issue when using custom dataset

[vainaixr]

I attempted to run this siamese network on a custom dataset of comic character faces, but got the error "all input arrays must have the same shape"

I am using the moeimouto-faces dataset, and ran this jupyter notebook on it.
Dataset - https://www.kaggle.com/mylesoneill/tagged-anime-illustrations/home

how to solve this issue?

[eldarovich99]

I am interesting in this issue too, I tried to train model on at&t facedatabase and I catch this error. Did you cope with the problem?

[eldarovich99]

Check your margin in try-catch block, my error was caused by this.

[vainaixr]

@eldarovich99 what did you do? where you able to run on custom dataset?

[Emirismail]

@vainaijr , please check the shape of your dataset images. It must have all the same shape.
Please try this code:
for object_folder in os.listdir(path):
print(object_folder)
image_path = os.path.join(path,object_folder)
for image_name in os.listdir(image_path):
image_path_1 = os.path.join(image_path, image_name)
image = imread(image_path_1)
print(image_name, image.shape)

[manmohansingh01]

how can i make all images of same shape

[kbmeena]

how can i make all images of same shape

use imresize

[ShrideviReddy]

Check size of your dataset images. Change layer dimension accordingly.