1 parent
da91b33763
commit
de30d8523d
7 files changed
+13
No files matched your search
@@ -54,6 +54,7 @@ If not specified, throughput is used as the default. To set the hint explicitly,
|
||||
.. note::
|
||||
|
||||
It is up to the user to ensure the environment on which the benchmark is running is optimized for maximum performance. Otherwise, different results may occur when using the application in different environment settings (such as power optimization settings, processor overclocking, thermal throttling).
|
||||
Stating flags that take only single option like `-m` multiple times, for example `./benchmark_app -m model.xml -m model2.xml`, results in only the first value being used.
|
||||
|
||||
Latency
|
||||
--------------------
|
||||
|
||||
@@ -94,6 +94,8 @@ To run the sample, you need to specify a model and image:
|
||||
|
||||
- The sample accepts models in ONNX format (.onnx) that do not require preprocessing.
|
||||
|
||||
- Stating flags that take only single option like `-m` multiple times, for example `./classification_sample_async -m model.xml -m model2.xml`, results in only the first value being used.
|
||||
|
||||
Example
|
||||
+++++++
|
||||
|
||||
|
||||
@@ -185,6 +185,8 @@ Here, the floating point Kaldi-generated reference neural network scores (``dev9
|
||||
|
||||
- The sample supports input and output in numpy file format (.npz)
|
||||
|
||||
- Stating flags that take only single option like `-m` multiple times, for example `./speech_sample -m model.xml -m model2.xml`, results in only the first value being used.
|
||||
|
||||
Sample Output
|
||||
#############
|
||||
|
||||
|
||||
Reference in new issue
Block a user