Open shashankvasisht opened 2 years ago
Hi Vinthony,
I saw that you are resizing the input image to 256x256. Is there any support for variable size inputs?
hi, thanks for your attention. Actually, our model is fully convolutional which can be tested in any resolution directly. Currently, 256x256 is just a good choice for evaluation.
Hi Vinthony,
I saw that you are resizing the input image to 256x256. Is there any support for variable size inputs?