Tests
Suites
Latest Results
Search
Register
Login
Popular Tests
Timed Linux Kernel Compilation
SVT-AV1
7-Zip Compression
Stockfish
x265
FFmpeg
Newest Tests
LiteRT
WarpX
Epoch
Valkey
Whisperfile
XNNPACK
Recently Updated Tests
ASTC Encoder
SVT-AV1
Unvanquished
Primesieve
XNNPACK
oneDNN
New & Recently Updated Tests
Recently Updated Suites
Database Test Suite
Machine Learning
Steam
New & Recently Updated Suites
Component Benchmarks
CPUs / Processors
GPUs / Graphics
OpenGL
Disks / Storage
Motherboards
File-Systems
Operating Systems
OpenBenchmarking.org
Corporate / Organization Info
Bug Reports / Feature Requests
TensorFlow Lite 1.1.0
pts/tensorflow-lite-1.1.0
- 19 May 2022 -
Update against latest upstream nightly.
downloads.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.3--> <PhoronixTestSuite> <Downloads> <Package> <URL>http://www.phoronix-test-suite.com/benchmark-files/tf-lite-20220518.tar.xz</URL> <MD5>dd5f65466ca96c640370064cd61f6ff9</MD5> <SHA256>f7f8c0ee4fa5b78b0943b7d10f9141fbc714dc16a7cdca54b42ea81ec8b9d590</SHA256> <FileName>tf-lite-20220518.tar.xz</FileName> <FileSize>2437736</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224.tgz</URL> <MD5>bc1d3a910cc3f70d94e5d608fc5e9590</MD5> <SHA256>2fadeabb9968ec6833bee903900dda6e61b3947200535874ce2fe42a8493abc0</SHA256> <FileName>mobilenet_v1_1.0_224.tgz</FileName> <FileSize>94321559</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224_quant.tgz</URL> <MD5>36af340c00e60291931cb30ce32d4e86</MD5> <SHA256>d32432d28673a936b2d6281ab0600c71cf7226dfe4cdcef3012555f691744166</SHA256> <FileName>mobilenet_v1_1.0_224_quant.tgz</FileName> <FileSize>35069912</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/tflite/model_zoo/upload_20180427/nasnet_mobile_2018_04_27.tgz</URL> <MD5>398345d7af082c173d90989d44d856db</MD5> <SHA256>b3a3c5471f23f165e49fe0c2e56a3c503eeaa6f85d97f22369e3c36088e127c5</SHA256> <FileName>nasnet_mobile_2018_04_27.tgz</FileName> <FileSize>39558480</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/tflite/model_zoo/upload_20180427/squeezenet_2018_04_27.tgz</URL> <MD5>8effe92b879970cad0953868401cb2b2</MD5> <SHA256>75fc495b2792db6edccdc3a6f1bced19622b59dcc8835f386ab39f481ca1db9c</SHA256> <FileName>squeezenet_2018_04_27.tgz</FileName> <FileSize>9298056</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/tflite/model_zoo/upload_20180427/inception_resnet_v2_2018_04_27.tgz</URL> <MD5>59d4080bd81c1b675d2124672d8afe4c</MD5> <SHA256>fb16b93ff2b2bcda0da5cdfd25a8d5b8b74438943dae738db659bad0d3d48ff1</SHA256> <FileName>inception_resnet_v2_2018_04_27.tgz</FileName> <FileSize>225882079</FileSize> </Package> <Package> <URL>https://storage.googleapis.com/download.tensorflow.org/models/tflite/model_zoo/upload_20180427/inception_v4_2018_04_27.tgz</URL> <MD5>97da95494e4a4d755cf79d636c726bcb</MD5> <SHA256>305e45035c690f7a064b5babe27ea68a4e6da5819147c7c94319963c6f256467</SHA256> <FileName>inception_v4_2018_04_27.tgz</FileName> <FileSize>317324155</FileSize> </Package> </Downloads> </PhoronixTestSuite>
install.sh
#!/bin/sh tar -xf tf-lite-20220518.tar.xz tar -xf mobilenet_v1_1.0_224.tgz tar -xf mobilenet_v1_1.0_224_quant.tgz tar -xf nasnet_mobile_2018_04_27.tgz tar -xf squeezenet_2018_04_27.tgz tar -xf inception_resnet_v2_2018_04_27.tgz tar -xf inception_v4_2018_04_27.tgz echo "#!/bin/sh if [ \$OS_ARCH = \"aarch64\" ] then ./linux_aarch64_benchmark_model --num_threads=\$NUM_CPU_CORES \$@ > \$LOG_FILE 2>&1 else ./linux_x86-64_benchmark_model --num_threads=\$NUM_CPU_CORES \$@ > \$LOG_FILE 2>&1 fi echo \$? > ~/test-exit-status" > tensorflow-lite chmod +x tensorflow-lite
results-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.3--> <PhoronixTestSuite> <ResultsParser> <OutputTemplate>Inference timings in us: Init: 317, First inference: 269835, Warmup (avg): 241235, Inference (avg): #_RESULT_#</OutputTemplate> <LineHint>Inference timings in us</LineHint> </ResultsParser> </PhoronixTestSuite>
test-definition.xml
<?xml version="1.0"?> <!--Phoronix Test Suite v10.8.3--> <PhoronixTestSuite> <TestInformation> <Title>TensorFlow Lite</Title> <AppVersion>2022-05-18</AppVersion> <Description>This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time.</Description> <ResultScale>Microseconds</ResultScale> <Proportion>LIB</Proportion> <TimesToRun>3</TimesToRun> </TestInformation> <TestProfile> <Version>1.1.0</Version> <SupportedPlatforms>Linux</SupportedPlatforms> <SoftwareType>Benchmark</SoftwareType> <TestType>System</TestType> <License>Free</License> <Status>Verified</Status> <EnvironmentSize>1500</EnvironmentSize> <ProjectURL>https://www.tensorflow.org/lite/performance/measurement</ProjectURL> <RepositoryURL>https://github.com/tensorflow/tensorflow</RepositoryURL> <InternalTags>SMP</InternalTags> <Maintainer>Michael Larabel</Maintainer> </TestProfile> <TestSettings> <Default> <Arguments>--warmup_runs=5 --num_runs=50 --min_secs=60</Arguments> </Default> <Option> <DisplayName>Model</DisplayName> <Identifier>model</Identifier> <ArgumentPrefix>--graph=</ArgumentPrefix> <Menu> <Entry> <Name>Mobilenet Float</Name> <Value>mobilenet_v1_1.0_224.tflite</Value> </Entry> <Entry> <Name>Mobilenet Quant</Name> <Value>mobilenet_v1_1.0_224_quant.tflite</Value> </Entry> <Entry> <Name>NASNet Mobile</Name> <Value>nasnet_mobile.tflite</Value> </Entry> <Entry> <Name>SqueezeNet</Name> <Value>squeezenet.tflite</Value> </Entry> <Entry> <Name>Inception ResNet V2</Name> <Value>inception_resnet_v2.tflite</Value> </Entry> <Entry> <Name>Inception V4</Name> <Value>inception_v4.tflite</Value> </Entry> </Menu> </Option> </TestSettings> </PhoronixTestSuite>