Release Information

The VisionPro Deep Learning 4.1 version introduces the following features, enhancements, and changes:

• Reduced the training Training is the process that your tool, which is a neural network, is learning about the features (pixels) based on the labels you made. For example, a tool will learn the defect/normal pixels in each image based on the defect/normal labels you drew. The goal of the tool Training is learning enough to give the correct inspection results of whether an unseen image is defective or not. The key to training is to ensure that you include all possible variations within your training set, and that your images are accurately labeled. Training times vary by the application, tool setup and the GPU in the PC being used to train the network. and preparation time for the Standard type tools. The reductions are more significant for Red Analyze tools that have larger images in the training set.

• A stage called optimizing resources is added before training. This stage can lead to faster training speeds during repeated training runs.

• Improved the system RAM and storage drive usage of Cognex Deep Learning Studio. This improvement provides better performance in areas such as labeling Labeling is the process of annotating an image with "ground truth". Depending on the tool that you are using, labeling can take different forms. You label an image set for two reasons: to provide the information needed to train the tool and to allow you to measure and validate the performance of the trained tool against the ground truth., tool training, tool processing, storage, and runtime export.

• Production mode is now available again. You can access it by clicking Production Mode in the Workspace toolbar menu same as before.

• The heatmap is now displayed in production mode for the Standard type Green Classify tool.

• Updated the Codemeter version from 7.51 to 8.20a.

• Added the Optimized for Green/Red Standard tool toggle to the Cognex Deep Learning Studio toolbar area, allowing you to easily toggle the Optimized GPU Memory option on and off.

• Introduced the heatmap-based label generator plugin. This plugin helps to convert heatmap results from Few Sample mode as labels.