GstInference/Benchmarks: Difference between revisions
Line 503: | Line 503: | ||
'TinyYoloV3 \n Tensorflow', | 'TinyYoloV3 \n Tensorflow', | ||
'TinyYoloV3 \n Tensorflow-Lite'], | 'TinyYoloV3 \n Tensorflow-Lite'], | ||
['x86', | ['x86', 63.747, 22.781, 48.381, 14.164, 20.482, 12.164, 10.338, 10.164, 24.255, 12.164, 27.113, 10.164], | ||
['x86+GPU', | ['x86+GPU', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], | ||
['TX2', | ['TX2', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], | ||
['TX2-GPU', | ['TX2-GPU', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], | ||
['Coral', | ['Coral', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], | ||
['Coral+TPU', | ['Coral+TPU', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] | ||
]); | ]); | ||
var table_model_platform = google.visualization.arrayToDataTable([ | var table_model_platform = google.visualization.arrayToDataTable([ | ||
Line 524: | Line 524: | ||
'Tensorflow-Lite \n Coral', | 'Tensorflow-Lite \n Coral', | ||
'Tensorflow-Lite \n Coral+TPU'], | 'Tensorflow-Lite \n Coral+TPU'], | ||
['InceptionV1', | ['InceptionV1', 63.747, 0, 0, 0, 0, 0, 22.781, 0, 0, 0, 0, 0], | ||
['InceptionV2', | ['InceptionV2', 48.381, 0, 0, 0, 0, 0, 14.164, 0, 0, 0, 0, 0], | ||
['InceptionV3', | ['InceptionV3', 20.482, 0, 0, 0, 0, 0, 12.164, 0, 0, 0, 0, 0], | ||
['InceptionV4', | ['InceptionV4', 10.338, 0, 0, 0, 0, 0, 10.164, 0, 0, 0, 0, 0], | ||
['TinyYoloV2', | ['TinyYoloV2', 24.255, 0, 0, 0, 0, 0, 12.164, 0, 0, 0, 0, 0], | ||
['TinyYoloV3', | ['TinyYoloV3', 27.113, 0, 0, 0, 0, 0, 10.164, 0, 0, 0, 0, 0] | ||
]); | ]); | ||
var table_model_backend = google.visualization.arrayToDataTable([ | var table_model_backend = google.visualization.arrayToDataTable([ | ||
Line 545: | Line 545: | ||
'Tensorflow-Lite \n Coral', | 'Tensorflow-Lite \n Coral', | ||
'Tensorflow-Lite \n Coral+TPU'], | 'Tensorflow-Lite \n Coral+TPU'], | ||
['InceptionV1', | ['InceptionV1', 63.747, 0, 0, 0, 0, 0, 22.781, 0, 0, 0, 0, 0], | ||
['InceptionV2', | ['InceptionV2', 48.381, 0, 0, 0, 0, 0, 14.164, 0, 0, 0, 0, 0], | ||
['InceptionV3', | ['InceptionV3', 20.482, 0, 0, 0, 0, 0, 12.164, 0, 0, 0, 0, 0], | ||
['InceptionV4', | ['InceptionV4', 10.338, 0, 0, 0, 0, 0, 10.164, 0, 0, 0, 0, 0], | ||
['TinyYoloV2', | ['TinyYoloV2', 24.255, 0, 0, 0, 0, 0, 12.164, 0, 0, 0, 0, 0], | ||
['TinyYoloV3', | ['TinyYoloV3', 27.113, 0, 0, 0, 0, 0, 10.164, 0, 0, 0, 0, 0] | ||
]); | ]); | ||
Revision as of 16:43, 3 April 2020
Make sure you also check GstInference's companion project: R2Inference |
GstInference |
---|
Introduction |
Getting started |
Supported architectures |
InceptionV1 InceptionV3 YoloV2 AlexNet |
Supported backends |
Caffe |
Metadata and Signals |
Overlay Elements |
Utils Elements |
Legacy pipelines |
Example pipelines |
Example applications |
Benchmarks |
Model Zoo |
Project Status |
Contact Us |
|
GstInference Benchmarks
The following benchmarks were run with a source video (1920x1080@60). With the following base GStreamer pipeline, and environment variables:
$ VIDEO_FILE='video.mp4' $ MODEL_LOCATION='graph_inceptionv1_tensorflow.pb' $ INPUT_LAYER='input' $ OUTPUT_LAYER='InceptionV1/Logits/Predictions/Reshape_1'
The environment variables were changed accordingly with the used model (Inception V1,V2,V3 or V4)
GST_DEBUG=inception1:1 gst-launch-1.0 filesrc location=$VIDEO_FILE ! decodebin ! videoconvert ! videoscale ! queue ! net.sink_model inceptionv1 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER net.src_model ! perf ! fakesink -v
The Desktop PC had the following specifications:
- Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz
- 8 GB RAM
- Cedar [Radeon HD 5000/6000/7350/8350 Series]
- Linux 4.15.0-54-generic x86_64 (Ubuntu 16.04)
The Jetson Xavier power modes used were 2 and 6 (more information: Supported Modes and Power Efficiency)
- View current power mode:
$ sudo /usr/sbin/nvpmodel -q
- Change current power mode:
sudo /usr/sbin/nvpmodel -m x
Where x is the power mode ID (e.g. 0, 1, 2, 3, 4, 5, 6).
Summary
Desktop PC | CPU Library | |
---|---|---|
Model | Framerate | CPU Usage |
Inception V1 | 11.89 | 48 |
Inception V2 | 10.33 | 65 |
Inception V3 | 5.41 | 90 |
Inception V4 | 3.81 | 94 |
Jetson Xavier (15W) | CPU Library | GPU Library | ||
---|---|---|---|---|
Model | Framerate | CPU Usage | Framerate | CPU Usage |
Inception V1 | 8.24 | 86 | 52.3 | 43 |
Inception V2 | 6.58 | 88 | 39.6 | 42 |
Inception V3 | 2.54 | 92 | 17.8 | 25 |
Inception V4 | 1.22 | 94 | 9.4 | 20 |
Jetson Xavier (30W) | CPU Library | GPU Library | ||
---|---|---|---|---|
Model | Framerate | CPU Usage | Framerate | CPU Usage |
Inception V1 | 6.41 | 93 | 66.27 | 72 |
Inception V2 | 5.11 | 95 | 50.59 | 62 |
Inception V3 | 1.96 | 98 | 22.95 | 44 |
Inception V4 | 0.98 | 99 | 12.14 | 32 |
Framerate
CPU Usage
TensorFlow Lite Benchmarks
FPS measurement
CPU usage measurement
Test benchmark video
The following video was used to perform the benchmark tests.
To download the video press right click on the video and select 'Save video as' and save this in your computer.