Training a Deep Learning Tool
In the API, to train a deep learning tool, call the EDeepLearningTool::Train(trainingDataset, validationDataset, numberOfIterations) method.
|
●
|
An Iteration corresponds to going through all the images in the training dataset once. |
|
□
|
The training process requires a large number of iterations to obtain good results. |
|
□
|
The training process requires a large number of iterations to obtain good results. |
|
□
|
The default number of iterations is 50. |
|
□
|
The larger the number of iterations, the longer the training is and the better the results you obtain. |
|
□
|
Calling the EDeepLearningTool::Train method several times with the same training and validation dataset is equivalent to calling it once but with a larger number of iterations. |
- You can add images to the training and validation dataset to train the tool to recognize new instances of your problem.
- We do not recommend that you remove images from the dataset as the tool might forget about these images during the new training phase.
|
●
|
The training process is asynchronous: |
|
●
|
The batch size corresponds to the number of image patches that are processed together. |
|
□
|
The training is influenced by the batch size. |
|
□
|
A large batch size increases the processing speed of a single iteration on a GPU but requires more memory. |
|
□
|
The training process is not able to learn a good model with too small batch sizes. |
|
□
|
It is common to choose powers of 2 as the batch size for performance reasons. |