-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
4b6b5c4
commit 89bd67e
Showing
2 changed files
with
1 addition
and
5 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -23,8 +23,6 @@ Unicorn is used for performing tasks such as performance optimization and perfor | |
|
||
Unicorn can be used for debugging and optimization for objectives such as latency (```inference_time```) and energy (```total_energy_consumption```) in both offline and online modes. Unicorn has been implemented on six software systems such as DEEPSTREAM (```Deepstream```), XCEPTION (```Image```), BERT (```NLP```), DEEPSPEECH (```Speech```), X264 (```x264```), and SQLITE (```sqlite```). | ||
|
||
__Note: In this artifact, we will be using offline mode. Contact [Md Shahriar Iqbal](mailto:[email protected]?subject=Testing%20UNICORN%20in%20online%20mode) for instructions if you are running UNICORN in online mode.__ | ||
|
||
## Setup | ||
|
||
To get started, you'll need to have `docker` and `docker-compose`. | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -9,8 +9,6 @@ Unicorn is used for performing tasks such as performance optimization and perfor | |
|
||
In both offline and online modes, Unicorn can be used for debugging and optimization for objectives such as latency (```inference_time```) and energy (```total_energy_consumption```). Unicorn has been implemented on six software systems such as DEEPSTREAM (```Deepstream```), XCEPTION (```Image```), BERT (```NLP```), DEEPSPEECH (```Speech```), X264 (```x264```), and SQLITE (```sqlite```). | ||
|
||
__Note: In this artifact, we will be using offline mode. Contact [Md Shahriar Iqbal](mailto:[email protected]?subject=Testing%20UNICORN%20in%20online%20mode) for instructions if you are running UNICORN in online mode.__ | ||
|
||
## Setup | ||
|
||
To get started, you'll need to have `docker` and `docker-compose`. | ||
|
@@ -133,7 +131,7 @@ password: nvidia | |
Once logged in into the device please use the following commands to run the experiments from one terminal: | ||
``` | ||
cd unicorn | ||
python3 ./services/run_services.py Image | ||
python3 ./services/run_service.py Image | ||
``` | ||
Please wait until the status shows the flask app is running on http://127.0.0.1/5000 | ||
|