Table 4 Data augmenting techniques used.
From: An attention based hybrid approach using CNN and BiLSTM for improved skin lesion classification
Transformation | Description | Parameters |
|---|---|---|
Rescaling | Scales pixel values to a range between 0 and 1. | Rescale = 1/255 |
Rotation | Rotates the image by a random degree within a specified range. | Rotation_range = 20 (degrees) |
Width Shift | Shifts the image horizontally by a fraction of the total width. | Width_shift_range = 0.1 |
Height Shift | Shifts the image vertically by a fraction of the total height. | Height_shift_range = 0.1 |
Zoom | Zooms in or out of the image within a specified range. | Zoom_range = 0.1 |
Shear | Applies a shear transformation to the image. | Shear_range = 10 (degrees) |
Horizontal Flip | Randomly flips the image horizontally. | Horizontal_flip = True |
Fill Mode | Fills gaps caused by transformations using the nearest pixel values. | Fill_mode=’nearest’ |
Validation Rescaling | Standardizes pixel values for validation data by dividing by 255. | Rescale = 1/255 |
