Caffe实战（十五）：数据层及参数设置

layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "examples/cifar10/mean.binaryproto"
  }
  data_param {
    source: "examples/cifar10/cifar10_train_lmdb"
    batch_size: 100
    backend: LMDB
  }
}

transform_param {
    # 实际上就是1/255, 即将输入数据由0-255归一化到0-1之间
    scale: 0.00390625
    # randomly horizontally mirror the image
    # 1表示开启镜像，0表示关闭，也可用ture和false来表示
    mirror: 1
    # corp a ‘crop_size‘x ‘corp_size‘patch:
    # -at random during training
    # -from the center during testing
    # 剪裁一个 227*227的图块，在训练阶段随机剪裁，在测试阶段从中间裁剪
    crop_size: 227
    # substract mean value(RGB three channel) 用一个配置文件来进行均值操作
    mean_file: "examples/cifar10/mean.binaryproto"
    # mean_value: 104
    # mean_value: 117
    # mean_value: 123
  }

layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "examples/mnist/mnist_train_lmdb"
    batch_size: 64
    backend: LMDB
  }
}

template <typename Dtype>
DataLayer<Dtype>::DataLayer(const LayerParameter& param)
  : BasePrefetchingDataLayer<Dtype>(param),
    reader_(param) {
}

void DataReader::Body::InternalThreadEntry() {
  shared_ptr<db::DB>  db(db::GetDB(param_.data_param().backend()));
  db->Open(param_.data_param().source(), db::READ);
  shared_ptr<db::Cursor> cursor(db->NewCursor());
  vector<shared_ptr<QueuePair> > qps;
  try {
    int solver_count = param_.phase() == TRAIN ?  Caffe::solver_count() : 1;
    // To ensure deterministic runs, only start running once  all solvers
    // are ready. But solvers need to peek on one item  during initialization,
    // so read one item, then wait for the next solver.
    for (int i = 0; i < solver_count; ++i) {
      shared_ptr<QueuePair> qp(new_queue_pairs_.pop());
      read_one(cursor.get(), qp.get());
      qps.push_back(qp);
    }
    // Main loop
    while (!must_stop()) {
      for (int i = 0; i < solver_count; ++i) {
        read_one(cursor.get(), qps[i].get());
      }
      // Check no additional readers have been created. This  can happen if
      // more than one net is trained at a time per process,  whether single
      // or multi solver. It might also happen if two data  layers have same
      // name and same source.
      CHECK_EQ(new_queue_pairs_.size(), 0);
    }
  } catch (boost::thread_interrupted&) {
    // Interrupted exception is expected on shutdown
  }
}

layer {
  top: "data"
  top: "label"
  name: "memory_data"
  type: "MemoryData"
  memory_data_param{
    batch_size: 2
    height: 100
    width: 100
    channels: 1
  }
  transform_param {
    scale: 0.0078125
    mean_file: "mean.proto"
    mirror: false
  }
}

layer {
  name: "data"
  type: "HDF5Data"
  top: "data"
  top: "label"
  hdf5_data_param {
    source: "examples/hdf5_classification/data/train.txt"
    batch_size: 10
  }
}

layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  transform_param {
    mirror: false
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
  }
  image_data_param {
    source: "examples/_temp/file_list.txt"
    batch_size: 50
    new_height: 256
    new_width: 256
  }
}

/path/to/images/img3423.jpg 2
/path/to/images/img3424.jpg 13
/path/to/images/img3425.jpg 8
...

layer {
  name: "data"
  type: "WindowData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
  }
  window_data_param {
    source: "examples/finetune_pascal_detection/window_file_2007_trainval.txt"
    batch_size: 128
    fg_threshold: 0.5
    bg_threshold: 0.5
    fg_fraction: 0.25
    context_pad: 16
    crop_mode: "warp"
  }
}

1. # 0  
2. /home/xxx/0001.jpg  
3. 641  
4. 7  
5. 1 1.0 353 356 393 396  
6. 1 0.5 338 344 379 384  
7. 2 0.7 339 336 379 376  
8. 5 0 334 330 374 370  
9. 4 1.0 330 324 370 364  
10. 4 1.0 335 319 375 359  
11. 4 1.0 341 313 381 353  
12. # 1  
13. /home/xxx/0002.jpg  
14. 600  
15. 3  
16. 2 1.0 353 356 393 396  
17. 2 0.5 338 344 379 384  
18. 3 0.7 339 336 379 376  

layer {
    name:"data"    #设定当前layer名称为data
    type:"Input"   #设置当前layer类型为Input
    top:"data"     #设置当前layer输出blob名称为data
    #定义输入数据维度为 batchsize =1 channel=1 height=42 dim=42
    input_param {shape: {dim: 1 dim: 1 dim: 42 dim:42}}
}

layer {  
  name: "data"  
  type: "DummyData"  
  top: "data"  
  include {  
    phase: TRAIN  
  }  
  dummy_data_param {  
    data_filler {  
      type: "constant"  
      value: 0.01  
    }  
    shape {  
      dim: 32  
      dim: 3  
      dim: 227  
      dim: 227  
    }  
  }  
}  
layer {  
  name: "data"  
  type: "DummyData"  
  top: "label"  
  include {  
    phase: TRAIN  
  }  
  dummy_data_param {  
    data_filler {  
      type: "constant"  
    }  
    shape {  
      dim: 32  
    }  
  }  
}