Release History

This topic lists the features and resolved issues in previous releases of VisionPro Deep Learning.

VisionPro Deep Learning 3.2.0

New Features

  • AI labeling tool

    In the AI labeling tool, you can use two key tools: AI Click Tool and AI Box Tool. These tools simplify labeling by automatically recognizing and labeling regions, eliminating the requirement for manual drawing. You can find more details in the "Create Label" section of Red Analyze.

  • Red Analyze processing speed

    The processing speed of the Red Analyze was enhanced, particularly in Red Analyze High Detail.

  • Faster image addition

    Adding images takes reduced time, resulting in faster handling when adding a large number of images.

Enhancements

  • GPU Clock Stabilizer
    The feature to maintain a stable GPU clock in a deployment environment can be helpful in multi-GPU scenarios or in situations where clock instability leads to reduced processing speed or spikes. For more details, refer to the API Change Log or API documentation.

Resolved Issues

  • Fixed an issue where CPU memory gradually increased when repeating training and processing of High Detail.

  • Fixed an issue where an internal error occurred during the creation of a runtime workspace, preventing its creation when there was a previously trained model using the large network in theGreen Classify High Detail from versions prior to VisionPro Deep Learning 3.1.1.

  • Fixed an issue where High Detail was not supported in ViDi.ITool.RegionOfInterest.

  • Fixed an error when training tools with a 1-channel 16-bit image.

  • Fixed an internal error that occurred during the Parameter Search when starting the search for Green Classify High Detail with Large model.

VisionPro Deep Learning 3.1.2

  • Hotfix release of VisionPro Deep Learning3.1.

Resolved Issues

  • Fixed an issue where tools trained using Green Classify High Detail tool's "large" modes inVisionPro Deep Learning 3.0 were not processing in VisionPro Deep Learning 3.1.1.

  • With the use of CLIP, you can now import a JSON file containing a "bad" tag without regions into Red Analyze.

  • Using CLIP, fixed an issue where the region name of a "bad" label in the Red Analyze Focused Supervised appeared as "bad" instead of "defect" during label export and import.

  • Using CLIP, fixed an issue of JSON file format labels not being imported in theGreen Classify.

  • The tooltip for the "mode" parameter in the High Detail parameters has been updated.

 

VisionPro Deep Learning 3.1.1

  • Windows 11 is now supported

    • Now VisionPro Deep Learning 3.2.1 supports Windows 11

  • RTX™ 40 series are tested

    • VisionPro Deep Learning supports on RTX™ 40 series which are RTX 4070 Ti, RTX 4080 and RTX 4090. It is tested on RTX 4080 and 4090.

  • Minor improvements

    • Improved the processing speed for High Detail tool by optimizing the internal logic, including the mask functionality.

    • Due to internal logic improvements, the training speed of Red Analyze High Detail tool has been partially enhanced.

    • In the Auto mode of Parameter search, remaining and elapsed time are displayed during the search.

Resolved Issues

  • Fixed an issue in Red Analyze High Detail where the view score would display as 0 after applying a mask and processing with the API.

  • Fixed an issue in the Red Analyze High Detail where the processing results differed when using Whole Image processing, although differences may still occur within an acceptable margin of error.

  • Fixed an issue where out of memory pop-up occurred during processing after completing training with Whole Image Processing on in Red Analyze High Detail, which prevented saving of the model. The tool now automatically turns off Whole Image Processing and proceeds with processing if it cannot perform the function.

  • Fixed an issue where the application would intermittently crash when loading a runtime workspace with multiple High Detail and using multi-GPU.

  • Fixed an issue where the Reuse mask option was not applied in the ROI settings for downstream tools when Red Analyze was the preceding tool.

  • Fixed an issue where the label check did not run when using Green Classify with more than three tags.

  • Restored the pan function that was missing in the image viewer.

  • Fixed an issue where Cognex Deep Learning Studio abnormally terminates when clicking on an empty column in the image list.

  • Fixed an issue where Cognex Deep Learning Studio abnormally terminates when entering an invalid color value for the tag after setting the tag in Green Classify.

  • Updated the tooltip description regarding the processing time displayed on the Cognex Deep Learning Studio, as it was previously shown in view unit instead of image unit.

  • Fixed an issue where entering -1 into the command line failed to correctly deactivate the auto-save feature in the service-client

  • Fixed an issue where the C++ sample code, Example.AdaptationMode.HD, was not functioning properly.

  • Fixed an issue that caused an error when attempting to switch from Auto mode to Manual mode in Parameter search, if there were spaces in the tags.

  • Fixed an issue where results were not displayed after conducting a search in auto mode with a tool in the downstream in Parameter search.

VisionPro Deep Learning 3.1.0 (Beta)

  • Beta release for Window 11

 

VisionPro Deep Learning 3.0.1

  • Adaptation Mode for High Detail tools

  • Red Analyze High Detail and Green Classify High Detail Architecture Upgrade

    • The neural network architecture of Red Analyze High Detail and Green Classify High Detail is updated in VisionPro Deep Learning 3.2.1.

  • Sampling without "Stride"

    • The sampling logic for Red Analyze High Detail training evolved that it can deliver the same performance without the Stride-based sampling. Due to this upgrade, the Stride in the Training parameters of Red Analyze High Detail is deprecated from VisionPro Deep Learning 3.0.

  • Backwards Compatibility

  • Change of Validation Loss Calculation

    • Another change from this architecture update is the new validation loss calculation for Red Analyze High Detail, which is used to select the best neural network during validation. See Validation Set and Validation Loss for more details.

  • Automatic Parameter Search

    • While the manual mode tests all combinations of the listed parameters and their value ranges, the auto mode cuts off unnecessary tests based on performance criteria and thus it can save more time for getting you the best values of provided parameters. The auto mode of is only supported for tools. See Parameter Search for details.

  • Label Check

    • The label quality value is scaled from 0 to 100. The lower the value, the noisier or the worse each label is. You can dramatically reduce the time spent reviewing the labels by sorting images in ascending order by the label quality value. Label Check is only supported for Red Analyze Focused Supervised, Red Analyze High Detail, and all Green Classify tool types. See Optimize Labeling with Label Check for more details.

  • Cognex Label Import/Export Plugin (CLIP)

    • CLIP is a new plug-in that supports importing/exporting masks and labels of a VisionPro Deep Learning workspace in VisionPro Deep Learning internal and external formats. You can export masks, labels, or images in a VisionPro Deep Learning workspace in VisionPro Deep Learning internal format or png file format, and also import masks or labels in various formats into a VisionPro Deep Learning workspace with this plug-in. See Cognex Label Import/Export Plug-in for details.

  • TensorRT Support for Runtime

    • The NVIDIA TensorRT is a library that boosts the inference speed of a deep neural network running on NVIDIA GPUs. The VisionPro Deep Learning now supports TensorRT for the runtime API, boosting the processing speed of each tool. TensorRT for Runtime is only supported in High Detail tools. For details of TensorRT support, see API Changelog.

  • Green Classify High Detail Batch Processing Support for Runtime

    • Using the Batch Processing API in runtime can speed up the Green Classify High Detail processing via API. For more details about the batch processing API, see API Changelog.

  • View Browser - List Mode

    • The list mode presents an information table that offers much more details about a view's status including marking, label, sets, or a view's index. You also can star a view if it is an important view or write and edit a memo for each view. See View Browser - List Mode for details.

  • Other Improvements & Changes

    • UI/UX Improvements in Parameter Search

    • GUI Refinement

    • Applying Label Change for Green Classify

    • Image Resize for Green Classify High Detail

    • Validation Set Indicator and Filter for Validation Set

    • Scale Change of Validation Loss

    • Image Processing Logic Change for Red Analyze High Detail

    • Minimum Image Size Change for Green Classify High Detail

    • Training Logic Change with Patience Epochs and Minimum Epochs

    • Designer Plug-in Support

    • Red Analyze sort filter keyword count(region!) in View Browser which sort the views by the number of labeled defect regions is changed to count(region![area > 0]).

 

VisionPro Deep Learning 2.1.1

  • Fixed an issue that the execution of VisionPro 10.1 C# API method Cognex.Vision.Startup.Shutdown() is not completed within an expected time when using VisionPro Deep Learning Tool Block.

  • Fixed an issue that the Focused tools (Blue Locate, Blue Read, Green Classify Focused, Red Analyze Focused Supervised, Red Analyze Focused Unsupervised) occasionally expose inconsistent results given exactly the same configurations.

  • Fixed an issue that the processing of Blue Locate or Blue Read rarely gets slower.

    • To solve this issue, we allowed access to a new processing parameter called max_scan_iterations in the runtime API. With this parameter, you can limit the maximum search time to speed up the processing. For more details, see API Changelog.

 

Resolved Issues

  • Fixed an issue that the execution of VisionPro 10.1 C# API method Cognex.Vision.Startup.Shutdown() is not completed within an expected time when using VisionPro Deep Learning Tool Block.

  • Fixed an issue that the Focused tools (Blue Locate, Blue Read, Green Classify Focused, Red Analyze Focused Supervised, Red Analyze Focused Unsupervised) occasionally expose inconsistent results given exactly the same configurations.

  • Fixed an issue that the processing of Blue Locate or Blue Read rarely gets slower. See API Changelog for more details.

 

VisionPro Deep Learning 2.1

  • Red Analyze High Detail Quick and Green Classify High Detail Quick
    • Faster than High Detail modes in training
    • Stay solid in task accuracy
    • More convenient with much less Tool Parameters to be tuned by hand.
  • Revamped Parameter Search
    • The user interface of Parameter Search has been completely renovated to enhance the usability of the tool.
  • Heatmap Overlay on Image Display Area for Green Classify High Detail and Green Classify High Detail Quick
    • For Green Classify High Detail and Green Classify High Detail Quick, the heatmaps are not only visible through View Inspector but directly in Image Display Area by enabling Heatmap checkbox in Image File Information. See Heatmap and GUI and API for the details.
  • Green Classify API Example Codes are updated for getting label information from images (RAPID XML)
    • C:\ProgramData\Cognex\VisionPro Deep Learning\2.1\Examples\c++\Example.Training.HDGreen
    • C:\ProgramData\Cognex\VisionPro Deep Learning\2.1\Examples\c++\Example.Training.Green
  • Improved tool loading speed into Workspace for a Red Analyze tool when it has significantly many detected regions (more than hundreds or thousands of regions) or regions with complex shapes per image.
  • Enhanced document contents. See Documentation Updates for the details.

 

Resolved Issues

  • Fixed an issue that some runtime API example codes were unable to be run because of missing DLL files.
  • Fixed an issue in High Detail Mode tools that the training time keeps increasing when training multiple High Detail mode tools in sequence.
  • Fixed an issue in Parameter Search that searching parameters for a Red Analyze tool already trained in VisionPro Deep Learning unnecessarily copies existing .vvb files and thus grows the size of the current workspace.
  • Fixed an issue in C API that 32-bit images (8-bit, 4 channel) added to a workspace by C API look bizarre when they are viewed in GUI.
  • Fixed an issue in Loss Graph that the Elapsed Time in Status table is not in accordance with the elapsed time in Progress bar.
  • Fixed an issue in Loss Graph that the Elapsed Epoch in Status table and Epoch in the loss graph are displayed incorrectly.
  • Fixed an issue that the value of ViDi2.View.maskCache keeps increasing and consumes memory.
  • For High Detail modes, fixed an issue that processing with GPU designation is not available when calling ISample.Process().
  • For VisionPro Deep Learning Client/Server environment, fixed an issue that VisionPro Deep Learning Client/Server cannot accept "16-bit depth, png/tiff format" image file as its input image.
  • For runtime workspaces, fixed an issue that users cannot get the label information of Green Classify High Detail with Runtime.IGreenTool.KnownTags
  • For Red Analyze, fixed an issue that after changing mode of tool operation (Supervised, Unsupervised) the class of a region is displayed incorrectly.
  • For Red Analyze, fixed an issue that after changing mode of tool operation (Supervised, Unsupervised) a region cannot be modified with Edit Region.
  • For Red Analyze High Detail, fixed an issue that if you change the mode of a Red Analyze tool to Red Analyze High Detail, add images, set ROI, and train with the default tool parameters, the score for a view is not generated.

 

VisionPro Deep Learning 2.0

  • VisionPro 10.0 Integration

    • VisionPro Deep Learning offers its tools (Blue, Red, Green tool in Runtime Workspace) for VisionPro 10.0 to be directly used in its QuickBuild as one of a VisionPro tool (DLRuntimeTool). See Integration with Cognex VisionPro and Known Issues.

  • Cognex Designer Support Termination

    • Since VisionPro Deep Learning runtime workspace can be directly imported into VisionPro 10.0 QuickBuild the integration with Cognex Designer (the Plug-in for Cognex Designer) is no longer supported from VisionPro Deep Learning 2.0.

 

Resolved Issues

  • Fixed an issue that a plug-in that was built in Examples (C:\ProgramData\Cognex\VisionPro Deep Learning\2.0\Examples\c#\Example.Deep.Learning.Studio.GUI.Plugin) is not shown on Add Plugin window of Plugin Manager.

 

VisionPro Deep Learning 1.1

  • Red Analyze High Detail

    • A new solution with a powerful new architecture for supervised segmentation tasks that were previously only handled by Red Analyze Supervised Mode. With the addition of Red Analyze High Detail Mode, Red Analyze tools are now reorganized and fall into the following category:

      Name Architecture Mode
      Red Analyze High Detail High Detail Supervised
      Red Analyze Supervised Focused Supervised
      Red Analyze Unsupervised Focused Unsupervised
  • Loss Inspector
    • A monitoring tool of the validation loss change during training that guides you in training High Detail Modes (Red Analyze High Detail and Green Classify High Detail mode).
  • F1 Score of Confusion Matrix for Red Analyze tools
    • The F1 score of the confusion matrix is introduced to show the result summary of the confusion matrix in Red Analyze tools. See Confusion Matrix for an example of the F1 score of confusion matrix.
    • Unlike the precision, recall, and F-score in Region Area Matrix which are calculated on a "pixel" basis, the F1 score of a confusion matrix is calculated from each "item in the confusion matrix table", aiming to suggest the performance of this tool with respect to the confusion matrix result.
  • Auto Threshold for Red Analyze High Detail and Red Analyze Focused Supervised
    • The T1 and T2 threshold values that maximize the F1 score of confusion matrix on Database Overview by following one of the 4 criteria in the Count dropdown menu. These threshold values are automatically calculated for you by enabling a checkbox. See Process Neural Network (Inferencing) for an example of the Auto Threshold.
  • Region List for Red Analyze tools
    • The region list is introduced to help you find and check the defect regions (both labeled defects and markings) in a view more easily and conveniently and thus enhance your usability of Red Analyze tools.
  • Overlay Checkbox
    • For all tools, the overlay checkbox is introduced for a handy alternative to "Cycle through Overlays" in the right-click pop-up menu on Image Display Area. See Review Markings for an example of the overlay checkbox for Blue Locate tool.
  • Restore Parameters
    • For all tools, the restore parameter button is introduced for an easier "roll-back" of the set of parameter values in the Tool Parameters pane toward those that were used in the last training session. See Train Neural Network for an example of the restore parameters button for Blue Locate tool.

  • Wibu CodeMeter Runtime update from 6.70a to 7.20b to resolve the known security vulnerabilities (WIBU-200521-01, WIBU-200521-02, WIBU-200521-03, WIBU-200521-05, WIBU-200521-06).

 

Resolved Issues

  • Fixed an issue in Parameter Search that some texts in Database Overview are overlapped to each other and displayed incorrectly.

  • Multiple GPUs are now fully supported efficiently for High Detail modes. See Configure Multiple GPUs for the details.

  • Fixed a bug that the multiple additions of the same plugin with Manage Plugins.

  • Fixed a bug that VisionPro Deep Learning is not launched when the version of nvml.dll (C:\Windows\System32\nvml.dll) is lower than the NVIDIA graphics driver version.

  • Fixed a bug in Blue Read that the overlay of marking and label is not correctly displayed.

  • Fixed a bug in Red Analyze that the area under ROC curve is different from AUC value in Database Overview - ROC tab.

  • Fixed an issue in Designer for Red Analyze that the workflow of Deep Learning Runtime Block of Red Analyze slows down due to heatmap processing. It is fixed by adding a 'heatmap' checkbox and the users now can control the processing speed by enabling/disabling the checkbox.

  • Fixed some naming inconsistencies in C:\ProgramData\Cognex\VisionPro Deep Learning\1.1\Examples\c#

    • The assembly name for Example.Training.HDRed.Console is modified to the right name.

    • The project file name "Example.ViDi.Suite.GUI.Plugin" is changed to "Example.Deep.Learning.Studio.GUI.Plugin"

    • The assembly name with "space" delimiter is changed to the one with "period/full-stop" delimiter.

 

VisionPro Deep Learning 1.0.1

  • Support for NVIDIA GeForce® RTX™ 30 series.

    • VisionPro Deep Learning 1.0.1 supports RTX 3090, RTX 3080 and RTX 3070 for all tasks.

    • If you're exploiting multiple GPUs, all of them should be consist of RTX™ 30 series of the same type and of the same specification. See Configure Multiple GPUs for more details.

    • Currently, there are some known issues relating to NVIDIA driver versions and Processing Time. See Known Issues for more details.

  • Support for Optimized GPU Memory in Parameter Search

    • If you use Focused Mode in Parameter Search, you can set and use Optimized GPU Memory.

    • If you use High Detail Mode in Parameter Search, Optimized GPU Memory is automatically disabled for the efficiency of High Detail Mode.

 

Resolved Issues

  • Resolved an issue that the prediction result of a cloned Red Analyze Tool is incorrect when Low Precision is enabled.

  • Resolved an issue that labeling is mistakenly applied on images, not views, after receiving views from an upstream tool.

  • Resolved an issue that the space between "Image Record" blocks you from using ImageRecord feature with DeepLearningRuntimeBlock inside Designer.

 

VisionPro Deep Learning 1.0

  • Two modes for the Green Classify Tool.

    • High Detail mode (from SuaKIT), which provides higher classification accuracy on many challenging applications.

    • Focused mode (from ViDi) for simpler applications that need faster training or runtime execution.

    • A Heat Map for High Detail mode, which visually indicates which portions of the image were most influential in the classification decision.

    • Validation sets for High Detail mode. These provide feedback on model performance and are used for training optimization.

    • You can enable/disable GPU memory optimization for use with High Detail mode and other tools.

  • Simpler labeling controls, including
    • Selecting multiple samples when label or accepting views, clearing markings and labels, processing, or managing image sets.
    • Automatically re-using the last label name by default, rather than requiring you to explicitly type each new label.

 

Resolved Issues

  • Resolved an issue with feature size indicator does not change after changing the value of the feature size in the sampling tool parameter.

  • Resolved an issue with "Save new version" in the workspace list does not act in the Blue Read Tool.

  • Resolved an issue with name of Set are shown as original name in the image viewer even though users change the name.

 

VisionPro ViDi 4.1.0

  • Additional Blue Locate tool enhancements, including the following:
    • New handles on the feature graphic labels to make resizing easier.
    • Select either rectangular or circular feature graphic labels.
    • Display or hide the name of feature graphic labels.
    • Copy and paste feature label graphics, as well as cloning a feature graphic label by clicking on it.
    • Auto-generate the creation of a layout model by selecting features and selecting Create Model.
  • Additional configuration options for assigning the GPU mode and memory, along with an auto-save feature and training image cache path, can now be set from the Options dialog, which is available in the Starting Cognex ViDi Suite startup dialog.
  • The ViDi Suite GUI has been localized into six languages: French, German, Japanese, Korean, Simplified Chinese and Spanish. The language can be selected from the Locale drop-down within the Options dialog.

 

Resolved Issues

  • To improve the ability to determine if a view is labeled or not, a new property, IView.IsLabeled, has been added to the .NET API.
  • Resolved an issue with large images and the Red Analyze tool in Unsupervised mode that could result in an invalid exception "Database is Locked" error.

 

VisionPro ViDi 3.4.1

  • Blue Locate tool
    The Blue Locate tool has undergone significant overhaul, including the following:
    • Create a Layout Model, which provides presence/absense verification of features in areas of an image.
    • New label, marking and model graphics to both increase visibility and usability by making labeled and marked features clearer, and handles to enhance graphic interaction when moving and resizing labels.
    • Feature identifiers can now be up to 140 characters.
    • Improved capabilities for oriented and scaled features.
    • Improved workflow when labeling images/views, with the tool remembering the previously labeled feature, allowing you to start with one image, create a label, and then apply that label to remainder of your images.
    • Improved performance of node models, along with a new Model Editor GUI.
    • The tool can now create a region of interest for downstream tools based on a feature, a match, or a node or layout model.
  • Training workflow
    • There is a new paradigm for defining the images/views that will be used to train tools, allowing the process to be more transparent and controllable through integration with the new image sample sets.
  • Image sample sets
    • The ability to create and manage images/views as training and testing sample sets has been added, which allows for better management of the images/views used to train and test tools.
  • Database Overview filtering
    • While in Expert Mode, it is now possible to filter results and statistics in the Database Overview, using the syntax of the Display filters.
  • Blue Read tool
    • Capability to identify and read rotated characters.
  • Red Analyze tool
    • An eraser tool has been added which allows you to remove areas of defect regions and masks.
  • In addition to the above new features, there have been numerous performance and stability improvements.

 

Resolved Issues

  • Resolved an issue where exporting or cloning a large workspace could cause the ViDi Suite GUI to become unresponsive or unexpectedly quit.

  • Resolved an issue where a Blue Locate or Blue Read tool's graphical display of markings could be offset from its actual location due to the language settings of the user's PC.

  • Resolved an issue with the Blue Read tool's Label Views dialog not displaying the names of Regex models that had been created.

  • Resolved an issue with the Red Analyze tool's generated reports not displaying the markings in the report.

 

VisionPro ViDi 3.3.0

  • General stability and performance improvements.
  • Improved support for NVIDIA® Turing™ Tensor Cores for the Red Analyze and Green Classify tools with the Low Precision parameter enabled.
  • Two new model types have been added for the Blue Read tool.
    • A regular expression model, which allows you to specify string matches based on regular expressions. This type of model offers faster, more flexible model matching for applications with linear arrangements of text than the existing node model.
    • A string model, which allows you to match linear strings based on the length of the text string.
  • Improved performance for image displays that include a large number (500+) of feature graphics.
  • Improved readability of the Green Classify tool's class labels when creating reports for the tool.
  • Simplified controls for rotating a tool's Region of Interest (ROI).
  • Support for Cognex VisionPro version 9.5 has been added.

 

Resolved Issues

Issue Description
AIC-1861 Corrected an issue with NVIDIA drivers 411.31 and newer. For more information, please visit the Cognex Support Site VisionPro ViDi Software Driver Support page.
AIC-1801 The Set Group option has been restored to the Actions for N Views menu in the View Browser, which allows you to create a group of images when using the Red Analyze tool in Unsupervised Mode.
AIC-1201 Corrected an issue where a workspace would not function correctly if a stream contained a single quote in the name.
AIC-1223 Corrected an issue where the ViDi Suite GUI would become unresponsive when applying a region for a Red Analyze tool with numerous views.
AIC-1387 Corrected an issue where the ViDi Suite GUI would not terminate properly after attempting to connect to a runtime-only service.

 

VisionPro ViDi 3.2.1

  • This release introduces the ViDi Client/Server functionality, allows you to use the training and runtime implementations of the ViDi software on multiple PCs, through the use of a server/client model. This functionality gives you the option of using a remote service for runtime inference and/or training, instead of using the GPU on your local PC. This can be useful if you have a more powerful GPU on the server, or perhaps you do not have a GPU installed locally.
  • This functionality supports up to 4 clients for deployment operation, and up to 8 clients for development.
  • This release provides enhancements and speed improvements for the ViDi runtime:
    • Support for NVIDIA® Tensor Cores has been added, and the GPU Optimization feature also now supports Tensor Cores.
    • The Low Precision parameter has been added to the Red Analyze and Green Classify tools, which optimizes the tools for speed during runtime operation.
  • The Feature Filter has been added to the Blue Locate and Blue Read tools, which allows you to filter found features by ID, X, Y, size and orientation.
  • The ViDi GUI and the ViDi Help file have been translated into Simplified Chinese. To view the GUI and Help in Chinese, the OS language setting must be set to Simplified Chinese.
  • Support for up to 32MP images (up to 16k in height or width) has been added.

 

VisionPro ViDi 3.1.0

Tool and GUI Changes

  • The ViDi Blue Read Tool has been added for Optical Character Recognition (OCR) applications.
  • Speed improvements and increased performance for the Blue Locate Tool when matching models.
  • The Feature Size parameter is now interactive and can be graphically resized within the GUI.
  • Labeling with the Blue tools has been improved to include multi-feature selection and interaction.
  • The Blue tools have improved flexibility for model optimization.
  • In the results, a Confusion Matrix has been added for the Blue Locate and Blue Read tools.
  • A new feature/match and region-focus display mode has been added when using the Database Explorer.
  • Checks have been added to provide feedback on wrongly labeled views.
  • The examples have been updated, and there is a new example for the Blue Read tool.
  • The Green Classify Tool now includes the Exclusive parameter, which, when disabled, allows you to label a single image with multiple labels (indicating that the image belongs to multiple classes).
  • The Red Analyze Tool – Statistics have been enhanced for better readability.
  • There have been numerous issues resolved, and additional enhancements and improvements to the ViDi software.

 

Processing and Support Changes

  • The GPU Memory Optimization is now activated by default (when using either the Windows Display Driver Model or Tesla Compute Cluster drivers). This feature can be activated and/or deactivated via command line arguments and the API.
  • Command line arguments have been added to allow you to select the number of GPUs to utilize at startup of ViDi, to specify the GPU mode and to specify the amount of GPU memory to pre-allocate.
  • There is a new Cognex VisionPro wrapper assembly, which provides data conversion between VisionPro and ViDi Suite, offering the following:
    • Efficient image conversion
    • Combined graphics
    • Fixturing conversion
    • Calibration conversion
  • Support for Cognex Designer 4.0 has been added, with the addition of a ViDi Sub Task block, which contains the ViDi Suite tools and the ability to program the tools within the Cognex Designer IDE.
  • Support for Cognex VisionPro 9.3 has been added.
  • Support for Microsoft® Windows® 10 Professional (64-bit).
  • Support for Microsoft® Windows® 7 Professional (64-bit).
  • The performance when loading training Workspaces, utilizing on-demand loading of tools, has been improved.
  • A new Workspace archive format, based on ZIP files, has been implemented.