欢提取个别层的信息。

我做的是

          net_->Forward();

          //Extract layer information
          cout << "Num layers:" << "'" << net_->layer_names().size() << "'"<< endl;
          for (int layer_index = 0; layer_index < net_->layer_names().size(); ++layer_index) 
          {
                // get that layer blob and its dimension
                const boost::shared_ptr<Blob<float> > blob = net_->blob_by_name(net_->blob_names()[layer_index]);
                int batch_size = blob->num();                
                int dim_features = blob->count() / batch_size;
                std::cout << "Layer name:" << "'" << net_->layer_names()[layer_index] << "'" << " Blob name:" << "'" <<net_->blob_names()[layer_index] << "'" << " batch size " << "'" << batch_size << "'" << " dim_features:" << "'" << dim_features << "'" <<  std::endl;
          }

我可以看到所有图层名称和尺寸。

Layer name'image' Blob name'image' batch_size'1' dim_features'921600'
Layer name'conv1/7x7_s2' Blob name'conv1/7x7_s2' batch_size'1' dim_features'4915200'
Layer name'conv1/relu_7x7' Blob name'pool1/3x3_s2' batch_size'1' dim_features'1228800'
Layer name'pool1/3x3_s2' Blob name'pool1/norm1' batch_size'1' dim_features'1228800'
Layer name'pool1/norm1' Blob name'conv2/3x3_reduce' batch_size'1' dim_features'1228800'
Layer name'conv2/3x3_reduce' Blob name'conv2/3x3' batch_size'1' dim_features'3686400'
Layer name'conv2/relu_3x3_reduce' Blob name'conv2/norm2' batch_size'1' dim_features'3686400'

但在这里我还需要更深入的信息。

当前维度为 921600，即批大小 x 通道 x 高 x 宽 = 921600。

(1)所以我的第一个问题是如何拆分信息？

(2)假设我有这个信息 batch size x channels x height x width = 1 x 3 x 480 x 640。然后

如何提取像 1 x 1 x 480 x 640 这样的 blob 中的每一层，以便我可以打印或绘图。

我可以在 Python 中做的那种事情，比如

for layer_name, blob in net.blobs.iteritems():
        print layer_name + '\t' + str(blob.data.shape)
            mydata = net.blobs[layer_name].data[0,0,:,:]
            #cv2.imshow("mydata",mydata);
            #cv2.waitKey(1)
            layer_name = layer_name.replace('/', '_')
            np.savetxt("printdata/"+layer_name+".csv", mydata, delimiter=",")

但现在，我喜欢 C++.

Answer 1

对于问题 1：

如果您查看 blob.hpp 文件，它有几种获取 blob 尺寸的方法。您可以调用 shape() returns const vector<int>& 或已弃用的方法，例如 num()、channels()、height()、width() returnsint。所以对于你的情况应该是这样的：

int batch_size = blob->num();
int channels = blob->channels();
int height = blob->height();
int width = blob->width();
std::cout << "Layer name:" << "'" << net_->layer_names()[layer_index] << "'" << " Blob name:" << "'" <<net_->blob_names()[layer_index] << "'" << " batch size " << "'" << batch_size << "'" << " channels:" << "'" << channels << "'" << " height:" << "'" << height << "'" << " width:" << "'" << width << "'" <<  std::endl;

编辑：

对于问题2：如果图层有 3 个通道，那么您可以这样做以显示为图像：

// assign channels
std::vector<cv::Mat> ccs;
cv::Size ss(width, height);
float* data = blob->mutable_cpu_data();
for (int i = 0; i < channels; ++i) {
    cv::Mat channel(ss, CV_32FC1, data);
    ccs.push_back(channel);
    data += ss.area();
}
cv::Mat res,dst;
// merge them
cv::merge(ccs, res);
// optional add mean if needed
cv::normalize(res, dst, 0, 1, cv::NORM_MINMAX);
cv::namedWindow("Display window");
cv::imshow("Display window", dst);
cv::waitKey(0);

如何在caffe中提取图层的blob信息？

How to extract layers' blob information in caffe?

c++

python-2.7

deep-learning

caffe