So if you download and untar the data set in this tutorial 图像分类 | TensorFlow Core,
and run the command PIL.Image.open(str(roses[1])), There is a woman on a horse.
is this intended?
So if you download and untar the data set in this tutorial 图像分类 | TensorFlow Core,
and run the command PIL.Image.open(str(roses[1])), There is a woman on a horse.
is this intended?
Thank you for reporting the issue.
They are flowers indeed
Maybe they could use GitHub - facebookresearch/odin: A simple and effective method for detecting out-of-distribution images in neural networks.