Green Classify Tool – High Detail Quick Mode

High Detail Quick mode uses an architecture which is different with Focused mode. Due to the architecture, High Detail Quick mode can get you more accurate results.

The way you create a model in High Detail Quick mode is basically same with Focused mode but High Detail Quick mode requires much less number of tool parameters to be tuned by hand. Also, you cannot assign multiple tags per view in High Detail Quick mode. Each view has only a single corresponding tag and it means that non-exclusive mode is not supported.

 

Green Classify High Detail Quick vs Green Classify Focused

Green Classify High Detail Quickmode uses an architecture which is different from that of Focused mode. Due to its architectural difference, it doesn't have Sampling Parameters in Tool Parameters pane as it samples from the entire view. The way you label images and create a neural network model in Green Classify High Detail Quick is basically the same as Focused mode, but it requires almost no parameters compared to Green Classify Focused.

 

Green Classify High Detail Quick vs Green Classify High Detail

High Detail Quick is different from High Detail mode as it adopted a different training algorithm, a one-of-kind one. Due to this backbone change, it became dramatically faster in training while keeping its classification accuracy only a little behind that of Green Classify High Detail. It does not use the validation set in training anymore and it does not require as many tool parameters as High Detail requires. Everything else is just the same as High Detail mode. Note that if the tool parameters are properly tuned, the accuracy of High Detail modes are higher than that of High Detail Quick modes on average.

 

Features

 Green Classify Focused Green Classify High Detail Green Classify High Detail Quick
View Inspector Supported without heat map Supported with heat map Supported with heat map
Loss Inspector Not supported Supported Not supported
Validation Set Not used in training Used in training Not used in training
VisionPro Deep Learning Tool Parameters Less parameters

More parameters for control*,
No sampling parameters

Almost no parameters
Multi-class Classification
(Non-Exclusive/Exclusive Mode)		 Supported Not supported Not supported
Resize Mode Not supported Supported Not Supported

* More training and perturbation parameters for detailed training control and granular adjustment

Note: To exploit all functions of each tool, go to Help and enable Expert Mode.

 

Training Process

The process for training High Detail Quick mode is:

  1. Collect images that represent the full range of each classification tag that you expect to encounter.

  2. Label the views with an appropriate tag and set the training set.

  3. Edit tool parameters.

  4. Resize the views if you need.

  5. Train the tool and check the result.

  6. You can check the result even if you stop in the middle of training of High Detail Quick mode. However, there would be no result or the result will not be updated when you stop in the middle of the preparing the training.