Known Issues

The following issues have been identified in this release. For the API known issues, see API Known Issues

VisionPro Deep Learning 3.2.1

There is a score difference between the GUI and the runtime when using 16-bit images with the Green Classify High Detail, Green Classify High Detail Quick, and the Red Analyze High Detail tools.

VisionPro Deep Learning 3.2

GPU

• Processing Time could be slower compared to 1.0.0 under old GPUs. Processing Time could be slower compared to 1.0.0 when using NVIDIA GeForce® RTX™ 20 series or older series due to NVIDIA internal issues.

• Due to several issues related to GUI and training, all users of VisionPro Deep Learning 3.2.1 MUST use NVIDIA driver that is of:

  • After VisionPro Deep Learning 3.2.1, recommended GPU driver version range is from 528.02 to 532.03, with the tested version being 528.02. Using driver versions beyond 532.03 may result in slower training and processing times in High Detail .

 

Cognex Deep Learning Studio (GUI)

• During creating a report when you log off your PC, some of images are shown black. To avoid this issue, please do not log off your PC (neither turn off the remote environment nor lock screen) while you are creating a report.

• “No License Found” error occasionally occurs when you try to open 2 different versions of VisionPro Deep Learning, or launch Parameter Search and VisionPro Deep Learning, at the same time.

 

Workspace

• Boost::filesystem::rename error occurs when the user or system repetitively saves the workspace in a short time. This is just an alert that there was an issue while saving. You can solve this problem only by saving the workspace again.
• Group is shown in the workspace imported from ViDi Suite.

• If you import workspaces including "Group" feature which are made 4.1 and before, "Group" is still displayed in Cognex Deep Learning Studio 3.0, but you cannot modify this.

• See the FAQ for the workaround for this issue.

• It is recommended to delete "Group" in the previous workspaces and import to Cognex Deep Learning Studio 3.0.

• Especially with bigger than 10GB workspaces,
  • Cloning work does not end when you clone tools in different big workspaces at the same time.
  • Some images are not included in the created report.

 

Tools - General

• If a tool is not saved well because of unspecific reasons, you cannot export or clone the workspace or the tool. You can avoid this problem by processing the tools again and save the workspace.

• For all tools, if the tool crashes with some unknown reason, images in this tool are deleted when the workspace that contains this tool is imported.

• If the name of a set in Database Overview contains a single quote ('), you cannot change the name of this set.

• If the name of a set in Database Overview contains a single quote ('), an error occurs when you try to filter views on View Browser by clicking the icon of this set in Database Overview.

 

Tools - Red Analyze

• Processing results are different between GPU and CPU. The difference is in the second decimal place of the result. For example, When you process with CPU and GPU respectively, different results can be obtained, such as 0.80 and 0.81.

• Defect regions do not extend to the left side of the view in Red Analyze Tool. To avoid this problem, when the defect area touches the left side of the image, please set 4 pixels wider ROI than the original image size. For example, if you have (x=0,y=0,w=100,h=100) image and it has detected area touch to left side of the image, please set (x=-4, y=0, w=104, h=100) ROI size.

• When you set the smaller feature size (especially smaller than 10) and train the Red Analyze tool (both in Supervised and Unsupervised mode), the workspace is getting bigger. The vvb file which is for saving heat map within the workspace is the main reason. For example:
  • feature size=10, sampling density=3, 8192x8192 image: 1 vvb file size=94MB
  • feature size=10, sampling density=10, 8192x8192 image: 1 vvb file size=1GB
  • feature size=40, sampling density=3, 8192x8192 image: 1 vvb file size=23KB

• For Red Analyze Supervised modes (High Detail and Focused), applying the region filter could affect the result of Auto Threshold to be compromised in generating an optimal threshold for the best F1 score.

• For Red Analyze High Detail, changing a value in Processing Parameter in Tool Parameters and rolling back to the original value could affect the result at 4 decimal places.

• For Red Analyze High Detail, generally, you can guess that processing time increases when you reduce the Downsampling Size, but the opposite case can happen but this is not a bug.

• For Red Analyze Supervised, if there were an extremely enormous amount of defect regions per view, especially when the tool is not trained enough, VisionPro Deep Learning becomes slow and the expected value of processing time becomes inaccurate. Please take the tool re-trained to learn the image information fairly enough.

• For Red Analyze Tool, the area of a marked defect region and the area of a labeled defect region which is created by accepting (right-click on a marked region → click Accept Region) that marked region, is slightly different from each other.

• For Red Analyze Focused Supervised, its Database Overview crashes when there are multiple types of labeled defect regions.

 

Tools - Green Classify

• Once you are done with training High Detail mode of Green Classify Tool, you cannot change the name of the class.

• For Green Classify High Detail, resizing views takes a little more time when it is the first processing of the tool.

• For Green Classify High Detail, the processing preparation takes a little more time when it is the first processing of the tool.

 

Tools - Blue Read

• For Blue Read, the markings are displayed on the view regardless of the Marking checkbox in Image File Information is whether enabled or disabled. This issue has existed since ViDi 4.1.

 

Parameter Search

• In Home page, if you set 1-depth directory path (example: "E:/," or "A:/") in the Path, Parameter Search is terminated with an error and you can't re-open it. Please refer to Unable to start Parameter Search after setting 1-depth directory path at Path in its Home page. for the workaround of this issue.

 

VisionPro Deep Learning Service

• MultipleDevicesPerTool is no longer supported for VisionPro Deep Learning. Therefore you will have an “One or more error occurred” error if you select “--gpu-mode =MultipleDevicesPerTool” for service. Please choose another option to run VisionPro Deep Learning Service.
• For VisionPro Deep Learning Service, Export Runtime Workspace to Service on the right-click pop-up menu on Workspaces panel is currently disabled. To export runtime workspace, please go to and select Workspace - Export Runtime Workspace to Service instead.
• For VisionPro Deep Learning Service, when hosting a service with 2 different server ports (Client 1 connects via Port 1 and Client 2 connects via Port 2), the “Lock” icon does not appear on a workspace in Workspaces for a client when this workspace has been already used by one another.

 

 

VisionPro Deep Learning 2.1 (2.0, 2.1.1)

GPU

• Processing Time could be slower compared to 1.0.0 under old GPUs. Processing Time could be slower compared to 1.0.0 when using NVIDIA GeForce® RTX™ 20 series or older series due to NVIDIA internal issues.

 

Operating System (OS)

• Due to OS compatibility issues caused from NVIDIA drivers, Windows Server 2016 is not supported on VisionPro Deep Learning. For the users with Windows Server 2016 environment, upgrading from Windows Server 2016 to Windows Server 2019 is required for the utilization of VisionPro Deep Learning servers. Windows Server 2019 is only supported for 'servers' configured to use the Deep Learning Client/Server functionality.

 

Cognex Deep Learning Studio (GUI)

• During creating a report when you log off your PC, some of images are shown black. To avoid this issue, please do not log off your PC (neither turn off the remote environment nor lock screen) while you are creating a report.

• “No License Found” error occasionally occurs when you try to open 2 different versions of VisionPro Deep Learning, or launch Parameter Search and VisionPro Deep Learning, at the same time.

 

Workspace

• Boost::filesystem::rename error occurs when the user or system repetitively saves the workspace in a short time. This is just an alert that there was an issue while saving. You can solve this problem only by saving the workspace again.
• Group is shown in the workspace imported from ViDi Suite.

• If you import workspaces including "Group" feature which are made 4.1 and before, "Group" is still displayed in Cognex Deep Learning Studio, but you cannot modify this.

• See the FAQ for the workaround for this issue.

• It is recommended to delete "Group" in the previous workspaces and import to Cognex Deep Learning Studio.

• Especially with bigger than 10GB workspaces,
  • Cloning work does not end when you clone tools in different big workspaces at the same time.
  • Some images are not included in the created report.

 

Tools - General

• If a tool is not saved well because of unspecific reasons, you cannot export or clone the workspace or the tool. You can avoid this problem by processing the tools again and save the workspace.

• For all tools, if the tool crashes with some unknown reason, images in this tool are deleted when the workspace that contains this tool is imported.

• If the name of a set in Database Overview contains a single quote ('), you cannot change the name of this set.

• If the name of a set in Database Overview contains a single quote ('), an error occurs when you try to filter views on View Browser by clicking the icon of this set in Database Overview.

 

Tools - Red Analyze

• Processing results are different between GPU and CPU. The difference is in the second decimal place of the result. For example, When you process with CPU and GPU respectively, different results can be obtained, such as 0.80 and 0.81.

• Defect regions do not extend to the left side of the view in Red Analyze Tool. To avoid this problem, when the defect area touches the left side of the image, please set 4 pixels wider ROI than the original image size. For example, if you have (x=0,y=0,w=100,h=100) image and it has detected area touch to left side of the image, please set (x=-4, y=0, w=104, h=100) ROI size.

• When you set the smaller feature size (especially smaller than 10) and train the Red Analyze tool (both in Supervised and Unsupervised mode), the workspace is getting bigger. The vvb file which is for saving heat map within the workspace is the main reason. For example:
  • feature size=10, sampling density=3, 8192x8192 image: 1 vvb file size=94MB
  • feature size=10, sampling density=10, 8192x8192 image: 1 vvb file size=1GB
  • feature size=40, sampling density=3, 8192x8192 image: 1 vvb file size=23KB

• For Red Analyze Supervised modes (High Detail and Focused), applying the region filter could affect the result of Auto Threshold to be compromised in generating an optimal threshold for the best F1 score.

• For Red Analyze High Detail, changing a value in Processing Parameter in Tool Parameters and rolling back to the original value could affect the result at 4 decimal places.

• For Red Analyze High Detail, generally, you can guess that processing time increases when you reduce the Downsampling Size, but the opposite case can happen but this is not a bug.

• For Red Analyze Supervised, if there were an extremely enormous amount of defect regions per view, especially when the tool is not trained enough, VisionPro Deep Learning becomes slow and the expected value of processing time becomes inaccurate. Please take the tool re-trained to learn the image information fairly enough.

• For Red Analyze Tool, the area of a marked defect region and the area of a labeled defect region which is created by accepting (right-click on a marked region → click Accept Region) that marked region, is slightly different from each other.

• Erasing maskings/regions in the mask/region editor pane (Edit Mask or Edit Region in right-click popup menu on the image display area) applies Gaussian smoothing on all the regions/maskings. This causes the entire maskings/regions to shift slightly and their sizes to be changed slightly. This issue has been an existing issue from VisionPro ViDi.

 

Tools - Green Classify

• Once you are done with training High Detail mode of Green Classify Tool, you cannot change the name of the class.

 

Tools - Blue Read

• For Blue Read, the markings are displayed on the view regardless of the Marking checkbox in Image File Information is whether enabled or disabled. This issue has existed since ViDi 4.1.

 

Parameter Search

• In Home page, if you set 1-depth directory path (example: "E:/," or "A:/") in the Path, Parameter Search is terminated with an error and you can't re-open it. Please refer to Unable to start Parameter Search after setting 1-depth directory path at Path in its Home page. for the workaround of this issue.

 

VisionPro Deep Learning Service

• MultipleDevicesPerTool is no longer supported for VisionPro Deep Learning. Therefore you will have an “One or more error occurred” error if you select “--gpu-mode =MultipleDevicesPerTool” for service. Please choose another option to run VisionPro Deep Learning Service.
• For VisionPro Deep Learning Service, Export Runtime Workspace to Service on the right-click pop-up menu on Workspaces panel is currently disabled. To export runtime workspace, please go to and select Workspace - Export Runtime Workspace to Service instead.
• For VisionPro Deep Learning Service, when hosting a service with 2 different server ports (Client 1 connects via Port 1 and Client 2 connects via Port 2), the “Lock” icon does not appear on a workspace in Workspaces for a client when this workspace has been already used by one another.

 

Migration from SuaKIT or The Past VisionPro Deep Learning Versions

• High Detail mode uses a different resize algorithm to SuaKIT (Green Classify Tool in High Detail mode only). To use an imported SuaKIT model with VPDL runtime API, please use SuaKIT resize API before processing.
• For SuaKIT plugin, The result of processing between the imported SuaKIT Segmentation project in VisionPro Deep Learning and the original SuaKIT Segmentation project could be different due to the internal logic change of VisionPro Deep Learning 1.1.

 

Integration with VisionPro

• Due to the currently limited support of VisionPro 10, the external ROI is not supported for a DLRuntimeTool Edit Control Panel in VisionPro 10 for the time being.

 

Plug-in

• For Designer, the added heatmap checkbox is initialized on Deep Learning Runtime Blocks of the tools other than Red Analyze. Tools other than Red Analyze were supposed not to support heatmap function.

 

VisionPro Deep Learning 1.1 (1.1.1)

GPU

• Processing Time could be slower compared to 1.0.0 under old GPUs. Processing Time could be slower compared to 1.0.0 when using NVIDIA GeForce® RTX™ 20 series or older series due to NVIDIA internal issues.

• Internal issues on supporting NVIDIA driver versions. Due to internal issues related to NVIDIA drivers, all users of VisionPro Deep Learning 1.1.0 MUST use NVIDIA driver that is of:

  • 461.09 or higher version for NVIDIA GeForce® series.

  • R460 U2 (461.09) or higher version for NVIDIA RTX / Quadro® series.

• Due to internal issues related to runtime, C API may not work as intended. To prevent this issue, all users of C API MUST follow the steps below.

  1. Remove the currently installed NVIDIA driver from your PC.

  2. Reboot your PC and install the DCH NVIDIA driver of which version is compatible with VisionPro Deep Learning 1.1.0 (461.09 or higher, or R460 U2 (461.09) or higher for NVIDIA RTX / Quadro®)

 

Operating System (OS)

• Due to OS compatibility issues caused from NVIDIA drivers, Windows Server 2016 is not supported on VisionPro Deep Learning. For the users with Windows Server 2016 environment, upgrading from Windows Server 2016 to Windows Server 2019 is required for the utilization of VisionPro Deep Learning servers. Windows Server 2019 is only supported for 'servers' configured to use the Deep Learning Client/Server functionality.

 

Cognex Deep Learning Studio (GUI)

• During creating a report when you log off your PC, some of images are shown black. To avoid this issue, please do not log off your PC (neither turn off the remote environment nor lock screen) while you are creating a report.

 

Workspace

• Boost::filesystem::rename error occurs when the user or system repetitively saves the workspace in a short time. This is just an alert that there was an issue while saving. You can solve this problem only by saving the workspace again.
• Group is shown in the workspace imported from ViDi Suite.

• If you import workspaces including "Group" feature which are made 4.1 and before, "Group" is still displayed in Cognex Deep Learning Studio, but you cannot modify this.

• See the FAQ for the workaround for this issue.

• It is recommended to delete "Group" in the previous workspaces and import to Cognex Deep Learning Studio.

• Especially with bigger than 10GB workspaces,
  • Cloning work does not end when you clone tools in different big workspaces at the same time.
  • Some images are not included in the created report.

 

Tools - General

• If a tool is not saved well because of unspecific reasons, you cannot export or clone the workspace or the tool. You can avoid this problem by processing the tools again and save the workspace.

• For all tools, if the tool crashes with some unknown reason, images in this tool are deleted when the workspace that contains this tool is imported.

• If the name of a set in Database Overview contains a single quote ('), you cannot change the name of this set.

• If the name of a set in Database Overview contains a single quote ('), an error occurs when you try to filter views on View Browser by clicking the icon of this set in Database Overview.

 

Tools - Red Analyze

• Processing results are different between GPU and CPU. The difference is in the second decimal place of the result. For example, When you process with CPU and GPU respectively, different results can be obtained, such as 0.80 and 0.81.

• Defect regions do not extend to the left side of the view in Red Analyze Tool. To avoid this problem, when the defect area touches the left side of the image, please set 4 pixels wider ROI than the original image size. For example, if you have (x=0,y=0,w=100,h=100) image and it has detected area touch to left side of the image, please set (x=-4, y=0, w=104, h=100) ROI size.

• When you set the smaller feature size (especially smaller than 10) and train the Red Analyze tool (both in Supervised and Unsupervised mode), the workspace is getting bigger. The vvb file which is for saving heat map within the workspace is the main reason. For example:
  • feature size=10, sampling density=3, 8192x8192 image: 1 vvb file size=94MB
  • feature size=10, sampling density=10, 8192x8192 image: 1 vvb file size=1GB
  • feature size=40, sampling density=3, 8192x8192 image: 1 vvb file size=23KB

• For Red Analyze Supervised modes (High Detail and Focused), applying the region filter could affect the result of Auto Threshold to be compromised in generating an optimal threshold for the best F1 score.

• For Red Analyze High Detail, changing a value in Processing Parameter in Tool Parameters and rolling back to the original value could affect the result at 4 decimal places.

• For Red Analyze High Detail, generally, you can guess that processing time increases when you reduce the Downsampling Size, but the opposite case can happen but this is not a bug.

• For Red Analyze Supervised, if there were an extremely enormous amount of defect regions per view, especially when the tool is not trained enough, VisionPro Deep Learning becomes slow and the expected value of processing time becomes inaccurate. Please take the tool re-trained to learn the image information fairly enough.

• For Red Analyze Tool, the area of a marked defect region and the area of a labeled defect region which is created by accepting (right-click on a marked region → click Accept Region) that marked region, is slightly different from each other.

• Erasing maskings/regions in the mask/region editor pane (Edit Mask or Edit Region in right-click popup menu on the image display area) applies Gaussian smoothing on all the regions/maskings. This causes the entire maskings/regions to shift slightly and their sizes to be changed slightly. This issue has been an existing issue from VisionPro ViDi.

 

Tools - Green Classify

• Once you are done with training High Detail mode of Green Classify Tool, you cannot change the name of the class.

 

Tools - Blue Read

• For Blue Read, the markings are displayed on the view regardless of the Marking checkbox in Image File Information is whether enabled or disabled. This issue has existed since ViDi 4.1.

 

VisionPro Deep Learning Service

• MultipleDevicesPerTool is no longer supported for VisionPro Deep Learning. Therefore you will have an “One or more error occurred” error if you select “--gpu-mode =MultipleDevicesPerTool” for service. Please choose another option to run VisionPro Deep Learning Service.
• For VisionPro Deep Learning Service, Export Runtime Workspace to Service on the right-click pop-up menu on Workspaces panel is currently disabled. To export runtime workspace, please go to and select Workspace - Export Runtime Workspace to Service instead.
• For VisionPro Deep Learning Service, when hosting a service with 2 different server ports (Client 1 connects via Port 1 and Client 2 connects via Port 2), the “Lock” icon does not appear on a workspace in Workspaces for a client when this workspace has been already used by one another.

 

Migration from SuaKIT or The Past VisionPro Deep Learning Versions

• High Detail mode uses a different resize algorithm to SuaKIT (Green Classify Tool in High Detail mode only). To use an imported SuaKIT model with VPDL runtime API, please use SuaKIT resize API before processing.
• For SuaKIT plugin, The result of processing between the imported SuaKIT Segmentation project in VisionPro Deep Learning and the original SuaKIT Segmentation project could be different due to the internal logic change of VisionPro Deep Learning 1.1.

 

Integration with VisionPro

• Due to the currently limited support of VisionPro 10, the external ROI is not supported for a DLRuntimeTool Edit Control Panel in VisionPro 10 for the time being.

 

Plug-in

• For Designer, the added heatmap checkbox is initialized on Deep Learning Runtime Blocks of the tools other than Red Analyze. Tools other than Red Analyze were supposed not to support heatmap function.

 

VisionPro ViDi 3.1.0 ~ VisionPro Deep Learning 1.0.1

GPU

• Processing Time could be slower compared to 1.0.0 under old GPUs. Processing Time could be slower compared to 1.0.0 when using NVIDIA GeForce® RTX™ 20 series or older series due to NVIDIA internal issues.

• Internal issues on supporting NVIDIA driver versions. Due to internal issues related to NVIDIA drivers, all users of VisionPro Deep Learning 1.0.1 MUST use NVIDIA driver that is of:

  • 457.09 or higher version for NVIDIA GeForce® series.

  • R460 U2 (461.09) or higher version for NVIDIA RTX / Quadro® series.

• Due to internal issues related to runtime, C API may not work as intended. To prevent this issue, all users of C API MUST follow the steps below.

1. Remove the currently installed NVIDIA driver from your PC.

2. Reboot your PC and install the DCH NVIDIA driver of which version is compatible with VisionPro Deep Learning 1.0.1 (457.09 or higher, or R460 U2 (461.09) or higher for NVIDIA RTX / Quadro®)

• Multiple GPUs are not supported efficiently for High Detail mode. You cannot get an advantage of using multiple GPUs when you proceed training or processing the other tool specifically with Green Classify Tool in High Detail mode at the same time. For example, when training or processing job of Focused mode and High Detail mode are simultaneously being processed, each job could be slower than just training or processing one job at a time.

 

Operating System (OS)

• Due to OS compatibility issues caused from NVIDIA drivers, Windows Server 2016 is not supported on VisionPro Deep Learning. For the users with Windows Server 2016 environment, upgrading from Windows Server 2016 to Windows Server 2019 is required for the utilization of VisionPro Deep Learning servers. Windows Server 2019 is only supported for 'servers' configured to use the Deep Learning Client/Server functionality.

 

Cognex Deep Learning Studio (GUI)

• During creating a report when you log off your PC, some of images are shown black. To avoid this issue, please do not log off your PC (neither turn off the remote environment nor lock screen) while you are creating a report.

 

Workspace

• Boost::filesystem::rename error occurs when the user or system repetitively saves the workspace in a short time. This is just an alert that there was an issue while saving. You can solve this problem only by saving the workspace again.
• Group is shown in the workspace imported from ViDi Suite.

• If you import workspaces including "Group" feature which are made 4.1 and before, "Group" is still displayed in Cognex Deep Learning Studio, but you cannot modify this.

• See the FAQ for the workaround for this issue.

• It is recommended to delete "Group" in the previous workspaces and import to Cognex Deep Learning Studio.

• Especially with bigger than 10GB workspaces,
  • Cloning work does not end when you clone tools in different big workspaces at the same time.
  • Some images are not included in the created report.

 

Tools - General

• If a tool is not saved well because of unspecific reasons, you cannot export or clone the workspace or the tool. You can avoid this problem by processing the tools again and save the workspace.

 

Tools - Red Analyze

• Processing results are different between GPU and CPU. The difference is in the second decimal place of the result. For example, When you process with CPU and GPU respectively, different results can be obtained, such as 0.80 and 0.81.

• Defect regions do not extend to the left side of the view in Red Analyze Tool. To avoid this problem, when the defect area touches the left side of the image, please set 4 pixels wider ROI than the original image size. For example, if you have (x=0,y=0,w=100,h=100) image and it has detected area touch to left side of the image, please set (x=-4, y=0, w=104, h=100) ROI size.

• When you set the smaller feature size (especially smaller than 10) and train the Red Analyze tool (both in Supervised and Unsupervised mode), the workspace is getting bigger. The vvb file which is for saving heat map within the workspace is the main reason. For example:
  • feature size=10, sampling density=3, 8192x8192 image: 1 vvb file size=94MB
  • feature size=10, sampling density=10, 8192x8192 image: 1 vvb file size=1GB
  • feature size=40, sampling density=3, 8192x8192 image: 1 vvb file size=23KB

• For Red Analyze Tool, the area of a marked defect region and the area of a labeled defect region which is created by accepting (right-click on a marked region → click Accept Region) that marked region, is slightly different from each other.

• Erasing maskings/regions in the mask/region editor pane (Edit Mask or Edit Region in right-click popup menu on the image display area) applies Gaussian smoothing on all the regions/maskings. This causes the entire maskings/regions to shift slightly and their sizes to be changed slightly. This issue has been an existing issue from VisionPro ViDi.

 

Tools - Green Classify

• Once you are done with training High Detail mode of Green Classify Tool, you cannot change the name of the class.

 

Tools - Blue Read

• For Blue Read, the markings are displayed on the view regardless of the Marking checkbox in Image File Information is whether enabled or disabled. This issue has existed since ViDi 4.1.

 

VisionPro Deep Learning Service

• MultipleDevicesPerTool is no longer supported for VisionPro Deep Learning. Therefore you will have an “One or more error occurred” error if you select “--gpu-mode =MultipleDevicesPerTool” for service. Please choose another option to run VisionPro Deep Learning Service.

 

Migration from SuaKIT or The Past VisionPro Deep Learning Versions

• High Detail mode uses a different resize algorithm to SuaKIT (Green Classify Tool in High Detail mode only). To use an imported SuaKIT model with VPDL runtime API, please use SuaKIT resize API before processing.

 

Integration with VisionPro

• Due to the currently limited support of VisionPro 10, the external ROI is not supported for a DLRuntimeTool Edit Control Panel in VisionPro 10 for the time being.