index 0aa90fd2af3c1b3afb0a9d787b882668bfd00009..c3140708d93f84bd42ee91f3ad5968ff4274fc5f 100644 (file)
enum PoolMethod {
MAX = 0;
AVE = 1;
+ STOCHASTIC = 2;
}
optional PoolMethod pool = 11 [default = MAX]; // The pooling method
optional float dropout_ratio = 12 [default = 0.5]; // dropout ratio
// The ratio that is multiplied on the global learning rate. If you want to set
// the learning ratio for one blob, you need to set it for all blobs.
repeated float blobs_lr = 51;
+ // The weight decay that is multiplied on the global weight decay.
+ repeated float weight_decay = 52;
}
message LayerConnection {
}
message SolverParameter {
- optional float base_lr = 1; // The base learning rate
+ optional string train_net = 1; // The proto file for the training net.
+ optional string test_net = 2; // The proto file for the testing net.
+ // The number of iterations for each testing phase.
+ optional int32 test_iter = 3 [ default = 0 ];
+ // The number of iterations between two testing phases.
+ optional int32 test_interval = 4 [ default = 0 ];
+ 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 = 2;
- optional int32 max_iter = 3; // the maximum number of iterations
- optional int32 snapshot = 4 [default = 0]; // The snapshot interval
- optional string lr_policy = 5; // The learning rate decay policy.
- optional float min_lr = 6 [default = 0]; // The mininum learning rate
- optional float max_lr = 7 [default = 1e10]; // The maximum learning rate
- optional float gamma = 8; // The parameter to compute the learning rate.
- optional float power = 9; // The parameter to compute the learning rate.
- optional float momentum = 10; // The momentum value.
- optional float weight_decay = 11; // The weight decay.
- optional float stepsize = 12; // the stepsize for learning rate policy "step"
-
- optional string snapshot_prefix = 13; // The prefix for the snapshot.
+ optional int32 display = 6;
+ optional int32 max_iter = 7; // the maximum number of iterations
+ optional string lr_policy = 8; // The learning rate decay policy.
+ 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 int32 stepsize = 13; // the stepsize for learning rate policy "step"
+ 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 = 14 [ default = false];
- // Adagrad solver parameters
- // For Adagrad, we will first run normal sgd using the sgd parameters above
- // for adagrad_skip iterations, and then kick in the adagrad algorithm, with
- // the learning rate being adagrad_gamma * adagrad_skip. Note that the adagrad
- // algorithm will NOT use the learning rate multiplier that is specified in
- // the layer parameter specifications, as it will adjust the learning rate
- // of individual parameters in a data-dependent way.
- // WORK IN PROGRESS: not actually implemented yet.
- optional float adagrad_gamma = 15; // adagrad learning rate multiplier
- optional float adagrad_skip = 16; // the steps to skip before adagrad kicks in
+ optional bool snapshot_diff = 16 [ default = false];
}
// A message that stores the solver snapshots