tensorflow_lite

321

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2106090-IB-TENSORFLO15
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
lite
June 09 2021
  29 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


tensorflow_liteOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-7700K @ 4.50GHz (4 Cores / 8 Threads)LENOVO 36C9 (O2YKT46A BIOS)Intel Xeon E3-1200 v6/7th + Z2704 x 8192 MB DDR4-2400MT/s Samsung M378A1K43CB2-CRC2048GB Western Digital PC SN720 SDAQNTX-2T00-1001MSI NVIDIA GeForce GTX 1060 6GBRealtek ALC1220Qualcomm Atheros Killer E2500 + Qualcomm Atheros QCA6174 802.11acUbuntu 20.045.8.0-55-generic (x86_64)GNOME Shell 3.36.7X Server 1.20.9NVIDIAGCC 9.3.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionTensorflow_lite BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xde - Thermald 1.9.1- itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable

tensorflow_litetensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2lite42222762035473180172909822965775616863OpenBenchmarking.org

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetlite90K180K270K360K450KSE +/- 5594.05, N = 3422227

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4lite1.3M2.6M3.9M5.2M6.5MSE +/- 8859.37, N = 36203547

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobilelite70K140K210K280K350KSE +/- 1406.30, N = 3318017

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Floatlite60K120K180K240K300KSE +/- 421.33, N = 3290982

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantlite60K120K180K240K300KSE +/- 1225.85, N = 3296577

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2lite1.2M2.4M3.6M4.8M6MSE +/- 3089.66, N = 35616863