Data augmentation performs random transformations on images given to a deep learning tool (EClassifier, EUnsupervisedSegmenter or ESupervisedSegmenter object) during the training.
| ● | 다양한 설정을 실험하여 데이터 증가에 가장 적합한 매개 변수를 선택합니다. |
| ● | Configure data augmentation according to your problem. However, flips, shifts (20 - 40 px), brightness (5%), contrast (0.95 to 1.05) or salt and pepper noise (2%) can be useful on many datasets. |
| ● | 변형이 이미지의 레이블을 변경하지 않는지 확인합니다(예: 회전 또는 대비 변경으로 인해 사라지는 결함). |
With EasyLocate, we do not recommend to use rotation and shear data augmentation as it is not possible to compute the minimal bounding box surrounding the object after these geometric transformations.
In Deep Learning Studio
| ● | Create and configure the data augmentation settings in the Data augmentation tab. |
| ● | 최소 설정 (Lower limits augmentation), 최대 설정 (Upper limits augmentation) 또는 무작위 설정 (Random augmentation)을 사용하여 데이터 확대 이미지를 표시하고 검토하십시오. |
API에서
Use EClassificationDataset::SetEnableDataAugmentation(true/false) to enable or disable these transformations or directly use an object EDataAugmentation that you give to the method EDeepLearningTool::Train.
The transformations
기하학적 변환
| ● | Horizontal and vertical flips (enabled with EClassificationDataset::SetEnableHorizontalFlip and EClassificationDataset::SetEnableVerticalFlip) |
| ● | Scaling (between a minimum and maximum value defined with EClassificationDataset::SetMinScale and EClassificationDataset::SetMaxScale) |
| ● | Horizontal and vertical shifts (between –maxValue and maxValue defined with EClassificationDataset::SetMaxHorizontalShift(maxValue) and EClassificationDataset::SetMaxVerticalShift(maxValue)) |
| ● | Rotations (between 0 and a maximum value defined with EClassificationDataset::SetMaxRotationAngle) |
| ● | Horizontal and vertical shear (between –maxValue and maxValue defined with EClassificationDataset::SetMaxHorizontalShear and EClassificationDataset::SetMaxVerticalShear) |
색상 및 광도 변환
| ● | Brightness offset (between –maxValue and maxValue defined with EClassificationDataset::SetMaxBrightnessOffset) |
| ● | Contrast gain (between a minimum and maximum value defined with EClassificationDataset::SetMinContrastGain and EClassificationDataset::SetMaxContrastGain) |
| ● | Gamma corrections (between a minimum and maximum value defined with EClassificationDataset::SetMinGamma and EClassificationDataset::SetMaxGamma) |
| ● | Hue offset (between –maxValue and maxValue defined with EClassificationDataset::SetMaxHueOffset) |
| ● | Saturation gain (between a minimum and maximum value defined with EClassificationDataset::SetMinSaturationGain and EClassificationDataset::SetMaxSaturationGain) |
노이즈 변환
표준 편차는 최대 픽셀 값의 백분율로 표시됩니다.
| ● | Gaussian noise, also called additive white noise, generated with a standard deviation (between a minimum and maximum value defined with EClassificationDataset::SetGaussianNoiseMinimumStandardDeviation and EClassificationDataset::SetGaussianNoiseMaximumStandardDeviation) |
| ● | Speckle noise, a multiplicative noise, generated from a Gamma distribution with a mean of 1 and a standard deviation (between a minimum and a maximum value defined with EClassificationDataset::SetSpeckleNoiseMinimumStandardDeviation and EClassificationDataset::GetSpeckleNoiseMinimumStandardDeviation). |
| ● | Salt and pepper noise generated from a pixel density (between a minimum and a maximum value defined with EClassificationDataset:: SetSaltAndPepperNoiseMinimumDensity and EClassificationDataset::SetSaltAndPepperNoiseMaximumDensity). |