which indicates that you provided a single image with shape (H, W, C) instead. If that is the case, you should use augment_image(image)

[billhhh]

You provided a numpy array of shape (1083L, 1200L, 3L) as input to augment_images(), which was interpreted as (N, H, W). The last dimension however has value 1 or 3, which indicates that you provided a single image with shape (H, W, C) instead. If that is the case, you should use augment_image(image) or augment_images([image]), otherwise you will not get the expected augmentations. "you will not get the expected augmentations." % (images_copy.shape,))

what is that mean

[aleju]

You called augment_images() with a single image, but that function is intended for multiple images. Either call augment_image(image) or do something like augment_images([image])[0].

[billhhh]

Got it, thanks

[Erotemic]

Should this be closed?