BenchmarkResult
Stay organized with collections
Save and categorize content based on your preferences.
Data class that contains BenchmarkResult.
Inherited Method Summary
From class java.lang.Object
|
Object
|
clone()
|
| boolean |
|
| void |
finalize()
|
|
final Class<?>
|
getClass()
|
| int |
hashCode()
|
| final void |
notify()
|
| final void |
notifyAll()
|
|
String
|
toString()
|
| final void |
wait(long arg0, int arg1)
|
| final void |
wait(long arg0)
|
| final void |
wait()
|
Public Methods
public abstract boolean
hasPassedAccuracyCheck ()
Returns whether accuracy validation check has passed.
public abstract List<Long> inferenceTimeMicros ()
Returns inference time of each sample input, in microseconds.
public abstract List<Long> initializationTimeMicros ()
Returns initialization time of each sample input, in microseconds.
public abstract int maxMemoryKb ()
Returns max memory used of all sample inputs, in kilobytes.
Returns the list of accuracy metrics.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-10-31 UTC.
[null,null,["Last updated 2024-10-31 UTC."],[[["\u003cp\u003e\u003ccode\u003eBenchmarkResult\u003c/code\u003e is a data class storing performance and accuracy data from TFLite model benchmarking.\u003c/p\u003e\n"],["\u003cp\u003eIt includes metrics like inference time, initialization time, memory usage, and accuracy validation results.\u003c/p\u003e\n"],["\u003cp\u003eThe class provides access to model output and a list of accuracy metrics through its methods.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eBenchmarkResult\u003c/code\u003e contains two nested classes, \u003ccode\u003eBenchmarkMetric\u003c/code\u003e for accuracy and \u003ccode\u003eInferenceOutput\u003c/code\u003e for model output.\u003c/p\u003e\n"],["\u003cp\u003eDevelopers can use \u003ccode\u003eBenchmarkResult\u003c/code\u003e to evaluate the performance and accuracy of different TFLite model configurations.\u003c/p\u003e\n"]]],[],null,["# BenchmarkResult\n\npublic abstract class **BenchmarkResult** extends [Object](//developer.android.com/reference/java/lang/Object.html) \nData class that contains BenchmarkResult. \n\n### Nested Class Summary\n\n|-------|---|---|-----------------------------|\n| class | [BenchmarkResult.BenchmarkMetric](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.BenchmarkMetric) || Accuracy metrics. |\n| class | [BenchmarkResult.InferenceOutput](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.InferenceOutput) || Model output of one tensor. |\n\n### Public Method Summary\n\n|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[BenchmarkResult.InferenceOutput](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.InferenceOutput)\\\u003e | [actualOutput](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#actualOutput())() Returns model output of running with this config. |\n| abstract boolean | [hasPassedAccuracyCheck](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#hasPassedAccuracyCheck())() Returns whether accuracy validation check has passed. |\n| abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[Long](//developer.android.com/reference/java/lang/Long.html)\\\u003e | [inferenceTimeMicros](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#inferenceTimeMicros())() Returns inference time of each sample input, in microseconds. |\n| abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[Long](//developer.android.com/reference/java/lang/Long.html)\\\u003e | [initializationTimeMicros](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#initializationTimeMicros())() Returns initialization time of each sample input, in microseconds. |\n| abstract int | [maxMemoryKb](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#maxMemoryKb())() Returns max memory used of all sample inputs, in kilobytes. |\n| abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[BenchmarkResult.BenchmarkMetric](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.BenchmarkMetric)\\\u003e | [metrics](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult#metrics())() Returns the list of accuracy metrics. |\n\n### Inherited Method Summary\n\nFrom class java.lang.Object \n\n|----------------------------------------------------------------------------|--------------------------------------------------------------------------------|\n| [Object](//developer.android.com/reference/java/lang/Object.html) | clone() |\n| boolean | equals([Object](//developer.android.com/reference/java/lang/Object.html) arg0) |\n| void | finalize() |\n| final [Class](//developer.android.com/reference/java/lang/Class.html)\\\u003c?\\\u003e | getClass() |\n| int | hashCode() |\n| final void | notify() |\n| final void | notifyAll() |\n| [String](//developer.android.com/reference/java/lang/String.html) | toString() |\n| final void | wait(long arg0, int arg1) |\n| final void | wait(long arg0) |\n| final void | wait() |\n\nPublic Methods\n--------------\n\n#### public abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[BenchmarkResult.InferenceOutput](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.InferenceOutput)\\\u003e\n**actualOutput** ()\n\nReturns model output of running with this config. Each [BenchmarkResult.InferenceOutput](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.InferenceOutput) maps to one output tensor. \n\n#### public abstract boolean\n**hasPassedAccuracyCheck** ()\n\nReturns whether accuracy validation check has passed. \n\n#### public abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[Long](//developer.android.com/reference/java/lang/Long.html)\\\u003e **inferenceTimeMicros** ()\n\nReturns inference time of each sample input, in microseconds. \n\n#### public abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[Long](//developer.android.com/reference/java/lang/Long.html)\\\u003e **initializationTimeMicros** ()\n\nReturns initialization time of each sample input, in microseconds. \n\n#### public abstract int **maxMemoryKb** ()\n\nReturns max memory used of all sample inputs, in kilobytes. \n\n#### public abstract [List](//developer.android.com/reference/java/util/List.html)\\\u003c[BenchmarkResult.BenchmarkMetric](/android/reference/com/google/android/gms/tflite/acceleration/BenchmarkResult.BenchmarkMetric)\\\u003e\n**metrics** ()\n\nReturns the list of accuracy metrics."]]