SolverParameter

net: "models/individually/viper_trainval.prototxt"
test_iter: 7
test_interval: 50
test_initialization: true

display: 20 #每迭代20次显示一次训练结果
average_loss: 20
iter_size: 2

lr_policy: "stepdecr"
base_lr: 0.1
gamma: 0.04
stepsize: 100
max_iter: 2700
min_lr: 0.0005

momentum: 0.9
weight_decay: 0.0005

snapshot_prefix: "external/exp/snapshots/individually/viper"
solver_mode: GPU

下面详细解释各参数：

 message SolverParameter {
  //////////////////////////////////////////////////////////////////////////////
  // Specifying the train and test networks
  //
  // Exactly one train net must be specified using one of the following fields:
  //     train_net_param, train_net, net_param, net
  // One or more test nets may be specified using any of the following fields:
  //     test_net_param, test_net, net_param, net
  // If more than one test net field is specified (e.g., both net and
  // test_net are specified), they will be evaluated in the field order given
  // above: (1) test_net_param, (2) test_net, (3) net_param/net.
  // A test_iter must be specified for each test_net.
  // A test_level and/or a test_stage may also be specified for each test_net.
  //////////////////////////////////////////////////////////////////////////////

  // Proto filename for the train net, possibly combined with one or more
  // test nets.
  optional string net = 24;
  // Inline train net param, possibly combined with one or more test nets.
  optional NetParameter net_param = 25;

  optional string train_net = 1; // Proto filename for the train net.
  repeated string test_net = 2; // Proto filenames for the test nets.
  optional NetParameter train_net_param = 21; // Inline train net params.
  repeated NetParameter test_net_param = 22; // Inline test net params.

  // The states for the train/test nets. Must be unspecified or
  // specified once per net.
  //
  // By default, all states will have solver = true;
  // train_state will have phase = TRAIN,
  // and all test_state's will have phase = TEST.
  // Other defaults are set according to the NetState defaults.
  optional NetState train_state = 26;
  repeated NetState test_state = 27;

  // The number of iterations for each test net.
  repeated int32 test_iter = 3;

  // The number of iterations between two testing phases.
  optional int32 test_interval = 4 [default = 0];
  optional bool test_compute_loss = 19 [default = false];
  // If true, run an initial test pass before the first iteration,
  // ensuring memory availability and printing the starting value of the loss.
  optional bool test_initialization = 32 [default = true];
  optional float base_lr = 5; // The base learning rate
  // the number of iterations between displaying info. If display = 0, no info
  // will be displayed.
  optional int32 display = 6;
  // Display the loss averaged over the last average_loss iterations
  optional int32 average_loss = 33 [default = 1];
  optional int32 max_iter = 7; // the maximum number of iterations
  // accumulate gradients over `iter_size` x `batch_size` instances
  optional int32 iter_size = 36 [default = 1];

  // The learning rate decay policy. The currently implemented learning rate
  // policies are as follows:
  //    - fixed: always return base_lr.
  //    - step: return base_lr * gamma ^ (floor(iter / step))
  //    - exp: return base_lr * gamma ^ iter
  //    - inv: return base_lr * (1 + gamma * iter) ^ (- power)
  //    - multistep: similar to step but it allows non uniform steps defined by
  //      stepvalue
  //    - poly: the effective learning rate follows a polynomial decay, to be
  //      zero by the max_iter. return base_lr (1 - iter/max_iter) ^ (power)
  //    - sigmoid: the effective learning rate follows a sigmod decay
  //      return base_lr ( 1/(1 + exp(-gamma * (iter - stepsize))))
  //    - stepdecr: return base_lr * (1 - gamma * (floor(iter / step)))
  //    - smoothstep: return base_lr * gamma ^ (iter / step)
  //
  // where base_lr, max_iter, gamma, step, stepvalue and power are defined
  // in the solver parameter protocol buffer, and iter is the current iteration.
  optional string lr_policy = 8;
  optional float gamma = 9; // The parameter to compute the learning rate.
  optional float power = 10; // The parameter to compute the learning rate.
  optional float momentum = 11; // The momentum value.
  optional float weight_decay = 12; // The weight decay.
  optional float min_lr = 39; // The minimum learning rate.
  // regularization types supported: L1 and L2
  // controlled by weight_decay
  optional string regularization_type = 29 [default = "L2"];
  // the stepsize for learning rate policy "step"
  optional int32 stepsize = 13;
  // the stepsize for learning rate policy "multistep"
  repeated int32 stepvalue = 34;

  // Set clip_gradients to >= 0 to clip parameter gradients to that L2 norm,
  // whenever their actual L2 norm is larger.
  optional float clip_gradients = 35 [default = -1];

  optional int32 snapshot = 14 [default = 0]; // The snapshot interval
  optional string snapshot_prefix = 15; // The prefix for the snapshot.
  // whether to snapshot diff in the results or not. Snapshotting diff will help
  // debugging but the final protocol buffer size will be much larger.
  optional bool snapshot_diff = 16 [default = false];
  enum SnapshotFormat {
    HDF5 = 0;
    BINARYPROTO = 1;
  }
  optional SnapshotFormat snapshot_format = 37 [default = BINARYPROTO];
  // the mode solver will use: 0 for CPU and 1 for GPU. Use GPU in default.
  enum SolverMode {
    CPU = 0;
    GPU = 1;
  }
  optional SolverMode solver_mode = 17 [default = GPU];
  // the device_id will that be used in GPU mode. Use device_id = 0 in default.
  repeated int32 device_id = 18;
  // If non-negative, the seed with which the Solver will initialize the Caffe
  // random number generator -- useful for reproducible results. Otherwise,
  // (and by default) initialize using a seed derived from the system clock.
  optional int64 random_seed = 20 [default = -1];

  // Solver type
  enum SolverType {
    SGD = 0;
    NESTEROV = 1;
    ADAGRAD = 2;
    RMSPROP = 3;
    ADADELTA = 4;
  }
  optional SolverType solver_type = 30 [default = SGD];
  // numerical stability for AdaGrad
  optional float delta = 31 [default = 1e-8];

  // RMSProp decay value
  // MeanSquare(t) = rms_decay*MeanSquare(t-1) + (1-rms_decay)*SquareGradient(t)
  optional float rms_decay = 38;

  // If true, print information about the state of the net that may help with
  // debugging learning problems.
  optional bool debug_info = 23 [default = false];

  // If false, don't save a snapshot after training finishes.
  optional bool snapshot_after_train = 28 [default = true];
}

// A message that stores the solver snapshots
message SolverState {
  optional int32 iter = 1; // The current iteration
  optional string learned_net = 2; // The file that stores the learned net.
  repeated BlobProto history = 3; // The history for sgd solvers
  optional int32 current_step = 4 [default = 0]; // The current step for learning rate
}

enum Phase {
   TRAIN = 0;
   TEST = 1;
}

message NetState {
  optional Phase phase = 1 [default = TEST];
  optional int32 level = 2 [default = 0];
  repeated string stage = 3;
}