experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #24335 from siju-samuel:patch-4

Browse Source 
PiperOrigin-RevId: 225830235
This commit is contained in:
TensorFlower Gardener 2018-12-17 08:33:07 -08:00
commit 9fd8253129
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
tensorflow/lite/java/ovic/README.md
View File

@ -137,7 +137,14 @@ If you are adding a detection model, simply modify `modelPath` and `testImagePat
* Adjust the benchmark parameters when needed: * Adjust the benchmark parameters when needed:
You can chnage the length of each experiment, and the processor affinity below. `BIG_CORE_MASK` is an integer whose binary encoding represents the set of used cores. This number is phone-specific. For example, Pixel 2 has 8 cores: the 4 little cores are represented by the 4 less significant bits, and the 4 big cores by the 4 more significant bits. Therefore a mask value of 16, or in binary `00010000`, represents using only the first big core. The mask 32, or in binary `00100000` uses the second big core and should deliver identical results as the mask 16 because the big cores are interchangeable. You can change the length of each experiment, and the processor affinity below.
`BIG_CORE_MASK` is an integer whose binary encoding represents the set of used
cores. This number is phone-specific. For example, Pixel 2 has 8 cores: the 4
little cores are represented by the 4 less significant bits, and the 4 big cores
by the 4 more significant bits. Therefore a mask value of 16, or in binary
`00010000`, represents using only the first big core. The mask 32, or in binary
`00100000` uses the second big core and should deliver identical results as the
mask 16 because the big cores are interchangeable.
``` ```
/** Wall time for each benchmarking experiment. */ /** Wall time for each benchmarking experiment. */