...
The algorithm (machine learning) learns from the annotaded annotated data, which was used from the Traning Training set of images.
The set of Testing Images are then used to create a is then evaluated using the Prediction Model, which is finally used to provide a first set of statistics. The statistics can be used to verify if the Bad Parts from Test Images are indeed indentified identified by the Prediction Model.
On the other hand, for the unsupervised model, unannotated (unlabeled) data is provided and the algorithm tries to make sense of by extracting features and patterns on its own.
PEKAT VISION software run offers training of models using both Supervised and Unsupervised methods. Detailed modules information can be found within the article Modules.
The Unsupervised module available is Artificial Intelligence Modules Anomaly Detector,where the only required end-user input is to assign at least 1 image 10 images to as ‘OK’ class.
The remaining modules are supervised, where the end-user is required to perform detailed annotations, however, the results are extremely accurate.
...
The Training mode for PEKAT are is available for the following Modules:
...
Below you can find a Training Overview Fluxogram, which demonstrates the overall training steps. However, for detailed training information about a specific module each module, please access the desired module’s page.
Training Graph - Loss Function Chart
...
Surface Detection (Chart not available for option Type 2 - Experimental - The number of tranining training cycles is defined by end-user before starting the training)
Based on the chart displayed, its graph gives you indication for the ideal moment to stop the training model from running.
The graph should gradually decrease over the training duration, because as the graph descreasesdecreases, training model results are improving.
Note that the Training Model can be finished at any time, however, one of the following scenarios are the optimal moment :
...
is when the chart is not decreasing anymore (sideways graph)
...
.
As shown below, the graph decreased over time at first and then near the end it had been already below one the green lines not been decreasing for a while, therefore, the end-user should click on 'Finish Training' button in order to evaulate evaluate the results.
Please note the chart is not available for the Module Anomaly of Surface, since by default we have the following:
Fast Training - Minimum amount of training cycle cycles pre-determined by the software
...
As described above, for both functions, the number of epochs is determined before training starts, therefore loss function graph is not available.
Avoiding Overfitting
We would like to highlight that our algorithm is designed to prevent overfitting.
Another reason for that is due the fact that Machine Learning is applied initially to the Trainning Images set, therefore, while performing deep training, the Error Overfitting is a situation when the model becomes so specific to the training set that it starts to lose the ability to generalize and has bad results on different (testing) images. While performing training, the Loss Function graph is displayed, showing the error in relation to the Traning Images set.the Training image set. In some cases, Validation image set can be used to evaluate how well the model performs on unseen images already during training. Overfitting zones are likely to happen in machine learning, when the loss function for the Validation set reaches its lowest peak as can be seen on this comparison between Training and Validation loss graphs.
...
There are several methods that help to prevent this situation from happening and we would like to highlight that our algorithm is designed to prevent overfitting.
If training is not interrupted when the graph is not decreasing anymore, the model will stop learningimproving, meaning that you will not achieve better results. However, this will not cause weakness to the model, in other words, this will not increase the presence of false positives/negatives - It it will just not provide better results. Therefore, if the graph is not deacreasing decreasing anymore, it means the model stopped from improving.
Considering that, overfitting zones are likely to happen in machine learning, when simultaneously comparison between Traning Images set & Testing Images set (Validation) is in place, and the Testing Set (Validation) reaches its lowest peak.
Extend Model
Extend model function is only available for the modules Classifier& , Detector and OCR.
This function allows you perform further training on an already trained model.
If you choose this option, the Network Type argumentation will be automatically set in compliance with the already trained model, as shown on pictures below:
...
Augmentation - Training Parameters
For detailed explaination explanation regarding argumentation augmentation (training parameters), visit the following article Augmentation Glossary.
...
At first, we recommend to run different models in Fast TraningTraining mode, using different sizes of view-finder and training parameters (brighness brightness resistance, resistance to deviation, etc.) to find out what combination works best in your case. When you find suitable settings, but you would like to achieve even more precise results, you may try Deep Training mode, with more training cycles, however, using the same training parameters (settings).
...