AISVision AI Software Toolkit User Manual v1.1 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . About this manual ............................................................................... 5 Chapter 1: Getting to know AISVision .................................................. 8 1.1 Introduction .................................................................................................... 8 1.1.1 Features: ...................................................................................................... 8 1.1.2 Trainer ......................................................
ASUS, Inc . 2.2.2.1.6 Select image(s) using the keyboard ........................................................20 2.2.2.1.7 Label assistant - Auto labeling ................................................................21 2.2.2.1.8 Edit category .........................................................................................22 2.2.2.1.9 Edit image list ........................................................................................22 2.2.2.1.10 Others ...................................
ASUS, Inc . 2.2.4.3 Adjust overall threshold ...........................................................................34 2.2.4.4 Apply default threshold value ...................................................................35 2.2.4.5 How to view report...................................................................................35 2.2.4.6 Detail report (1) - (segmentation/Object detection) ..................................36 2.2.4.7 Detail report (2) - (Classification and Anomaly detection).....
ASUS, Inc . Safety Information ...............................................................................................51 Regulatory notice.................................................................................................51 Contacting ASUS ..................................................................................................51 Error Messages ....................................................................................................52 4 © 2021 ASUS, Inc.
ASUS, Inc . About this manual This manual provides an overview of the features of this AI software toolkit and gives step-by-step instructions for making full use of them. Release notes Version Description Modify by Date 1.0 1.First released version 2.Set 2.2.1 to 2.3.4 as help content 3.Set 1.1 and 1.1.1 as about Eric 2021/08/18 1.1 1. Modified pictures Xu 2021/12/22 2. Modified Training schedule 3. Add export report 5 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . How this manual is organized Chapter 1 Chapter 4 Getting to know AISVision This chapter details the key features and functions of this AI toolkit. Using AISVision This chapter provides information on how to use this AI toolkit. Upgrading AISVision This chapter provides information on how to upgrade the toolkit version, pre-trained models, and other necessary functions. Support for AISVision Appendix This chapter provides information for troubleshooting and contacting ASUS for support.
ASUS, Inc . Conventions used in this manual Throughout this manual, blocks of text as shown below are used to emphasize important information in this manual. IMPORTANT! This message contains vital information that must be followed to complete a task. NOTE: This message contains additional information and tips that can help to complete a task.
ASUS, Inc . Chapter 1: Getting to know AISVision 1.1 Introduction AISVision is an advanced AI training tool with a unique and intuitive user interface that allows you to quickly train and easily deploy AI models in the field. With four (4) vision AI functions (Abnormal detection, Fast object detection, Fast classification, and Fast anomaly detection), this all-in-one tool can quickly and efficiently detect and recognize objects, defects, and other characteristics in the field. 1.1.
ASUS, Inc . 1.2 About the AISVision Support API AISVision now supports C++/C/C# and python for extended development. For a developer guide, contact ASUS through the email provided in Contacting ASUS. 1.3 System Requirements Your computer must meet the minimum system requirements below to run the artificial intelligence model training and inference functions in this software toolkit.
ASUS, Inc . Chapter 2: Using AISVision 2.1 Download the toolkit Go to the ASUS IoT website and find the AISVision product download page 2.1.2 Install the toolkit Run installation.exe once the image file is downloaded. 2.1.3 Activate the toolkit When prompted for the activation key, plug the ASUS IoT USB dongle into the computer that you have installed AISVision and can use it to perform the product quality inspection or object recognition. 2.
ASUS, Inc . 2.2.1 Project In this section, you can set up a project to define and keep information, including desired features and functions, for use in subsequent steps. Create a new project Import project(s) Open a project Add/modify description Description in project detail box 2.2.1.1 Create a new project This is to name a specific action for keeping track of the activities.
ASUS, Inc . 2.2.1.2 Import project(s) - Open existing projects Click the Project to load the specific project, or double click on a project under Project List to load the project. 12 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.1.3 Open a project - Open/load project from a project list Load a project through the steps below: Click Project to load a project. Double click on a project under Project List to load the project. Other: When the project is successfully loaded, the Modify and Delete icons are available in the top right corner of that project info pane, and a vertical blue bar is visible on the left edge of that pane. Additional information is then displayed at the bottom of the screen.
ASUS, Inc . 2.2.1.4 Add/modify description A description helps you to describe the specific action to keep important information for the project or action. Click in the Description box to add/modify the project description. Once finished, click Save. Double-check if the change is reflected in the additional information box at the bottom of the screen. 14 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.1.5 Project details - Description in project detail box For each project under the Project List pane, you can find the project name in the first row, followed by the project type, task count, number of images, and description underneath the project name in the second row. For the location of the project, as well as the timestamp of when the project was created and when it was last modified, see the third row. 15 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.2 Labeller This function allows you to load and label images for the next steps to complete this AI function and has four (4) categories: segmentation, object detection, classification, and anomaly detection as shown below. 16 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.2.1 Labeller - Segmentation This allows you to label images for segmentation. Segmentation can add a pixel-level label for high-quality inspections. Add category Add image(s) Labeling Modify lable Label assistant (auto labling) Edit category Edit image list others Remove lable Select image by keyboard 2.2.2.1.1 Add category Click Add Category to add a category for the project. Make sure you select the correct project type.
ASUS, Inc . 2.2.2.1.2 Add image(s) This is to add images to a category. Click an image category from the Category List pane, click Add Images or Add Folders to import images. Only images for the selected category are shown in the Image List pane. 2.2.2.1.3 Labeling Click on the target object and select a category. Select one of the labeling methods - brush, polygon, oval, and rectangular. When using polygon for labeling, click along the object’s edge and double-click to finish the selection.
ASUS, Inc . 2.2.2.1.4 Modify label - Modify polygon, ellipse, rectangle, or lines for labeling When labeling using polygon, ellipse, rectangle, or line, you will see a dashed border around the labeled area. Continue to fine-tune and modify the labeling until you have the desired area selected. To confirm the selection, click and cursor outside of the labeled area. 2.2.2.1.5 Remove label This is to remove any unnecessary labels.
ASUS, Inc . 2.2.2.1.6 Select image(s) using the keyboard Press the Up (or Left) arrow to go to the previous image and the Down (or Right) arrow to go to the next image. Press Ctrl + A to select all images at once. Press and hold Ctrl and use the cursor to select multiple images. 20 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.2.1.7 Label assistant - Auto labeling To use auto labeling for a single image on the screen, click Label assistant in the toolbar at the top of the window. To use auto labeling for multiple images, select multiple images in the Image List pane, and then click Label assistant at the top of the Image List pane. NOTE: Labels in already labeled images will be overwritten when auto labeling is applied to them.
ASUS, Inc . 2.2.2.1.8 Edit category Click Remove or Edit at the top of the Category List pane to delete or modify the category. 2.2.2.1.9 Edit image list To delete image(s) from the image list, select the image(s), and click the Delete icon at the top of the image list pane. 22 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.2.1.10 Others Autosaving can be enabled by clicking the Auto Save icon in the top left corner of the toolbar. When enabled, image(s) will be automatically saved without having to bring up the dialog box. The number of labeled images and the total number of images are shown in the top row of the Image List pane.
ASUS, Inc . 2.2.2.2 Labeller - Object Detection This allows you to label images for object detection. Object Detection can label a rectangular area for good quality inspection. Add category Add image(s) Labeling Modify lable Label assistant (auto labling) Edit category Edit image list others Remove lable Select image by keyboard 2.2.2.2.1 Add category, add image(s) For these two steps, the process is the same as for segmentation, so you can refer to sections 2.2.2.1.1 and 2.2.2.1.
ASUS, Inc . 2.2.2.2.3 Modify label When an object is selected, you will see a dashed border around the labeled area. To adjust the selected area, move the cursor to one of the corners of the rectangular area and then click and drag to the desired size. Once complete, click the cursor outside of the selected area. 2.2.2.2.4 Remove label To remove any unnecessary or wrong labels, right-click over the labeled area, and select Clear All Mask.
ASUS, Inc . 2.2.2.2.5 Select image(s) by keyboard, Label assistant - Auto labeling, Edit category, Edit image list, and Others For these five steps, the process is the same as segmentation, so you can refer to sections 2.2.2.1.6 and 2.2.2.1.10 for details. 26 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.2.3 Labeller - Classification This allows you to label images for the classification process. Classification can quickly detect an entire photo for inspection. Add category Add image(s) Labeling Modify lable Label assistant (auto labling) Edit category Edit image list others Remove lable Select image by keyboard Except for labeling, all the steps are the same as for object detection, so refer to sections 2.2.2.1.1 and 2.2.2.1.10 for details. 2.2.2.3.
ASUS, Inc . 2.2.2.1.2, 2.2.2.1.6, and 2.2.2.1.8 to 2.2.2.1.10 for details. 2.2.3 Trainer This session is to train labeled image data that were prepared in the Labeller session. You can prepare or train AI models by setting different conditions using task(s). The time required for AI model training depends highly on the number of iterations. When running training sessions, avoid running simultaneously any GPU-hungry application(s).
ASUS, Inc . 2.2.3.2 Create and delete task(s) Click Add task(s) to create a new task. Click Delete task(s) to delete the currently selected task. 2.2.3.3 How to modify task detail Click Setting to see and edit the details for the selected task. 29 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.3.4 Task detail confirmation When a task is selected in the Task Setting pane, the details of that task are shown in the center of the window. Double-check the data for training and verification in the right-hand pane. Click any image file, and a preview box will show below. 2.2.3.5 Edit task detail Turn on or off to define the parameters required for training.
ASUS, Inc . 2.2.3.6 Start training To start training, select the training task and click START. 2.2.3.7 Training process During training, quit any GPU-hungry application(s). The top right corner shows the training progress in percent, and the center of the training main page shows a loss value curve. For any training, the ideal curve trends down with a converging amplitude. 31 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.3.8 Training complete When the training is complete, you will see 100% shown under Progress. You are now ready for the next step – verification. 2.2.3.9 Training schedule This part can schedule multiple tasks into the Scheduler for training. 32 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.4 Verifier This session is to verify how effectively the AI model was trained in the Trainer session. Verification reference is labeled “Ground Truth” in the Labeler session. The result pages show verification in Precision/Recall and Accuracy, respectively.
ASUS, Inc . 2.2.4.2 Check the result of each image. Once prediction in the verification process is complete, you can click each image data to check the prediction result for verification purposes. 2.2.4.3 Adjust overall threshold Adjust the threshold for each category in the Verification Setting pane. Once the thresholds are set, click Apply. The screen then shows the current image and the corresponding results. 34 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.4.4 Apply default threshold value Hitting Default can restore threshold and apply default value. 2.2.4.5 How to view report Click View to open the report page. A detailed verification report is displayed. 35 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.4.6 Detail report (1) - (segmentation/Object detection) The Report Viewer page shows Precision (Avg.) and Recall (Avg.) on top of this page and summary numbers right below. Right hand side shows detail of each image data for verification after prediction proceed upon category (Select desired category to see different result accordingly.) Row background color will display accurate prediction as green and inaccurate prediction in red accordingly upon desired or selected category. 2.2.4.
ASUS, Inc . 37 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.4.8 Export report Click Export Report to export button and selecting target path, you can export report to a html format file. 2.2.4.9 Export model Click Export to export the current task model, the model will be used in Predictor later. 38 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.4.10 Confusion Matrix Refer to the figure below for the definition and explanation of Confusion Matrix. True Positives (TP): Predicted target event a Positive, and the actual event is a positive. True Negatives (TN): Predicted target event a Negative, and the actual event is a negative. False Positives (FP): Predicted target event a Positive, and the actual event is a negative. False Negatives (FN): Predicted target event a Negative, and the actual event is a positive.
ASUS, Inc . Precision is the ratio of true positive events predicted over total sum of all predicted positive events. Recall = TP / (TP+FN) Recall is the ratio of true positive events predicted over total sum of actual positive events. Loss = FN / (TP+FN) Loss is the ratio of FN events over total sum of actual positive events. Detection = TP / (TP+FN) Detection is equal to Recall.
ASUS, Inc . 2.2.5 Predictor Predictor allows you to proceed with the AI model (*.ditox generated by Verifier) for prediction to target data (image). The prediction result can be shown as an image or in text format. Choose model Select target data Proceed prediction Result check 2.2.5.1 Choose model (*.ditox) Click Load Model (red box) to select a pre-trained model in the .ditox filename extension. The model name will show in the blue box below once the model is successfully loaded.
ASUS, Inc . 2.2.5.2 Select target data Click Add image to select the image data you want to process with prediction. Image data will be shown in the blue box below once it is successfully loaded. 2.2.5.3 Proceed prediction Click RUN to proceed with prediction. The time required depends on the model selected and the minimum data requirement that is set for prediction. A green mark in front of the predicted data image file(s) (shown boxed in blue). 42 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.2.5.4 Result check Click the image(s) to check the prediction result. Result related information provided (in the blue box below) and the elapsed time shown in the bottom right corner. 43 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.3 Scheduler This allows you to manage multiple parameters for pre-set project(s) Load project(s) Scheduling Re-arrange parameter(s) Training started 44 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.3.1 Load project(s) Click Import Project from the Project List pane, select the project(s) (*.ditprj) to be used for training. NOTE: Check the project labeling for training purposes with proper parameters. If labeling was not done correctly, circle back to the Trainer function to redo it. You can add multiple project(s) simultaneously. 45 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . 2.3.2 Scheduling -Select required parameter(s) to the scheduler list for each project or group of projects Available project(s) and parameter(s) are shown in the left pane. Select and set parameter(s) for each selected project or group of projects. 2.3.3 Re-arrange parameter(s) -Re-arrange the training sequence based on the selected parameter(s) Use the three (3) buttons on the top to move the parameter(s) up or down or to delete the parameter(s).
ASUS, Inc . 2.3.4 Start training Once the training parameter(s) have been arranged as planned, press START to start the training. The training progress is shown as a percentage in the right pane. Click Show Results at the right bottom corner. Once training is complete, the training results will be displayed. 47 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . Chapter 3: Upgrading AISVision 3.1 Complimentary AISVision upgrade policy You are eligible for a complimentary upgrade under the following circumstances. Otherwise, you will need to pay for an upgrade. A new version of AISVision is released with bug fixes A new version of AISVision is released with new features/functions/pre-trained models within 365 days of your AISVision purchase Otherwise, you will need to pay for an upgrade. 3.
ASUS, Inc . Step 2. 3.3 Cost to upgrade AI Toolkit Check with your ASUS representative for more details. 49 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . Chapter 4: Support for AISVision 4.1 Before you call customer support 4.1.1 Troubleshooting Double-check your hardware and software settings to make sure that they are set to run as designed. 4.1.2 Call for support Find the phone number of the ASUS IoT support center that is nearest to or most convenient for you in Contacting ASUS. A log file will be generated and saved in the system file manager folder (AISVision_version \App_Data\Logs). 4.1.
ASUS, Inc . Appendix Safety Information Regulatory notice Contacting ASUS Taiwan Talk to us AIS_support@asus.com Call Us | Official Support | ASUS Global China 官方支持 | ASUS 中国 Germany Telefonische Produktunterstützung +49 (0) 2102 5789 557 Telefon Ö sterreich +43 (0) 1360 2775 461 USA Chat with us 1-888-678-3688 https://www.asus.com/us/support 51 © 2021 ASUS, Inc. All rights reserved.
ASUS, Inc . Error Messages Do you want to save the modifications? FlowController.cs(177) Do not show this dialog box the next time, and project will be saved automatically every hour. The project has been modified. Do you want to save the FlowController.cs(215) modifications? Do not show this dialog box the next time, and project will be saved automatically. FlowController.cs(505) Would you save current project? FlowController.cs(540) The project is not found.
ASUS, Inc . PrjManagerForm.cs(738) Project is not fouund! ParamController.cs(519) Cannot delete following directory. [folder name] ParamController.cs(537) Cannot delete following directory. [folder name] SettingParameterForm.cs(385) Auto Split will Discard All Custom Changes. Continue Anyway? SettingParameterForm.cs(1096) The trained model will be deleted permanently (if exists), and it is irreversible.Continue anyway? SettingParameterForm.
ASUS, Inc . Cannot find any support image files in selected path VerifierController.cs(1321) (.png, .jpg, .jpeg). Please select a different path. VerifierController.cs(1353) Model weight (ckpt) is not defined. DoramiAIDetector.cs(65) Fail to load Model DoramiAIDetector.cs(185) Fail to load Image ClassEditor.cs(71) Class Name Can not be Blank ClassEditor.cs(88) The Class Name Already Exist. ClassEditor.cs(97) The Color of Class Already Exist. ClassEditor.