Open zhuozhongshuo opened 2 years ago
Hi,
Hi,
- It doesn't matter whether using 256_256 or 512_512 for training. Our method is non-reference-based learning. So, you can achieve similar results.
- It is common to use different sizes for training and testing if you use a full convolution network.
- we used 512*512 to train our model.
thanks for your rapidly repsponse.
hi, thanks for your interesting work. And I have 3 problems:
thanks.