Manual

Table Of Contents
DobotVisionStudio User Guide
Issue V4.1.2 (2022-06-08) User Guide Copyright © Yuejiang Technology Co., Ltd.
153
Select the image to be trained, use the VisionTrain to train the image marking, and divide the
image types in the image set. See the user manual of VisionTrain for specific training methods.
Import the model trained by VisionTrain into the running parameter model file path of DL
module, as shown in the following figure.
Import the Gallery model file obtained during training into the Gallery path, as shown in the
following table:
After adding the Gallery path and model file path, click Execute to configure the parameters.
Running Parameters:
Model File Path: Select the model file created by the previous character training.
Saving Model in Solution: After enabling, save the model data to the solution file or
process file. When loading a solution across machines, you do not need to enter the model file path.
Gallery Path: It is generated together with the training model during training, and the path
of the gallery file is VisionTrain1.2.0\Applications\DeepLearningModel.
Top-K Category: The number of categories displayed in the result, with a value range of
1 to 10.
Min. Similarity: You can filter results whose search results are less than this value.
Gallery Management:
Search Category: You can search and delete categories in the gallery.
Register Image: You can create Gallery files manually.