class TrainSummary extends Summary
Train logger for tensorboard. Use optimize.setTrainSummary to enable train logger. Then the log will be saved to logDir/appName/train.
- Alphabetic
- By Inheritance
- TrainSummary
- Summary
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
TrainSummary(logDir: String, appName: String)
- logDir
log dir.
- appName
application Name.
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
addHistogram[T](tag: String, value: Tensor[T], step: Long)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): TrainSummary.this.type
Add a histogram summary.
Add a histogram summary.
- tag
tag name.
- value
a tensor.
- step
current step.
- returns
this
- Definition Classes
- Summary
-
def
addScalar(tag: String, value: Float, step: Long): TrainSummary.this.type
Add a scalar summary.
Add a scalar summary.
- tag
tag name.
- value
tag value.
- step
current step.
- returns
this
- Definition Classes
- Summary
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )
-
def
close(): Unit
Close this logger.
Close this logger.
- Definition Classes
- Summary
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
val
folder: String
- Attributes
- protected
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getSummaryTrigger(tag: String): Option[Trigger]
Get a trigger by tag name.
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
readScalar(tag: String): Array[(Long, Float, Double)]
Read scalar values to an array of triple by tag name.
Read scalar values to an array of triple by tag name. First element of the triple is step, second is value, third is wallClockTime.
- tag
tag name. Supported tag names is "LearningRate", "Loss", "Throughput"
- returns
an array of triple.
- Definition Classes
- TrainSummary → Summary
-
def
setSummaryTrigger(tag: String, trigger: Trigger): TrainSummary.this.type
Supported tag name are LearningRate, Loss, Throughput, Parameters.
Supported tag name are LearningRate, Loss, Throughput, Parameters. Parameters contains weight, bias, gradWeight, gradBias, and some running status(eg. runningMean and runningVar in BatchNormalization).
Notice: By default, we record LearningRate, Loss and Throughput each iteration, while recording parameters is disabled. The reason is getting parameters from workers is a heavy operation when the model is very big.
- tag
tag name
- trigger
trigger
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )
-
val
writer: FileWriter
- Attributes
- protected
- Definition Classes
- TrainSummary → Summary