Package org.tensorflow.framework
Interface BatchingOptionsOrBuilder
- All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder,com.google.protobuf.MessageOrBuilder
- All Known Implementing Classes:
BatchingOptions,BatchingOptions.Builder
public interface BatchingOptionsOrBuilder
extends com.google.protobuf.MessageOrBuilder
-
Method Summary
Modifier and TypeMethodDescriptionintgetAllowedBatchSizes(int index) Optional list of allowed batch sizes.intOptional list of allowed batch sizes.Optional list of allowed batch sizes.intMaximum number of microseconds to wait before outputting an incomplete batch.intThe maximum allowed batch size.intMaximum number of batches enqueued for processing before requests are failed fast.intNumber of scheduling threads for processing batches of work.Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder
isInitializedMethods inherited from interface com.google.protobuf.MessageOrBuilder
findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof
-
Method Details
-
getNumBatchThreads
int getNumBatchThreads()Number of scheduling threads for processing batches of work. Determines the number of batches processed in parallel. This should be roughly in line with the number of TPU cores available.
int32 num_batch_threads = 1;- Returns:
- The numBatchThreads.
-
getMaxBatchSize
int getMaxBatchSize()The maximum allowed batch size. Can be larger than allowed_batch_sizes to utilize large batch splitting.
int32 max_batch_size = 2;- Returns:
- The maxBatchSize.
-
getBatchTimeoutMicros
int getBatchTimeoutMicros()Maximum number of microseconds to wait before outputting an incomplete batch.
int32 batch_timeout_micros = 3;- Returns:
- The batchTimeoutMicros.
-
getAllowedBatchSizesList
Optional list of allowed batch sizes. If left empty, does nothing. Otherwise, supplies a list of batch sizes, causing the op to pad batches up to one of those sizes. The entries must increase monotonically, and the final entry must be equal or less than the max_batch_size.
repeated int32 allowed_batch_sizes = 4;- Returns:
- A list containing the allowedBatchSizes.
-
getAllowedBatchSizesCount
int getAllowedBatchSizesCount()Optional list of allowed batch sizes. If left empty, does nothing. Otherwise, supplies a list of batch sizes, causing the op to pad batches up to one of those sizes. The entries must increase monotonically, and the final entry must be equal or less than the max_batch_size.
repeated int32 allowed_batch_sizes = 4;- Returns:
- The count of allowedBatchSizes.
-
getAllowedBatchSizes
int getAllowedBatchSizes(int index) Optional list of allowed batch sizes. If left empty, does nothing. Otherwise, supplies a list of batch sizes, causing the op to pad batches up to one of those sizes. The entries must increase monotonically, and the final entry must be equal or less than the max_batch_size.
repeated int32 allowed_batch_sizes = 4;- Parameters:
index- The index of the element to return.- Returns:
- The allowedBatchSizes at the given index.
-
getMaxEnqueuedBatches
int getMaxEnqueuedBatches()Maximum number of batches enqueued for processing before requests are failed fast.
int32 max_enqueued_batches = 5;- Returns:
- The maxEnqueuedBatches.
-