caffe c++API特徵提取

作為caffe初學者，特徵提取python官方給的教程比較好用；但是關於c++API的使用，找了一些資料，說的並不是特徵完善；項目要求，得到ImageNet映像在CaffeNet網路結構中第fc7層的特徵。

環境：window7+caffe
語言：C++
目的：測試映像某層特徵，並以儲存
可以直接執行下面的命令，（注意官方給的案例是儲存為leveldb 格式，資料庫格式不夠直觀，解析也比較麻煩，直接儲存為文本形式多好呀~另外是7個參數哦，直接弄清楚對應的參數資訊）

extract_features.exe D:/caffe-windows/examples/_temp/caffe_reference_imagenet_model D:/caffe-windows/examples/_temp/imagenet_val.prototxt fc7 D:/caffe-windows/examples/_temp/features_fc7 10 leveldb GPU

然後通過解決方案中的extract_features工程源碼extract_features.cpp進行了改進,代碼更改地區塊如下

 ofstream *fout = new ofstream[num_features];  for (size_t i = 0; i < num_features; ++i) {    LOG(INFO)<< "Opening dataset " << dataset_names[i];    //boost::shared_ptr<db::DB> db(db::GetDB(db_type));  //  db->Open(dataset_names.at(i), db::NEW);   // feature_dbs.push_back(db);   // boost::shared_ptr<db::Transaction> txn(db->NewTransaction());    //txns.push_back(txn);    string feat_file_name = dataset_names.at(i);    feat_file_name = feat_file_name.append("/").append(blob_names[i]).append(".txt");    fout[i].open(feat_file_name);  }  LOG(ERROR)<< "Extacting Features";  //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]);        //blob是一個四維的資料：n*c*w*h,“fc7”層50*1*1*4960；“conv1”層50*96*55*55；       // “conv2”層50*256*27*27。      int batch_size = feature_blob->num();      //batch_size 就是blob中的n，表示feature-map的個數      LOG(ERROR) << "總的特徵塊數量:" << batch_size*num_mini_batches;//50*10      int dim_features = feature_blob->count() / batch_size;      LOG(ERROR) << "dim_features:" << dim_features;//4096      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]);//寫入到文字檔中，fc7總共有4096維        if (n == 0)        {            for (int d = 0; d < dim_features; ++d)                fout[i] << 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)      fout[i].close();    }  // for (int i = 0; i < num_features; ++i)  }  // for (int batch_index = 0; batch_index < num_mini_batches; ++batch_index)  // write the last batch // for (int i = 0; i < num_features; ++i) {   // if (image_indices[i] % 1000 != 0) {    //  txns.at(i)->Commit();   // }   // LOG(ERROR)<< "Extracted features of " << image_indices[i] <<        //" query images for feature blob " << blob_names[i];    //feature_dbs.at(i)->Close();  //}

代碼改寫後，得到的結果就是有文檔形式的特徵了，可以繼續接下來的專案工作了~~

fc7.txt儲存的就是4096維的float資料啦~
設定檔上傳出現問題，不能超過60M,暈~~