- 1. Change history
- 2. Terms/Abbreviations
- 3. Reference materials
- 4. Expected use case
- 5. Functional overview/Algorithm
- 6. User interface specifications (Import AI model)
- 7. User interface specifications (Delete AI model)
- 8. User interface specifications (Import "PPL")
- 9. User interface specifications (Delete "PPL")
- 10. Target performances/Impact on performances
- 11. Assumption/Restriction
- 12. Remarks
- 13. Unconfirmed items
Date | What/Why |
---|---|
2023/01/30 |
Initial draft. |
2023/05/26 |
Fixed the notation of tool names and parentheses. |
Terms/Abbreviations | Meaning |
---|---|
"PPL" |
A module that processes the output of the AI model (Output Tensor) of edge AI devices |
SAS |
Shared Access Signatures |
-
Reference/Related documents
-
API Reference
-
"Console Access Library" Functional Specifications
-
-
Import AI models created in your environment into "Console for AITRIOS"
-
Import created "PPL" into "Console for AITRIOS"
-
Check the import status of the AI model or "PPL"
-
Convert an AI model imported into "Console for AITRIOS" into a format that can be deployed to edge AI devices
-
Check AI model conversion state
-
Delete an AI model or "PPL" that has been imported into "Console for AITRIOS"
-
Users can use "Console Access Library" in the SDK’s Dev Container (Local PC or Codespaces)
-
Users can do the following through the "Console Access Library":
-
Import AI models into "Console for AITRIOS"
-
Use AI models supported by "Console for AITRIOS". See here.
-
Must store AI models to Azure Blob Storage to import into "Console for AITRIOS"
-
-
Convert AI models imported into "Console for AITRIOS"
-
Import "PPL" into "Console for AITRIOS"
-
Import the following "PPL":
-
SDK supports ".wasm" (File not yet AOT compiled)
-
-
-
-
Extensions for "PPL" files that can be imported | SDK support |
---|---|
.wasm (File not yet AOT compiled) |
Yes |
.aot (AOT compiled file) |
No |
flowchart TD;
%% definition
classDef object fill:#FFE699, stroke:#FFD700
classDef external_service fill:#BFBFBF, stroke:#6b8e23, stroke-dasharray: 10 2
style legend fill:#FFFFFF,stroke:#000000
%% impl
subgraph legend["Legend"]
process(Processing/User behavior)
end
-
Flow
flowchart TD
%% definition
classDef object fill:#FFE699, stroke:#FFD700
start((Start))
id2(Run the notebook for system client authentication)
id3(Run the notebook to get AI model list)
id4(Create and edit the configuration file for running the notebook to import AI model)
id5(Run the notebook to import AI model)
finish(((Finish)))
%% impl
start --> id2
id2 --> id3
id3 --> id4
id4 --> id5
id5 --> finish
-
Flow details
-
Run the notebook for system client authentication
-
Run the notebook to get AI model list
-
Run the notebook to get a list of AI models that have been imported into "Console for AITRIOS", and get settings in the configuration file,
model_id
.-
Assume the following case
-
Upgrade an AI model that has already been imported into "Console for AITRIOS"
-
Check the AI model import status of "Console for AITRIOS"
-
Check the conversion status of the AI model in "Console for AITRIOS"
-
-
-
-
Create and edit the configuration file for running the notebook to import AI model
-
Create and edit the configuration file configuration.json to configure notebook runtime settings
-
-
Run the notebook to import AI model
-
Run the notebook with the following features:
-
Imports AI models into "Console for AITRIOS"
-
Checks the AI model import status of "Console for AITRIOS"
-
Converts an AI model imported into "Console for AITRIOS"
-
Checks AI model conversion state.
-
-
-
-
Flow
flowchart TD
%% definition
classDef object fill:#FFE699, stroke:#FFD700
start((Start))
id1(Run the notebook for system client authentication)
id2(Run the notebook to get AI model list)
id3(Create and edit the configuration file for running the notebook to delete AI model)
id4(Run the notebook to delete AI model)
finish(((Finish)))
%% impl
start --> id1
id1 --> id2
id2 --> id3
id3 --> id4
id4 --> finish
-
Flow details
-
Run the notebook for system client authentication
-
Run the notebook to get AI model list
-
Run the notebook to get a list of AI models that have already been imported into "Console for AITRIOS", and get settings in the configuration file,
model_id
.
-
-
Create and edit the configuration file for running the notebook to delete AI model
-
Create and edit the configuration file configuration.json to configure notebook runtime settings
-
-
Run the notebook to delete AI model
-
Run the notebook to delete the AI model from "Console for AITRIOS"
-
-
-
Flow
flowchart TD
%% definition
classDef object fill:#FFE699, stroke:#FFD700
start((Start))
id1(Prepare PPL to import)
id2(Run the notebook for system client authentication)
id3(Run the notebook to get PPL list)
id4(Create and edit the configuration file for running the notebook to import PPL)
id5(Run the notebook to import PPL)
finish(((Finish)))
%% impl
start --> id1
id1 --> id2
id2 --> id3
id3 --> id4
id4 --> id5
id5 --> finish
-
Flow details
-
Prepare "PPL" to import
-
Store the "PPL" to import into the SDK runtime environment
-
-
Run the notebook for system client authentication
-
Run the notebook to get "PPL" list
-
Run the notebook to get a list of "PPL" that have already been imported into "Console for AITRIOS", and get settings in the configuration file,
app_name
andversion_number
.-
Assume the following case
-
Check the "PPL" import status of "Console for AITRIOS"
-
-
-
-
Create and edit the configuration file for running the notebook to import "PPL"
-
Create and edit the configuration file configuration.json to configure notebook runtime settings
-
-
Run the notebook to import "PPL"
-
Run the notebook with the following features:
-
Encodes "PPL" in Base64 format
-
Imports "PPL" into "Console for AITRIOS"
-
Checks the "PPL" import status of "Console for AITRIOS"
-
-
-
-
Flow
flowchart TD
%% definition
classDef object fill:#FFE699, stroke:#FFD700
start((Start))
id1(Run the notebook for system client authentication)
id2(Run the notebook to get PPL list)
id3(Create and edit the configuration file for running the notebook to delete PPL)
id4(Run the notebook to delete PPL)
finish(((Finish)))
%% impl
start --> id1
id1 --> id2
id2 --> id3
id3 --> id4
id4 --> finish
-
Flow details
-
Run the notebook for system client authentication
-
Run the notebook to get "PPL" list
-
Run the notebook to get a list of "PPL" that have already been imported into "Console for AITRIOS", and get settings in the configuration file,
app_name
andversion_number
.
-
-
Create and edit the configuration file for running the notebook to delete "PPL"
-
Create and edit the configuration file configuration.json to configure notebook runtime settings
-
-
Run the notebook to delete "PPL"
-
Run the notebook to delete the "PPL" from "Console for AITRIOS"
-
-
%%{init:{'themeCSS':'text.actor {font-size:18px !important;} .messageText {font-size:18px !important;} .loopText {font-size:18px !important;} .noteText {font-size:18px !important;}'}}%%
sequenceDiagram
participant user as User
participant container as Dev Container
participant console as Console<br>for AITRIOS
user->>container: Run the notebook <br> for system client authentication
opt Run arbitrarily
user->>container: Run the notebook <br> to get AI model list
end
user->>container: Create and edit <br> the configuration file <br> for running the notebook <br> to import AI model
user->>container: Run the notebook <br> to import AI model <br> (Cell to import AI model)
container->>console: Run the API <br> to import AI model
console-->>container: Response
container-->>user: Results
user->>container: Run the notebook <br> to import AI model <br> (Cell to check <br> AI model import results)
container->>console: Run the API <br> to get AI model information
console-->>container: Response
container-->>user: Results
user->>container: Run the notebook <br> to import AI model <br> (Cell to convert AI model)
container->>+console: Run the API <br> to convert AI model
console-->>container: Response
container-->>user: Results
Note over container, console: AI model conversion <br> runs on Console for AITRIOS <br> and may wait tens of minutes <br> after response is returned
opt Run arbitrarily multiple times
user->>container: Run the notebook <br> to import AI model <br> (Cell to check <br> AI model conversion state)
container->>console: Run the API <br> to get the status <br> of AI model conversion
console-->>-container: Response
container-->>user: Results
end
%%{init:{'themeCSS':'text.actor {font-size:18px !important;} .messageText {font-size:18px !important;} .loopText {font-size:18px !important;} .noteText {font-size:18px !important;}'}}%%
sequenceDiagram
participant user as User
participant container as Dev Container
participant console as Console<br>for AITRIOS
user->>container: Run the notebook <br> for system client authentication
user->>container: Run the notebook <br> to get AI model list
user->>container: Create and edit <br> the configuration file <br> for running the notebook <br> to delete AI model
user->>container: Run the notebook <br> to delete AI model
container->>console: Run the API <br> to delete AI model
console-->>container: Response
container-->>user: Results
%%{init:{'themeCSS':'text.actor {font-size:18px !important;} .messageText {font-size:18px !important;} .loopText {font-size:18px !important;} .noteText {font-size:18px !important;}'}}%%
sequenceDiagram
participant user as User
participant container as Dev Container
participant console as Console<br>for AITRIOS
user->>container: Prepare PPL to import
user->>container: Run the notebook <br> for system client authentication
opt Run arbitrarily
user->>container: Run the notebook <br> to get PPL list
end user->>container: Create and edit <br> the configuration file <br> for running the notebook <br> to import PPL
user->>container: Run the notebook <br> to import PPL <br> (Cell to import PPL)
container->>container: Encode PPL in Base64 format
container->>console: Run the API <br> to import PPL
console-->>container: Response
container-->>user: Results
opt Run arbitrarily multiple times
user->>container: Run the notebook <br> to import PPL <br> (Cell to check <br> PPL import results)
container->>console: Run the API <br> to get PPL information
console-->>container: Response
container-->>user: Results
end
%%{init:{'themeCSS':'text.actor {font-size:18px !important;} .messageText {font-size:18px !important;} .loopText {font-size:18px !important;} .noteText {font-size:18px !important;}'}}%%
sequenceDiagram
participant user as User
participant container as Dev Container
participant console as Console<br>for AITRIOS
user->>container: Run the notebook <br> for system client authentication
user->>container: Run the notebook <br> to get PPL list
user->>container: Create and edit <br> the configuration file <br> for running the notebook <br> to delete PPL
user->>container: Run the notebook <br> to delete PPL
container->>console: Run the API <br> to delete PPL
console-->>container: Response
container-->>user: Results
-
You have registered as a user through "Portal for AITRIOS" and participated in the AITRIOS project
-
You have prepared an AI model
-
You have uploaded an AI model to Azure Blob Storage and gotten its SAS URI
-
Launch the SDK environment and preview the
README.md
in the top directory -
Jump to the
README.md
in thetutorials
directory from the hyperlink in the SDK environment top directory -
Jump to the
README.md
in the3_prepare_model
directory from the hyperlink in theREADME.md
in thetutorials
directory -
Jump to the
README.md
in thedevelop_on_sdk
directory from the hyperlink in theREADME.md
in the3_prepare_model
directory -
Jump to the
README.md
in the3_import_to_console
directory from the hyperlink in theREADME.md
in thedevelop_on_sdk
directory -
Jump to each feature from each file in the
3_import_to_console
directory
-
Jump to the
README.md
in theset_up_console_client
directory from the hyperlink in theREADME.md
in the3_import_to_console
directory -
Open the notebook for system client authentication, *.ipynb, in the
set_up_console_client
directory, and run the python scripts in it
-
Jump to the
README.md
in theget_model_list
directory from the hyperlink in theREADME.md
in the3_import_to_console
directory -
Open the notebook to get AI model list, *.ipynb, in the
get_model_list
directory, and run the python scripts in it
Note
|
All parameters are required, unless otherwise indicated. |
Note
|
The parameters passed to the "Console Access Library" API are as specified in the "Console Access Library" API. |
-
Create and edit the configuration file,
configuration.json
, in the execution directory.
Configuration | Meaning | Range | Remarks |
---|---|---|---|
|
ID of AI model to import |
String |
Don’t abbreviate
|
|
SAS URI for AI model to import |
SAS URI format |
Don’t abbreviate
|
|
Option to indicate converted |
true or false |
Optional
|
|
Vendor name |
String |
Optional
|
|
AI model and version description |
String |
Optional
|
|
Network type |
String |
Optional
|
|
Label name |
["label01","label02","label03"] |
Optional
|
-
Open the notebook,
import_to_console.ipynb
, in the3_import_to_console
directory, and run the python scripts in it-
The scripts do the following:
-
Checks that configuration.json exists in the
3_import_to_console
directory-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Checks the contents of configuration.json
-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Runs the API to import AI model
-
If the import is successful,
import_to_console.ipynb
displays a successful message
-
-
Runs the API to check AI model import results
-
If the AI model information is successfully gotten,
import_to_console.ipynb
displays a successful message and the gotten status
-
-
Runs the API to convert AI model
-
If the API execution is successful,
import_to_console.ipynb
displays a successful message -
It takes several tens of minutes to complete conversion of the AI model, so checks AI model conversion state
-
-
Runs the API to check AI model conversion state
-
If the conversion status of the AI model information is successfully gotten,
import_to_console.ipynb
displays a successful message and the gotten status
-
-
-
If an error occurs, the error description is displayed in the
import_to_console.ipynb
and running is interrupted.-
See "Cloud SDK Console Access Library (Python) Functional Specifications" for details on errors and response times
-
-
-
You have registered as a user through "Portal for AITRIOS" and participated in the AITRIOS project
-
You have imported AI model into "Console for AITRIOS"
-
Launch the SDK environment and preview the
README.md
in the top directory -
Jump to the
README.md
in thetutorials
directory from the hyperlink in the SDK environment top directory -
Jump to the
README.md
in the3_prepare_model
directory from the hyperlink in theREADME.md
in thetutorials
directory -
Jump to the
README.md
in thedevelop_on_sdk
directory from the hyperlink in theREADME.md
in the3_prepare_model
directory -
Jump to the
README.md
in thedelete_model_on_console
directory from the hyperlink in theREADME.md
in thedevelop_on_sdk
directory -
Jump to each feature from each file in the
delete_model_on_console
directory
-
Jump to the
README.md
in theset_up_console_client
directory from the hyperlink in theREADME.md
in thedelete_model_on_console
directory -
Open the notebook for system client authentication, *.ipynb, in the
set_up_console_client
directory, and run the python scripts in it
-
Jump to the
README.md
in theget_model_list
directory from the hyperlink in theREADME.md
in thedelete_model_on_console
directory -
Open the notebook to get AI model list, *.ipynb, in the
get_model_list
directory, and run the python scripts in it
Note
|
All parameters are required, unless otherwise indicated. |
Note
|
The parameters passed to the "Console Access Library" API are as specified in the "Console Access Library" API. |
-
Create and edit the configuration file,
configuration.json
, in the execution directory.
Configuration | Meaning | Range | Remarks |
---|---|---|---|
|
ID of AI model to delete |
String |
Don’t abbreviate
|
-
Open the notebook,
delete_model_on_console.ipynb
, in thedelete_model_on_console
directory, and run the python scripts in it-
The scripts do the following:
-
Checks that configuration.json exists in the
delete_model_on_console
directory-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Checks the contents of configuration.json
-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Runs the API to delete AI model
-
If the deletion is successful,
delete_model_on_console.ipynb
displays a successful message
-
-
-
If an error occurs, the error description is displayed in the
delete_model_on_console.ipynb
and running is interrupted.-
See "Cloud SDK Console Access Library (Python) Functional Specifications" for details on errors and response times
-
-
-
You have registered as a user through "Portal for AITRIOS" and participated in the AITRIOS project
-
You have prepared "PPL"
-
Launch the SDK environment and preview the
README.md
in the top directory -
Jump to the
README.md
in thetutorials
directory from the hyperlink in the SDK environment top directory -
Jump to the
4_prepare_application
directory from the hyperlink in theREADME.md
in thetutorials
directory -
Jump to the
README.md
in the2_import_to_console
directory from the hyperlink in theREADME.md
in the4_prepare_application
directory -
Jump to each feature from each file in the
2_import_to_console
directory
-
Jump to the
README.md
in theset_up_console_client
directory from the hyperlink in theREADME.md
in the2_import_to_console
directory -
Open the notebook for system client authentication, *.ipynb, in the
set_up_console_client
directory, and run the python scripts in it
-
Jump to the
README.md
in theget_application_list
directory from the hyperlink in theREADME.md
in the2_import_to_console
directory -
Open the notebook to get "PPL" list, *.ipynb, in the
get_application_list
directory, and run the python scripts in it
Note
|
All parameters are required, unless otherwise indicated. |
Note
|
Do not use symbolic links to files and directories. |
Note
|
The parameters passed to the "Console Access Library" API are as specified in the "Console Access Library" API. |
-
Create and edit the configuration file,
configuration.json
, in the execution directory.
Configuration | Meaning | Range | Remarks |
---|---|---|---|
|
"PPL" name |
String |
Don’t abbreviate
|
|
"PPL" version |
String |
Don’t abbreviate
|
|
"PPL" file path |
Absolute path or relative to the notebook (*.ipynb) |
Don’t abbreviate |
|
"PPL" description |
String |
Optional
|
-
Open the notebook,
import_to_console.ipynb
, in the2_import_to_console
directory, and run the python scripts in it-
The scripts do the following:
-
Checks that configuration.json exists in the
2_import_to_console
directory-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Checks the contents of configuration.json
-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Encodes "PPL" in Base64 format
-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Runs the API to import "PPL"
-
If the import is successful,
import_to_console.ipynb
displays a successful message
-
-
Runs the API to check "PPL" import results
-
If the "PPL" information is successfully gotten,
import_to_console.ipynb
displays a successful message and the gotten status
-
-
-
If an error occurs, the error description is displayed in the
import_to_console.ipynb
and running is interrupted.-
See "Cloud SDK Console Access Library (Python) Functional Specifications" for details on errors and response times
-
-
-
You have registered as a user through "Portal for AITRIOS" and participated in the AITRIOS project
-
You have imported "PPL" into "Console for AITRIOS"
-
Launch the SDK environment and preview the
README.md
in the top directory -
Jump to the
README.md
in thetutorials
directory from the hyperlink in the SDK environment top directory -
Jump to the
4_prepare_application
directory from the hyperlink in theREADME.md
in thetutorials
directory -
Jump to the
README.md
in thedelete_application_on_console
directory from the hyperlink in theREADME.md
in the4_prepare_application
directory -
Jump to each feature from each file in the
delete_application_on_console
directory
-
Jump to the
README.md
in theset_up_console_client
directory from the hyperlink in theREADME.md
in thedelete_application_on_console
directory -
Open the notebook for system client authentication, *.ipynb, in the
set_up_console_client
directory, and run the python scripts in it
-
Jump to the
README.md
in theget_application_list
directory from the hyperlink in theREADME.md
in thedelete_application_on_console
directory -
Open the notebook to get "PPL" list, *.ipynb, in the
get_application_list
directory, and run the python scripts in it
Note
|
All parameters are required, unless otherwise indicated. |
Note
|
The parameters passed to the "Console Access Library" API are as specified in the "Console Access Library" API. |
-
Create and edit the configuration file,
configuration.json
, in the execution directory.
Configuration | Meaning | Range | Remarks |
---|---|---|---|
|
"PPL" name |
String |
Don’t abbreviate
|
|
"PPL" version |
String |
Don’t abbreviate
|
-
Open the notebook,
delete_application_on_console.ipynb
, in thedelete_application_on_console
directory, and run the python scripts in it-
The scripts do the following:
-
Checks that configuration.json exists in the
delete_application_on_console
directory-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Checks the contents of configuration.json
-
If an error occurs, the error description is displayed and running is interrupted.
-
-
Runs the API to delete "PPL"
-
If the deletion is successful,
delete_application_on_console.ipynb
displays a successful message
-
-
-
If an error occurs, the error description is displayed in the
delete_application_on_console.ipynb
and running is interrupted.-
See "Cloud SDK Console Access Library (Python) Functional Specifications" for details on errors and response times
-
-
-
Usability
-
When the SDK environment is built, AI models and "PPL" can be imported into "Console for AITRIOS" without any additional installation steps
-
-
UI response time of 1.2 seconds or less
-
If processing takes more than 5 seconds, indicates that processing is in progress with successive updates
-
If you cancel and restart an encoding or import process, start each process from the beginning instead of resuming in the middle