Open meetps opened 7 years ago
WRT
https://github.com/warmspringwinds/tf-image-segmentation/blob/master/tf_image_segmentation/utils/tf_records.py#L37
I think you should reconsider using scipy.misc.imread in place of PIL Image, because for VOC datasets, the PIL loads a grayscale image for the segmentation annotation, while a 3 channel input is necessary to determine the segments.
Hi,
Can you elaborate more?
I agree PIL is a bad dependency.
PIL
I needed a way to do this.
If it is possible to do with scipy.misc.imread, I would be glad to change it.
scipy.misc.imread
WRT
https://github.com/warmspringwinds/tf-image-segmentation/blob/master/tf_image_segmentation/utils/tf_records.py#L37
I think you should reconsider using scipy.misc.imread in place of PIL Image, because for VOC datasets, the PIL loads a grayscale image for the segmentation annotation, while a 3 channel input is necessary to determine the segments.