ljjcoder

@knazeri ，thanks for your reply！do you mean that it only needs to change the mask = self.resize(mask, imgh, imgw) to mask = self.resize(mask, imgh, imgw,centerCrop=False)? if only do this ,the...

@knazeri I also ask what is different between Data of Places-Extra69 and Data of Places365-Challenge 2016? which one do you use? or both of them are used?

@knazeri yes, I download the high-resolution version of the Places2. I still feel confused that if I just change change the the mask = self.resize(mask, imgh, imgw) to mask =...

@knazeri ，thanks for your reply！when test the fid on places2 ，the score is reasonable（the better result from a human point of view will get lower fid scores）.But when test it...

@knazeri , On celebA, the mask hole is 128x128 square, and the image is 256x256, I test 1000 images, I get fid score is 14.24 use CA model. but I...

@jingyuanli001 I try to train places2 with your code，however it works slow. if i trained the model with your suggested parameter(2000000) and finutune(1000000), it will cost 2 month to finish....

@KaiWU5 ,I train the fixmatch-ccssl with label 4--(seeds=5)。However, I only get the 60.22 acc which is lower than yours. I noticed that in fixmatch_ccssl.py, the output of self.cfg.get("contrast_left_out", False) is...

@KaiWU5 Thanks for your prompt reply, I have one more question. Since your code refactors fixmatch's original code, this changes the randomness to some extent. For a fair comparison, fixmatch...

@KaiWU5 Thank you for answering my doubts, by the way your method is very performant and concise. Nice work!

@KaiWU5 Thank you for your reply! I will try it