numpy.random.randint gets [0,0) range in training

[Parskatt]

deq-flow/code.v.2.0/core/utils/augmentor.py

Line 105 in 869d4bc

y0 = np.random.randint(0, img1.shape[0] - self.crop_size[0])

The crop augmentation here introduces a bug when the crop size is equal to the image size. Then numpy.random.randint gets a [0,0) range and throws an exception. This happened for me with some images equal in size to the crop size. The solution seems to me to simply add a +1.

[Gsunshine]

Hi @Parskatt,

Thank you for letting me know this! I'll fix it in the next release! Thanks!
If you have any questions, please feel free to post it!

Best regards,
Zhengyang

[Parskatt]

@Gsunshine thanks for the quick response, great project :)