You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
cv2.resize deforms the images and thus leads to bad learning
Instead I used the random crop function to always crop the image instead of deforming it
it's not and ideal fix but it leads to way better performances
Hi,
I found that you resize images with opencv for the validation (see val_generator arguments)
Keras-ICNet/utils.py
Lines 61 to 63 in 987a6aa
cv2.resize deforms the images and thus leads to bad learning
Instead I used the random crop function to always crop the image instead of deforming it
it's not and ideal fix but it leads to way better performances
change this line
Keras-ICNet/train
Line 48 in 987a6aa
to
val_generator = MapillaryGenerator(mode='validation', batch_size=opt.batch_size, crop_shape=(opt.image_width, opt.image_height))
and put this lines
Keras-ICNet/utils.py
Lines 91 to 92 in 987a6aa
out of the
if self.mode == 'training':
conditionNow in each validation iteration the image will not be resized but randomly cropped
The text was updated successfully, but these errors were encountered: